text-classification bool 2 classes | text stringlengths 0 664k |
|---|---|
false |
# Dataset Card for "conll2003"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [https://www.aclweb.org/anthology/W03-0419/](https://www.aclweb.org/anthology/W03-0419/)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Size of downloaded dataset files:** 4.85 MB
- **Size of the generated dataset:** 10.26 MB
- **Total amount of disk used:** 15.11 MB
### Dataset Summary
The shared task of CoNLL-2003 concerns language-independent named entity recognition. We will concentrate on
four types of named entities: persons, locations, organizations and names of miscellaneous entities that do
not belong to the previous three groups.
The CoNLL-2003 shared task data files contain four columns separated by a single space. Each word has been put on
a separate line and there is an empty line after each sentence. The first item on each line is a word, the second
a part-of-speech (POS) tag, the third a syntactic chunk tag and the fourth the named entity tag. The chunk tags
and the named entity tags have the format I-TYPE which means that the word is inside a phrase of type TYPE. Only
if two phrases of the same type immediately follow each other, the first word of the second phrase will have tag
B-TYPE to show that it starts a new phrase. A word with tag O is not part of a phrase. Note the dataset uses IOB2
tagging scheme, whereas the original dataset uses IOB1.
For more details see https://www.clips.uantwerpen.be/conll2003/ner/ and https://www.aclweb.org/anthology/W03-0419
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### conll2003
- **Size of downloaded dataset files:** 4.85 MB
- **Size of the generated dataset:** 10.26 MB
- **Total amount of disk used:** 15.11 MB
An example of 'train' looks as follows.
```
{
"id": "0",
"document_id": 1,
"sentence_id": 3,
"tokens": ["The", "European", "Commission", "said", "on", "Thursday", "it", "disagreed", "with", "German", "advice", "to", "consumers", "to", "shun", "British", "lamb", "until", "scientists", "determine", "whether", "mad", "cow", "disease", "can", "be", "transmitted", "to", "sheep", "."]
"pos_tags": [12, 22, 22, 38, 15, 22, 28, 38, 15, 16, 21, 35, 24, 35, 37, 16, 21, 15, 24, 41, 15, 16, 21, 21, 20, 37, 40, 35, 21, 7],
"ner_tags": [0, 3, 4, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
"chunk_tags": [11, 12, 12, 21, 13, 11, 11, 21, 13, 11, 12, 13, 11, 21, 22, 11, 12, 17, 11, 21, 17, 11, 12, 12, 21, 22, 22, 13, 11, 0],
}
```
The original data files have `-DOCSTART-` lines used to separate documents, but these lines are removed here.
Indeed `-DOCSTART-` is a special line that acts as a boundary between two different documents, and it is filtered out in this implementation.
### Data Fields
The data fields are the same among all splits.
#### conll2003
- `id`: a `string` feature.
- `document_id`: an `int32` feature tracking which document the sample is from.
- `sentence_id`: an `int32` feature tracking which sentence in this document the sample is from.
- `tokens`: a `list` of `string` features.
- `pos_tags`: a `list` of classification labels (`int`). Full tagset with indices:
```python
{'"': 0, "''": 1, '#': 2, '$': 3, '(': 4, ')': 5, ',': 6, '.': 7, ':': 8, '``': 9, 'CC': 10, 'CD': 11, 'DT': 12,
'EX': 13, 'FW': 14, 'IN': 15, 'JJ': 16, 'JJR': 17, 'JJS': 18, 'LS': 19, 'MD': 20, 'NN': 21, 'NNP': 22, 'NNPS': 23,
'NNS': 24, 'NN|SYM': 25, 'PDT': 26, 'POS': 27, 'PRP': 28, 'PRP$': 29, 'RB': 30, 'RBR': 31, 'RBS': 32, 'RP': 33,
'SYM': 34, 'TO': 35, 'UH': 36, 'VB': 37, 'VBD': 38, 'VBG': 39, 'VBN': 40, 'VBP': 41, 'VBZ': 42, 'WDT': 43,
'WP': 44, 'WP$': 45, 'WRB': 46}
```
- `chunk_tags`: a `list` of classification labels (`int`). Full tagset with indices:
```python
{'O': 0, 'B-ADJP': 1, 'I-ADJP': 2, 'B-ADVP': 3, 'I-ADVP': 4, 'B-CONJP': 5, 'I-CONJP': 6, 'B-INTJ': 7, 'I-INTJ': 8,
'B-LST': 9, 'I-LST': 10, 'B-NP': 11, 'I-NP': 12, 'B-PP': 13, 'I-PP': 14, 'B-PRT': 15, 'I-PRT': 16, 'B-SBAR': 17,
'I-SBAR': 18, 'B-UCP': 19, 'I-UCP': 20, 'B-VP': 21, 'I-VP': 22}
```
- `ner_tags`: a `list` of classification labels (`int`). Full tagset with indices:
```python
{'O': 0, 'B-PER': 1, 'I-PER': 2, 'B-ORG': 3, 'I-ORG': 4, 'B-LOC': 5, 'I-LOC': 6, 'B-MISC': 7, 'I-MISC': 8}
```
### Data Splits
| name |train|validation|test|
|---------|----:|---------:|---:|
|conll2003|14041| 3250|3453|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
From the [CoNLL2003 shared task](https://www.clips.uantwerpen.be/conll2003/ner/) page:
> The English data is a collection of news wire articles from the Reuters Corpus. The annotation has been done by people of the University of Antwerp. Because of copyright reasons we only make available the annotations. In order to build the complete data sets you will need access to the Reuters Corpus. It can be obtained for research purposes without any charge from NIST.
The copyrights are defined below, from the [Reuters Corpus page](https://trec.nist.gov/data/reuters/reuters.html):
> The stories in the Reuters Corpus are under the copyright of Reuters Ltd and/or Thomson Reuters, and their use is governed by the following agreements:
>
> [Organizational agreement](https://trec.nist.gov/data/reuters/org_appl_reuters_v4.html)
>
> This agreement must be signed by the person responsible for the data at your organization, and sent to NIST.
>
> [Individual agreement](https://trec.nist.gov/data/reuters/ind_appl_reuters_v4.html)
>
> This agreement must be signed by all researchers using the Reuters Corpus at your organization, and kept on file at your organization.
### Citation Information
```
@inproceedings{tjong-kim-sang-de-meulder-2003-introduction,
title = "Introduction to the {C}o{NLL}-2003 Shared Task: Language-Independent Named Entity Recognition",
author = "Tjong Kim Sang, Erik F. and
De Meulder, Fien",
booktitle = "Proceedings of the Seventh Conference on Natural Language Learning at {HLT}-{NAACL} 2003",
year = "2003",
url = "https://www.aclweb.org/anthology/W03-0419",
pages = "142--147",
}
```
### Contributions
Thanks to [@jplu](https://github.com/jplu), [@vblagoje](https://github.com/vblagoje), [@lhoestq](https://github.com/lhoestq) for adding this dataset.
|
false |
# Dataset Card for Business Scene Dialogue
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Github](https://raw.githubusercontent.com/tsuruoka-lab/BSD/)
- **Repository:** [Github](https://raw.githubusercontent.com/tsuruoka-lab/BSD/)
- **Paper:** [Rikters et al., 2019](https://www.aclweb.org/anthology/D19-5204)
- **Leaderboard:**
- **Point of Contact:** Matīss Rikters
### Dataset Summary
This is the Business Scene Dialogue (BSD) dataset,
a Japanese-English parallel corpus containing written conversations
in various business scenarios.
The dataset was constructed in 3 steps:
1) selecting business scenes,
2) writing monolingual conversation scenarios according to the selected scenes, and
3) translating the scenarios into the other language.
Half of the monolingual scenarios were written in Japanese
and the other half were written in English.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English, Japanese.
## Dataset Structure
### Data Instances
Each instance contains a conversation identifier, a sentence number that indicates its
position within the conversation, speaker name in English and Japanese,
text in English and Japanese, original language, scene of the scenario (tag),
and title of the scenario (title).
```python
{
"id": "190315_E004_13",
"no": 14,
"speaker": "Mr. Sam Lee",
"ja_speaker": "サム リーさん",
"en_sentence": "Would you guys consider a different scheme?",
"ja_sentence": "別の事業案も考慮されますか？",
"original_language": "en",
"tag": "phone call",
"title": "Phone: Review spec and scheme"
}
```
### Data Fields
- id: dialogue identifier
- no: sentence pair number within a dialogue
- en_speaker: speaker name in English
- ja_speaker: speaker name in Japanese
- en_sentence: sentence in English
- ja_sentence: sentence in Japanese
- original_language: language in which monolingual scenario was written
- tag: scenario
- title: scenario title
### Data Splits
- There are a total of 24171 sentences / 808 business scenarios.
- Train: 20000 sentences / 670 scenarios
- Dev: 2051 sentences / 69 scenarios
- Test: 2120 sentences / 69 scenarios
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
Dataset provided for research purposes only. Please check dataset license for additional information.
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
This dataset was released under the Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA) license.
### Citation Information
```
@inproceedings{rikters-etal-2019-designing,
title = "Designing the Business Conversation Corpus",
author = "Rikters, Mat{\=\i}ss and
Ri, Ryokan and
Li, Tong and
Nakazawa, Toshiaki",
booktitle = "Proceedings of the 6th Workshop on Asian Translation",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D19-5204",
doi = "10.18653/v1/D19-5204",
pages = "54--61"
}
```
### Contributions
Thanks to [@j-chim](https://github.com/j-chim) for adding this dataset. |
true |
# Dataset Card for NusaX-Senti
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Repository:** [GitHub](https://github.com/IndoNLP/nusax/tree/main/datasets/sentiment)
- **Paper:** [EACL 2022](https://arxiv.org/abs/2205.15960)
- **Point of Contact:** [GitHub](https://github.com/IndoNLP/nusax/tree/main/datasets/sentiment)
### Dataset Summary
NusaX is a high-quality multilingual parallel corpus that covers 12 languages, Indonesian, English, and 10 Indonesian local languages, namely Acehnese, Balinese, Banjarese, Buginese, Madurese, Minangkabau, Javanese, Ngaju, Sundanese, and Toba Batak.
NusaX-Senti is a 3-labels (positive, neutral, negative) sentiment analysis dataset for 10 Indonesian local languages + Indonesian and English.
### Supported Tasks and Leaderboards
- Sentiment analysis for Indonesian languages
### Languages
- ace: acehnese,
- ban: balinese,
- bjn: banjarese,
- bug: buginese,
- eng: english,
- ind: indonesian,
- jav: javanese,
- mad: madurese,
- min: minangkabau,
- nij: ngaju,
- sun: sundanese,
- bbc: toba_batak,
## Dataset Creation
### Curation Rationale
There is a shortage of NLP research and resources for the Indonesian languages, despite the country having over 700 languages. With this in mind, we have created this dataset to support future research for the underrepresented languages in Indonesia.
### Source Data
#### Initial Data Collection and Normalization
NusaX-senti is a dataset for sentiment analysis in Indonesian that has been expertly translated by native speakers.
#### Who are the source language producers?
The data was produced by humans (native speakers).
### Annotations
#### Annotation process
NusaX-senti is derived from SmSA, which is the biggest publicly available dataset for Indonesian sentiment analysis. It comprises of comments and reviews from multiple online platforms. To ensure the quality of our dataset, we have filtered it by removing any abusive language and personally identifying information by manually reviewing all sentences. To ensure balance in the label distribution, we randomly picked 1,000 samples through stratified sampling and then translated them to the corresponding languages.
#### Who are the annotators?
Native speakers of both Indonesian and the corresponding languages.
Annotators were compensated based on the number of translated samples.
### Personal and Sensitive Information
Personal information is removed.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
NusaX is created from review text. These data sources may contain some bias.
### Other Known Limitations
No other known limitations
## Additional Information
### Licensing Information
CC-BY-SA 4.0.
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Please contact authors for any information on the dataset.
### Citation Information
```
@misc{winata2022nusax,
title={NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages},
author={Winata, Genta Indra and Aji, Alham Fikri and Cahyawijaya,
Samuel and Mahendra, Rahmad and Koto, Fajri and Romadhony,
Ade and Kurniawan, Kemal and Moeljadi, David and Prasojo,
Radityo Eko and Fung, Pascale and Baldwin, Timothy and Lau,
Jey Han and Sennrich, Rico and Ruder, Sebastian},
year={2022},
eprint={2205.15960},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@afaji](https://github.com/afaji) for adding this dataset.
|
false |
# Dataset Card for [Dataset Name]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **[Repository](https://github.com/TevenLeScao/glucose)**
- **[Paper](https://arxiv.org/abs/2009.07758)**
- **Point of Contact:** [glucose@elementalcognition.com](mailto:glucose@elementalcognition.com)
### Dataset Summary
GLUCOSE: GeneraLized and COntextualized Story Explanations, is a novel conceptual framework and dataset for commonsense reasoning. Given a short story and a sentence X in the story, GLUCOSE captures ten dimensions of causal explanation related to X. These dimensions, inspired by human cognitive psychology, cover often-implicit causes and effects of X, including events, location, possession, and other attributes.
### Supported Tasks and Leaderboards
Common sense inference of:
1. Causes
2. Emotions motivating an event
3. Locations enabling an event
4. Possession states enabling an event
5. Other attributes enabling an event
6. Consequences
7. Emotions caused by an event
8. Changes in location caused by an event
9. Changes in possession caused by an event
10. Other attributes that may be changed by an event
### Languages
English, monolingual
## Dataset Structure
### Data Instances
```
{
"experiment_id": "e56c7c3e-4660-40fb-80d0-052d566d676a__4",
"story_id": "e56c7c3e-4660-40fb-80d0-052d566d676a",
"worker_id": 19,
"submission_time_normalized": "20190930",
"worker_quality_rating": 3,
"selected_sentence_index": 4,
"story": "It was bedtime at our house. Two of the three kids hit the pillow and fall asleep. The third is a trouble maker. For two hours he continues to get out of bed and want to play. Finally he becomes tired and falls asleep."
selected_sentence: "Finally he becomes tired and falls asleep.",
"1_specificNL": "The third kid continues to get out of bed and wants to play >Causes/Enables> The kid finally becomes tired and falls asleep",
"1_specificStructured": "{The third kid}_[subject] {continues}_[verb] {to }_[preposition1] {get out of bed}_[object1] {and wants to play}_[object2] >Causes/Enables> {The kid}_[subject] {finally becomes}_[verb] {tired}_[object1] {and falls asleep}_[object2]",
"1_generalNL": "Someone_A doesn't want to go to sleep >Causes/Enables> Someone_A finally falls asleep",
"1_generalStructured": "{Someone_A}_[subject] {doesn't want}_[verb] {to }_[preposition1] {go to sleep}_[object1] >Causes/Enables> {Someone_A}_[subject] {finally falls}_[verb] {asleep}_[object1]",
"2_specificNL": "escaped",
"2_specificStructured": "escaped",
"2_generalNL": "escaped",
"2_generalStructured": "escaped",
"3_specificNL": "The third kid is in bed >Enables> The kid finally becomes tired and falls asleep",
"3_specificStructured": "{The third kid}_[subject] {is}_[verb] {in}_[preposition] {bed}_[object] >Enables> {The kid}_[subject] {finally becomes}_[verb] {tired}_[object1] {and falls asleep}_[object2]",
"3_generalNL": "Someone_A is in bed >Enables> Someone_A falls asleep",
"3_generalStructured": "{Someone_A}_[subject] {is}_[verb] {in}_[preposition] {bed}_[object] >Enables> {Someone_A}_[subject] {falls}_[verb] {asleep}_[object1]",
"4_specificNL": "escaped",
"4_specificStructured": "escaped",
"4_generalNL": "escaped",
"4_generalStructured": "escaped",
"5_specificNL": "escaped",
"5_specificStructured": "escaped",
"5_generalNL": "escaped",
"5_generalStructured": "escaped",
"6_specificNL": "escaped",
"6_specificStructured": "escaped",
"6_generalNL": "escaped",
"6_generalStructured": "escaped",
"7_specificNL": "escaped",
"7_specificStructured": "escaped",
"7_generalNL": "escaped",
"7_generalStructured": "escaped",
"8_specificNL": "escaped",
"8_specificStructured": "escaped",
"8_generalNL": "escaped",
"8_generalStructured": "escaped",
"9_specificNL": "escaped",
"9_specificStructured": "escaped",
"9_generalNL": "escaped",
"9_generalStructured": "escaped",
"10_specificNL": "escaped",
"10_specificStructured": "escaped",
"10_generalNL": "escaped",
"10_generalStructured": "escaped",
"number_filled_in": 7
}
```
### Data Fields
- __experiment_id__: a randomly generated alphanumeric sequence for a given story with the sentence index appended at the end after two underscores. Example: cbee2b5a-f2f9-4bca-9630-6825b1e36c13__0
- __story_id__: a random alphanumeric identifier for the story. Example: e56c7c3e-4660-40fb-80d0-052d566d676a
- __worker_id__: each worker has a unique identificaiton number. Example: 21
- __submission_time_normalized__: the time of submission in the format YYYYMMDD. Example: 20200115
- __worker_quality_assessment__: rating for the worker on the assignment in the row. Example: 2
- __selected_sentence_index__: the index of a given sentence in a story. Example: 0
- __story__: contains the full text of the ROC story that was used for the HIT. Example: It was bedtime at our house. Two of the three kids hit the pillow and fall asleep. The third is a trouble maker. For two hours he continues to get out of bed and want to play. Finally he becomes tired and falls asleep.
- __selected_sentence__: the sentence from the story that is being annotated. Example: It was bedtime at our house.
- __[1-10]\_[specific/general][NL/Structured]__: This is the primary data collected. It provides the common sense knowledge about the related stories and those general rules about the world derived from the specific statements. For each of the ten relationships, there are four columns. The specific columns give the specific statements from the story. The general statements give the corresponding generalization. The NL columns are formatted in natural language, whereas the structured columns contain indications of the slots used to fill in the data. Example:
- __1_specificNL__: "The school has a football team >Causes/Enables> The football game was last weekend"
- __1_specificStructured__: "{The school }\_[subject] {has }\_[verb] {a football team }\_[object1] >Causes/Enables> {The football game }\_[subject] {was last weekend }\_[verb]"
- __1_generalNL__: "Somewhere_A (that is a school ) has Something_A (that is a sports team ) >Causes/Enables> The game was last weekend"
- __1_generalStructured__: "{Somewhere_A ||that is a school ||}\_[subject] {has }\_[verb] {Something_A ||that is a sports team ||}\_[object1] >Causes/Enables> {The game }\_[subject] {was last weekend }\_[verb]"
- __number\_filled\_in__: number of dimensions filled in for the assignment. Example: 4
### Data Splits
Train split: 65,521 examples
Test splits: 500 examples, without worker id and rating, number filled in, and structured text.
## Dataset Creation
### Curation Rationale
When humans read or listen, they make implicit commonsense inferences that frame their understanding of what happened and why. As a step toward AI systems that can build similar mental models, we introduce GLUCOSE, a large-scale dataset of implicit commonsense causal knowledge, encoded as causal mini-theories about the world, each grounded in a narrative context.
### Source Data
#### Initial Data Collection and Normalization
Initial text from ROCStories
#### Who are the source language producers?
Amazon Mechanical Turk.
### Annotations
#### Annotation process
To enable developing models that can build mental models of narratives, we aimed to crowdsource a large, quality-monitored dataset. Beyond the scalability benefits, using crowd workers (as opposed to a small set of expert annotators) ensures diversity of thought, thus broadening coverage of a common-sense knowledge resource. The annotation task is complex: it requires annotators to understand different causal dimensions in a variety of contexts and to come up with generalized theories beyond the story context. For
strict quality control, we designed a three-stage knowledge acquisition pipeline for crowdsourcing the GLUCOSE dataset on the Amazon Mechanical Turk Platform. The workers first go through a qualification test where they must score at least 90% on 10 multiple-choice questions on select GLUCOSE dimensions. Next, qualified workers can work on the main GLUCOSE data collection task: given a story S and a story sentence X, they are asked to fill in (allowing for non-applicable) all ten GLUCOSE dimensions, getting step-by-step guidance from the GLUCOSE data acquisition. To ensure data consistency, the same workers answer all dimensions for an S, X pair. Finally, the submissions are reviewed by an expert who rates each worker on a scale from 0 to 3, and provides feedback on how to improve. Our final UIs are the result of more than six rounds of pilot studies, iteratively improving the interaction elements, functionality, dimension definitions, instructions, and examples.
#### Who are the annotators?
Amazon Mechanical Turk workers, with feedback from an expert.
### Personal and Sensitive Information
No personal or sensitive information.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Nasrin Mostafazadeh, Aditya Kalyanpur, Lori Moon, David Buchanan, Lauren Berkowitz, Or Biran, Jennifer Chu-Carroll, from Elemental Cognition
### Licensing Information
Creative Commons Attribution-NonCommercial 4.0 International Public License
### Citation Information
```
@inproceedings{mostafazadeh2020glucose,
title={GLUCOSE: GeneraLized and COntextualized Story Explanations},
author={Nasrin Mostafazadeh and Aditya Kalyanpur and Lori Moon and David Buchanan and Lauren Berkowitz and Or Biran and Jennifer Chu-Carroll},
year={2020},
booktitle={The Conference on Empirical Methods in Natural Language Processing},
publisher={Association for Computational Linguistics}
}
```
### Contributions
Thanks to [@TevenLeScao](https://github.com/TevenLeScao) for adding this dataset. |
false | ---
# Dataset Card for CAIL 2018
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Github](https://github.com/thunlp/CAIL/blob/master/README_en.md)
- **Repository:** [Github](https://github.com/thunlp/CAIL)
- **Paper:** [Arxiv](https://arxiv.org/abs/1807.02478)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@JetRunner](https://github.com/JetRunner) for adding this dataset. |
false |
# Dataset Card for SEDE
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Repository:** https://github.com/hirupert/sede
- **Paper:** https://arxiv.org/abs/2106.05006
- **Leaderboard:** https://paperswithcode.com/sota/text-to-sql-on-sede
- **Point of Contact:** [email](moshe@hirupert.com)
### Dataset Summary
SEDE (Stack Exchange Data Explorer) is a dataset for Text-to-SQL tasks with more than 12,000 SQL queries and their natural language description. It's based on a real usage of users from the Stack Exchange Data Explorer platform, which brings complexities and challenges never seen before in any other semantic parsing dataset like including complex nesting, dates manipulation, numeric and text manipulation, parameters, and most importantly: under-specification and hidden-assumptions.
### Supported Tasks and Leaderboards
- `parsing`: The dataset can be used to train a model for Text-to-SQL task. A Seq2Seq model (e.g. T5) can be used to solve the task. A model with more inductive-bias (e.g. a model with a grammar-based decoder) or an interactive settings for Text-to-SQL (https://arxiv.org/abs/2005.02539) can improve the results further. The model performance is measured by how high its [PCM-F1](https://arxiv.org/abs/2106.05006) score is. A [t5-large](https://huggingface.co/t5-large) achieves a [PCM-F1 of 50.6](https://arxiv.org/abs/2106.05006).
### Languages
The text in the dataset is in English. The associated BCP-47 code is `en`.
## Dataset Structure
### Data Instances
A typical data point comprises a question title, (optionally) a description and its underlying SQL query. In addition, each sample has a unique ID (from the Stack Exchange Data Explorer), its creation date and a boolean flag named `validated` if this sample was validated to be in gold quality by humans, see the paper for full details regarding the `validated` flag.
An instance for example:
```
{
'QuerySetId':1233,
'Title':'Top 500 Askers on the site',
'Description':'A list of the top 500 askers of questions ordered by average answer score excluding community wiki closed posts.',
'QueryBody':'SELECT * FROM (\nSELECT \n TOP 500\n OwnerUserId as [User Link],\n Count(Posts.Id) AS Questions,\n CAST(AVG(CAST(Score AS float)) as numeric(6,2)) AS [Average Question Score]\nFROM\n Posts\nWHERE \n PostTypeId = 1 and CommunityOwnedDate is null and ClosedDate is null\nGROUP BY\n OwnerUserId\nORDER BY\n Count(Posts.Id) DESC\n)ORDER BY\n [Average Question Score] DESC',
'CreationDate':'2010-05-27 20:08:16',
'validated':true
}
```
### Data Fields
- QuerySetId: a unique ID coming from the Stack Exchange Data Explorer.
- Title: utterance title.
- Description: utterance description (might be empty).
- QueryBody: the underlying SQL query.
- CreationDate: when this sample was created.
- validated: `true` if this sample was validated to be in gold quality by humans.
### Data Splits
The data is split into a training, validation and test set. The validation and test set contain only samples that were validated by humans to be in gold quality.
Train Valid Test
10309 857 857
## Dataset Creation
### Curation Rationale
Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of the richness and variety of natural-occurring utterances, where humans ask about data they need or are curious about. SEDE contains a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset. There is a large gap between the performance on SEDE compared to other common datasets, which leaves a room for future research for generalisation of Text-to-SQL models.
### Source Data
#### Initial Data Collection and Normalization
To introduce a realistic Text-to-SQL benchmark, we gather SQL queries together with their titles and descriptions from a naturally occurring dataset: the Stack Exchange Data Explorer. Stack Exchange is an online question & answers community, with over 3 million questions asked. However in its raw form many of the rows are duplicated or contain unusable queries or titles. The reason for this large difference between the original data size and the cleaned version is that any time that the author of the query executes it, an entry is saved to the log. To alleviate these issues, we write rule-based filters that remove bad queries/descriptions pairs with high precision. For example, we filter out examples with numbers in the description, if these numbers do not appear in the query (refer to the preprocessing script in the repository for the complete list of filters and the number of examples each of them filter). Whenever a query has multiple versions due to multiple executions, we take the last executed query which passed all filters. After this filtering step, we are left with 12,309 examples. Using these filters cleans most of the noise, but not all of it. To complete the cleaning process, we manually go over the examples in the validation and test sets, and either filter-out wrong examples or perform minimal changes to either the utterances or the queries (for example, fix a wrong textual value) to ensure that models are evaluated with correct data. The final number of all training, validation and test examples is 12,023.
#### Who are the source language producers?
The language producers are Stack Exchange Data Explorer (https://data.stackexchange.com/) users.
### Annotations
#### Annotation process
[N/A]
#### Who are the annotators?
[N/A]
### Personal and Sensitive Information
All the data in the dataset is for public use.
## Considerations for Using the Data
### Social Impact of Dataset
We hope that the release of this challenging dataset will encourage research on improving generalisation for real-world SQL prediction that will help non technical business users acquire the data they need from their company's database.
### Discussion of Biases
[N/A]
### Other Known Limitations
[Needs More Information]
## Additional Information
### Dataset Curators
The dataset was initially created by Moshe Hazoom, Vibhor Malik and Ben Bogin, during work done at Ruper.
### Licensing Information
Apache-2.0 License
### Citation Information
```
@misc{hazoom2021texttosql,
title={Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data},
author={Moshe Hazoom and Vibhor Malik and Ben Bogin},
year={2021},
eprint={2106.05006},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@Hazoom](https://github.com/Hazoom) for adding this dataset. |
true |
# Dataset Card for DKHate
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Paper:** https://aclanthology.org/2021.nodalida-main.53/
- **Direct Download**: https://danlp-downloads.alexandra.dk/datasets/game_tweets.zip
### Dataset Summary
This dataset consists of anonymised Danish Twitter data that has been annotated for sentiment analysis through crowd-sourcing. All credits go to the authors of the following paper, who created the dataset:
[Pauli, Amalie Brogaard, et al. "DaNLP: An open-source toolkit for Danish Natural Language Processing." Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa). 2021](https://aclanthology.org/2021.nodalida-main.53/)
### Supported Tasks and Leaderboards
This dataset is suitable for sentiment analysis.
### Languages
This dataset is in Danish.
## Dataset Structure
### Data Instances
Every entry in the dataset has a tweet and an associated label.
### Data Fields
An entry in the dataset consists of the following fields:
- `text` (`str`): The tweet content.
- `label` (`str`): The label of the `text`. Can be "positiv", "neutral" or "negativ" for positive, neutral and negative sentiment, respectively.
### Data Splits
A `train` and `test` split is available, with the test split being 30% of the dataset, randomly sampled in a stratified fashion. There are 2,437 tweets in the training split and 1,047 in the test split.
## Additional Information
### Dataset Curators
The collection and annotation of the dataset is solely due to the authors of [the original paper](https://aclanthology.org/2021.nodalida-main.53/): Amalie Brogaard Pauli, Maria Barrett, Ophélie Lacroix and Rasmus Hvingelby. The tweets have been anonymised by [@saattrupdan](https://github.com/saattrupdan).
### Licensing Information
The dataset is released under the CC BY 4.0 license.
### Citation Information
```
@inproceedings{pauli2021danlp,
title={DaNLP: An open-source toolkit for Danish Natural Language Processing},
author={Pauli, Amalie Brogaard and Barrett, Maria and Lacroix, Oph{\'e}lie and Hvingelby, Rasmus},
booktitle={Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)},
pages={460--466},
year={2021}
}
```
### Contributions
Thanks to [@saattrupdan](https://github.com/saattrupdan) for adding this dataset to the Hugging Face Hub. |
true |
# Dataset Card for [Dataset Name]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:**
https://klejbenchmark.com/
- **Repository:**
https://github.com/allegro/klejbenchmark-allegroreviews
- **Paper:**
KLEJ: Comprehensive Benchmark for Polish Language Understanding (Rybak, Piotr and Mroczkowski, Robert and Tracz, Janusz and Gawlik, Ireneusz)
- **Leaderboard:**
https://klejbenchmark.com/leaderboard/
- **Point of Contact:**
klejbenchmark@allegro.pl
### Dataset Summary
Allegro Reviews is a sentiment analysis dataset, consisting of 11,588 product reviews written in Polish and extracted from Allegro.pl - a popular e-commerce marketplace. Each review contains at least 50 words and has a rating on a scale from one (negative review) to five (positive review).
We recommend using the provided train/dev/test split. The ratings for the test set reviews are kept hidden. You can evaluate your model using the online evaluation tool available on klejbenchmark.com.
### Supported Tasks and Leaderboards
Product reviews sentiment analysis.
https://klejbenchmark.com/leaderboard/
### Languages
Polish
## Dataset Structure
### Data Instances
Two tsv files (train, dev) with two columns (text, rating) and one (test) with just one (text).
### Data Fields
- text: a product review of at least 50 words
- rating: product rating of a scale of one (negative review) to five (positive review)
### Data Splits
Data is splitted in train/dev/test split.
## Dataset Creation
### Curation Rationale
This dataset is one of nine evaluation tasks to improve polish language processing.
### Source Data
#### Initial Data Collection and Normalization
The Allegro Reviews is a set of product reviews from a popular e-commerce marketplace (Allegro.pl).
#### Who are the source language producers?
Customers of an e-commerce marketplace.
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Allegro Machine Learning Research team klejbenchmark@allegro.pl
### Licensing Information
Dataset licensed under CC BY-SA 4.0
### Citation Information
@inproceedings{rybak-etal-2020-klej,
title = "{KLEJ}: Comprehensive Benchmark for Polish Language Understanding",
author = "Rybak, Piotr and Mroczkowski, Robert and Tracz, Janusz and Gawlik, Ireneusz",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.acl-main.111",
pages = "1191--1201",
}
### Contributions
Thanks to [@abecadel](https://github.com/abecadel) for adding this dataset. |
false | # Gameplay Images
## Dataset Description
- **Homepage:** [kaggle](https://www.kaggle.com/datasets/aditmagotra/gameplay-images)
- **Download Size** 2.50 GiB
- **Generated Size** 1.68 GiB
- **Total Size** 4.19 GiB
A dataset from [kaggle](https://www.kaggle.com/datasets/aditmagotra/gameplay-images).
This is a dataset of 10 very famous video games in the world.
These include
- Among Us
- Apex Legends
- Fortnite
- Forza Horizon
- Free Fire
- Genshin Impact
- God of War
- Minecraft
- Roblox
- Terraria
There are 1000 images per class and all are sized `640 x 360`. They are in the `.png` format.
This Dataset was made by saving frames every few seconds from famous gameplay videos on Youtube.
※ This dataset was uploaded in January 2022. Game content updated after that will not be included.
### License
CC-BY-4.0
## Dataset Structure
### Data Instance
```python
>>> from datasets import load_dataset
>>> dataset = load_dataset("Bingsu/Gameplay_Images")
DatasetDict({
train: Dataset({
features: ['image', 'label'],
num_rows: 10000
})
})
```
```python
>>> dataset["train"].features
{'image': Image(decode=True, id=None),
'label': ClassLabel(num_classes=10, names=['Among Us', 'Apex Legends', 'Fortnite', 'Forza Horizon', 'Free Fire', 'Genshin Impact', 'God of War', 'Minecraft', 'Roblox', 'Terraria'], id=None)}
```
### Data Size
download: 2.50 GiB<br>
generated: 1.68 GiB<br>
total: 4.19 GiB
### Data Fields
- image: `Image`
- A `PIL.Image.Image object` containing the image. size=640x360
- Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the "image" column, i.e. `dataset[0]["image"]` should always be preferred over `dataset["image"][0]`.
- label: an int classification label.
Class Label Mappings:
```json
{
"Among Us": 0,
"Apex Legends": 1,
"Fortnite": 2,
"Forza Horizon": 3,
"Free Fire": 4,
"Genshin Impact": 5,
"God of War": 6,
"Minecraft": 7,
"Roblox": 8,
"Terraria": 9
}
```
```python
>>> dataset["train"][0]
{'image': <PIL.PngImagePlugin.PngImageFile image mode=RGBA size=640x360>,
'label': 0}
```
### Data Splits
| | train |
| ---------- | -------- |
| # of data | 10000 |
### Note
#### train_test_split
```python
>>> ds_new = dataset["train"].train_test_split(0.2, seed=42, stratify_by_column="label")
>>> ds_new
DatasetDict({
train: Dataset({
features: ['image', 'label'],
num_rows: 8000
})
test: Dataset({
features: ['image', 'label'],
num_rows: 2000
})
})
```
|
false |
# Generated_Chat_0.4M
## 内容
包含约40万条由[BELLE](https://github.com/LianjiaTech/BELLE)项目生成的个性化角色对话数据，包含角色介绍。
注意：此数据集是由ChatGPT产生的，未经过严格校验，题目或解题过程可能包含错误。使用过程中请注意这一点。
## 样例
```
{
"instruction": "于以下角色信息完成一段对话\nAlice是一个年轻的律师，她正在为一个涉及濒危物种保护的案件做准备。Bob是一位当地的居民，他所在的社区经常受到该濒危物种的干扰。\n",
"input": "",
"output": "\nAlice: 你好Bob，我是濒危物种保护案的律师，很高兴见到你。我们前几天发给你的文件你看到了吗？\nBob: 看到了，你们说要禁止我们在该物种的常住地采集蘑菇，这很不公平。\nAlice: 保护濒危物种对整个生态系统都很重要，如果我们的举动损害了这个物种的生存，那么整个生态系统都将遭受损失。\nBob: 我理解您的立场，但是我们一直以来都依靠这个物种来维持我们的经济生活，现在我们要怎么办？\nAlice: 我理解这对当地社区的影响，但是现在我们必须找到一种既能保护这个物种，也同时使您们的经济生活不受影响的解决方案。你有任何想法吗？我们可以一起来想办法。\n"
}
```
### 字段
```
instruction: 指令
input: 输入（本数据集均为空）
output: 输出
```
## 局限性和使用限制
我们要求开发者仅将我们开源的代码、数据、模型及后续衍生物用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。
由于数据是由*ChatGPT*生成的，未经严格验证，在事实性和其他方面还存在一些不足。因此，在使用此数据集时，请务必注意甄别。
本数据集不代表任何一方的立场、利益或想法，无关任何团体的任何类型的主张。因使用本数据集带来的任何损害、纠纷，本项目的开发者不承担任何责任。
***
# Generated_Chat_0.4M
## Contents
Includes approx. 400k Personalized Character Dialogue generated by BELLE, with character Introduction.
Note: this subset was generated by *ChatGPT* and was not strictly verified. The quizzes or answers might contain errors. Please take this in mind when using this subset.
## Sample
```
{
"instruction": "于以下角色信息完成一段对话\nAlice是一个年轻的律师，她正在为一个涉及濒危物种保护的案件做准备。Bob是一位当地的居民，他所在的社区经常受到该濒危物种的干扰。\n",
"input": "",
"output": "\nAlice: 你好Bob，我是濒危物种保护案的律师，很高兴见到你。我们前几天发给你的文件你看到了吗？\nBob: 看到了，你们说要禁止我们在该物种的常住地采集蘑菇，这很不公平。\nAlice: 保护濒危物种对整个生态系统都很重要，如果我们的举动损害了这个物种的生存，那么整个生态系统都将遭受损失。\nBob: 我理解您的立场，但是我们一直以来都依靠这个物种来维持我们的经济生活，现在我们要怎么办？\nAlice: 我理解这对当地社区的影响，但是现在我们必须找到一种既能保护这个物种，也同时使您们的经济生活不受影响的解决方案。你有任何想法吗？我们可以一起来想办法。\n"
}
```
### Schema
```
instruction: 指令
input: 输入（本数据集均为空）
output: 输出
```
## Limitation and Usage Limits
We require developers only use the open-sourced code, data, model and any other artifacts generated via this project for research purposes. Commercial use and other potential harmful use cases are not allowed.
Since this dataset was generated by *ChatGPT* and was not strictly verified, it still has shortcomings regarding factuality and other aspects. When using this dataset, careful inspection is needed.
This dataset does not represent anyone's ground, interest or thought, and is not related to any kind of claim of any groups. The developers of this project do not assume any responsibility to potential harm inflicted by using this dataset and project. |
true |
# Dataset Card for Structured Argument Extraction for Korean
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Structured Argument Extraction for Korean](https://github.com/warnikchow/sae4k)
- **Repository:** [Structured Argument Extraction for Korean](https://github.com/warnikchow/sae4k)
- **Paper:** [Machines Getting with the Program: Understanding Intent Arguments of Non-Canonical Directives](https://arxiv.org/abs/1912.00342)
- **Point of Contact:** [Won Ik Cho](wicho@hi.snu.ac.kr)
### Dataset Summary
The Structured Argument Extraction for Korean dataset is a set of question-argument and command-argument pairs with their respective question type label and negativeness label. Often times, agents like Alexa or Siri, encounter conversations without a clear objective from the user. The goal of this dataset is to extract the intent argument of a given utterance pair without a clear directive. This may yield a more robust agent capable of parsing more non-canonical forms of speech.
### Supported Tasks and Leaderboards
* `intent_classification`: The dataset can be trained with a Transformer like [BERT](https://huggingface.co/bert-base-uncased) to classify the intent argument or a question/command pair in Korean, and it's performance can be measured by it's BERTScore.
### Languages
The text in the dataset is in Korean and the associated is BCP-47 code is `ko-KR`.
## Dataset Structure
### Data Instances
An example data instance contains a question or command pair and its label:
```
{
"intent_pair1": "내일 오후 다섯시 조별과제 일정 추가해줘"
"intent_pair2": "내일 오후 다섯시 조별과제 일정 추가하기"
"label": 4
}
```
### Data Fields
* `intent_pair1`: a question/command pair
* `intent_pair2`: a corresponding question/command pair
* `label`: determines the intent argument of the pair and can be one of `yes/no` (0), `alternative` (1), `wh- questions` (2), `prohibitions` (3), `requirements` (4) and `strong requirements` (5)
### Data Splits
The corpus contains 30,837 examples.
## Dataset Creation
### Curation Rationale
The Structured Argument Extraction for Korean dataset was curated to help train models extract intent arguments from utterances without a clear objective or when the user uses non-canonical forms of speech. This is especially helpful in Korean because in English, the `Who, what, where, when and why` usually comes in the beginning, but this isn't necessarily the case in the Korean language. So for low-resource languages, this lack of data can be a bottleneck for comprehension performance.
### Source Data
#### Initial Data Collection and Normalization
The corpus was taken from the one constructed by [Cho et al.](https://arxiv.org/abs/1811.04231), a Korean single utterance corpus for identifying directives/non-directives that contains a wide variety of non-canonical directives.
#### Who are the source language producers?
Korean speakers are the source language producers.
### Annotations
#### Annotation process
Utterances were categorized as question or command arguments and then further classified according to their intent argument.
#### Who are the annotators?
The annotation was done by three Korean natives with a background in computational linguistics.
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The dataset is curated by Won Ik Cho, Young Ki Moon, Sangwhan Moon, Seok Min Kim and Nam Soo Kim.
### Licensing Information
The dataset is licensed under the CC BY-SA-4.0.
### Citation Information
```
@article{cho2019machines,
title={Machines Getting with the Program: Understanding Intent Arguments of Non-Canonical Directives},
author={Cho, Won Ik and Moon, Young Ki and Moon, Sangwhan and Kim, Seok Min and Kim, Nam Soo},
journal={arXiv preprint arXiv:1912.00342},
year={2019}
}
```
### Contributions
Thanks to [@stevhliu](https://github.com/stevhliu) for adding this dataset. |
false |
## Dataset Description
- **Homepage:** http://www.openslr.org/57/
### Dataset Summary
This corpus consists of approximately 22 hours of speech recordings. Transcripts are provided for all the recordings. The corpus can be divided into 3 parts:
1. Yaounde
Collected by a team from the U.S. Military Academy's Center for Technology Enhanced Language Learning (CTELL) in 2003 in Yaoundé, Cameroon. It has recordings from 84 speakers, 48 male and 36 female.
2. CA16
This part was collected by a RDECOM Science Team who participated in the United Nations exercise Central Accord 16 (CA16) in Libreville, Gabon in June 2016. The Science Team included DARPA's Dr. Boyan Onyshkevich and Dr. Aaron Lawson (SRI International), as well as RDECOM scientists. It has recordings from 125 speakers from Cameroon, Chad, Congo and Gabon.
3. Niger
This part was collected from 23 speakers in Niamey, Niger, Oct. 26-30 2015. These speakers were students in a course for officers and sergeants presented by Army trainers assigned to U.S. Army Africa. The data was collected by RDECOM Science & Technology Advisors Major Eddie Strimel and Mr. Bill Bergen.
### Languages
French
## Dataset Structure
### Data Instances
A typical data point comprises the path to the audio file, called audio and its sentence.
### Data Fields
- audio: A dictionary containing the path to the downloaded audio file, the decoded audio array, and the sampling rate. Note that when accessing the audio column: `dataset[0]["audio"]` the audio file is automatically decoded and resampled to `dataset.features["audio"].sampling_rate`. Decoding and resampling of a large number of audio files might take a significant amount of time. Thus it is important to first query the sample index before the `"audio"` column, *i.e.* `dataset[0]["audio"]` should **always** be preferred over `dataset["audio"][0]`.
- sentence: The sentence the user was prompted to speak
### Data Splits
The speech material has been subdivided into portions for train and test.
The train split consists of 9401 audio clips and the related sentences.
The test split consists of 1985 audio clips and the related sentences.
### Contributions
[@gigant](https://huggingface.co/gigant) added this dataset. |
true |
# Dataset Card for Fake News English
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://dl.acm.org/doi/10.1145/3201064.3201100**
- **Repository:** https://github.com/jgolbeck/fakenews/
- **Paper:** https://doi.org/10.1145/3201064.3201100
- **Leaderboard:**
- **Point of Contact:** Jennifer Golbeck (http://www.jengolbeck.com)
### Dataset Summary
This dataset contains URLs of news articles classified as either fake or satire. The articles classified as fake also have the URL of a rebutting article.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English
## Dataset Structure
### Data Instances
```
{
"article_number": 102 ,
"url_of_article": https://newslo.com/roger-stone-blames-obama-possibility-trump-alzheimers-attacks-president-caused-severe-stress/ ,
"fake_or_satire": 1, # Fake
"url_of_rebutting_article": https://www.snopes.com/fact-check/donald-trumps-intelligence-quotient/
}
```
### Data Fields
- article_number: An integer used as an index for each row
- url_of_article: A string which contains URL of an article to be assessed and classified as either Fake or Satire
- fake_or_satire: A classlabel for the above variable which can take two values- Fake (1) and Satire (0)
- url_of_rebutting_article: A string which contains a URL of the article used to refute the article in question (present - in url_of_article)
### Data Splits
This dataset is not split, only the train split is available.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Golbeck, Jennifer
Everett, Jennine
Falak, Waleed
Gieringer, Carl
Graney, Jack
Hoffman, Kelly
Huth, Lindsay
Ma, Zhenya
Jha, Mayanka
Khan, Misbah
Kori, Varsha
Mauriello, Matthew
Lewis, Elo
Mirano, George
IV, William
Mussenden, Sean
Nelson, Tammie
Mcwillie, Sean
Pant, Akshat
Cheakalos, Paul
### Licensing Information
[More Information Needed]
### Citation Information
@inproceedings{inproceedings,
author = {Golbeck, Jennifer and Everett, Jennine and Falak, Waleed and Gieringer, Carl and Graney, Jack and Hoffman, Kelly and Huth, Lindsay and Ma, Zhenya and Jha, Mayanka and Khan, Misbah and Kori, Varsha and Mauriello, Matthew and Lewis, Elo and Mirano, George and IV, William and Mussenden, Sean and Nelson, Tammie and Mcwillie, Sean and Pant, Akshat and Cheakalos, Paul},
year = {2018},
month = {05},
pages = {17-21},
title = {Fake News vs Satire: A Dataset and Analysis},
doi = {10.1145/3201064.3201100}
}
### Contributions
Thanks to [@MisbahKhan789](https://github.com/MisbahKhan789), [@lhoestq](https://github.com/lhoestq) for adding this dataset. |
false |
# Dataset Card for OneStopQA
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [OneStopQA repository](https://github.com/berzak/onestop-qa)
- **Repository:** [OneStopQA repository](https://github.com/berzak/onestop-qa)
- **Paper:** [STARC: Structured Annotations for Reading Comprehension](https://arxiv.org/abs/2004.14797)
- **Leaderboard:** [Needs More Information]
- **Point of Contact:** [Needs More Information]
### Dataset Summary
OneStopQA is a multiple choice reading comprehension dataset annotated according to the STARC (Structured Annotations for Reading Comprehension) scheme. The reading materials are Guardian articles taken from the [OneStopEnglish corpus](https://github.com/nishkalavallabhi/OneStopEnglishCorpus). Each article comes in three difficulty levels, Elementary, Intermediate and Advanced. Each paragraph is annotated with three multiple choice reading comprehension questions. The reading comprehension questions can be answered based on any of the three paragraph levels.
### Supported Tasks and Leaderboards
[Needs More Information]
### Languages
English (`en-US`).
The original Guardian articles were manually converted from British to American English.
## Dataset Structure
### Data Instances
An example of instance looks as follows.
```json
{
"title": "101-Year-Old Bottle Message",
"paragraph": "Angela Erdmann never knew her grandfather. He died in 1946, six years before she was born. But, on Tuesday 8th April, 2014, she described the extraordinary moment when she received a message in a bottle, 101 years after he had lobbed it into the Baltic Sea. Thought to be the world’s oldest message in a bottle, it was presented to Erdmann by the museum that is now exhibiting it in Germany.",
"paragraph_index": 1,
"level": "Adv",
"question": "How did Angela Erdmann find out about the bottle?",
"answers": ["A museum told her that they had it",
"She coincidentally saw it at the museum where it was held",
"She found it in her basement on April 28th, 2014",
"A friend told her about it"],
"a_span": [56, 70],
"d_span": [16, 34]
}
```
Where,
| Answer | Description | Textual Span |
|--------|------------------------------------------------------------|-----------------|
| a | Correct answer. | Critical Span |
| b | Incorrect answer. A miscomprehension of the critical span. | Critical Span |
| c | Incorrect answer. Refers to an additional span. | Distractor Span |
| d | Incorrect answer. Has no textual support. | - |
The order of the answers in the `answers` list corresponds to the order of the answers in the table.
### Data Fields
- `title`: A `string` feature. The article title.
- `paragraph`: A `string` feature. The paragraph from the article.
- `paragraph_index`: An `int` feature. Corresponds to the paragraph index in the article.
- `question`: A `string` feature. The given question.
- `answers`: A list of `string` feature containing the four possible answers.
- `a_span`: A list of start and end indices (inclusive) of the critical span.
- `d_span`: A list of start and end indices (inclusive) of the distractor span.
*Span indices are according to word positions after whitespace tokenization.
**In the rare case where a span is spread over multiple sections,
the span list will contain multiple instances of start and stop indices in the format:
[start_1, stop_1, start_2, stop_2,...].
### Data Splits
Articles: 30
Paragraphs: 162
Questions: 486
Question-Paragraph Level pairs: 1,458
No preconfigured split is currently provided.
## Dataset Creation
### Curation Rationale
[Needs More Information]
### Source Data
#### Initial Data Collection and Normalization
[Needs More Information]
#### Who are the source language producers?
[Needs More Information]
### Annotations
#### Annotation process
The annotation and piloting process of the dataset is described in Appendix A in
[STARC: Structured Annotations for Reading Comprehension](https://aclanthology.org/2020.acl-main.507.pdf).
#### Who are the annotators?
[Needs More Information]
### Personal and Sensitive Information
[Needs More Information]
## Considerations for Using the Data
### Social Impact of Dataset
[Needs More Information]
### Discussion of Biases
[Needs More Information]
### Other Known Limitations
[Needs More Information]
## Additional Information
### Dataset Curators
[Needs More Information]
### Licensing Information
<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.
### Citation Information
[STARC: Structured Annotations for Reading Comprehension](http://people.csail.mit.edu/berzak/papers/acl2020.pdf)
```
@inproceedings{starc2020,
author = {Berzak, Yevgeni and Malmaud, Jonathan and Levy, Roger},
title = {STARC: Structured Annotations for Reading Comprehension},
booktitle = {ACL},
year = {2020},
publisher = {Association for Computational Linguistics}
}
```
### Contributions
Thanks to [@scaperex](https://github.com/scaperex) for adding this dataset. |
false |
# Dataset Card for Spanish Billion Words
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Spanish Billion Words homepage](https://crscardellino.github.io/SBWCE/)
- **Point of Contact:** [Cristian Cardellino](mailto:ccardellino@unc.edu.ar) (Corpus Creator), [María Grandury](mailto:mariagrandury@gmail.com) (Corpus Submitter)
### Dataset Summary
The Spanish Billion Words Corpus is an unannotated Spanish corpus of nearly 1.5 billion words, compiled from different resources from the web.
This resources include the spanish portions of SenSem, the Ancora Corpus, some OPUS Project Corpora and the Europarl,
the Tibidabo Treebank, the IULA Spanish LSP Treebank, and dumps from the Spanish Wikipedia, Wikisource and Wikibooks.
This corpus is a compilation of 100 text files. Each line of these files represents one of the 50 million sentences from the corpus.
### Supported Tasks and Leaderboards
This dataset can be used for language modelling and for pretraining language models.
### Languages
The text in this dataset is in Spanish, BCP-47 code: 'es'.
## Dataset Structure
### Data Instances
Each example in this dataset is a sentence in Spanish:
```
{'text': 'Yo me coloqué en un asiento próximo a una ventana cogí un libro de una mesa y empecé a leer'}
```
### Data Fields
- `text`: a sentence in Spanish
### Data Splits
The dataset is not split.
## Dataset Creation
### Curation Rationale
The Spanish Billion Words Corpus was created to train word embeddings using the word2vect algorithm provided by the gensim package.
### Source Data
#### Initial Data Collection and Normalization
The corpus was created compiling the following resources:
- The Spanish portion of [SenSem]().
- The Spanish portion of the [Ancora Corpus](http://clic.ub.edu/corpus/en).
- [Tibidabo Treebank and IULA Spanish LSP Treebank](http://lod.iula.upf.edu/resources/metadata_TRL_Tibidabo_LSP_treebank_ES).
- The Spanish portion of the following [OPUS Project](http://opus.nlpl.eu/index.php) Corpora:
- The [books](http://opus.nlpl.eu/Books.php) aligned by [Andras Farkas](https://farkastranslations.com/).
- The [JRC-Acquis](http://opus.nlpl.eu/JRC-Acquis.php) collection of legislative text of the European Union.
- The [News Commentary](http://opus.nlpl.eu/News-Commentary.php) corpus.
- The [United Nations](http://opus.nlpl.eu/UN.php) documents compiled by [Alexandre Rafalovitch](https://www.outerthoughts.com/) and [Robert Dale](http://web.science.mq.edu.au/~rdale/).
- The Spanish portion of the [Europarl](http://statmt.org/europarl/) (European Parliament), compiled by [Philipp Koehn](https://homepages.inf.ed.ac.uk/pkoehn/).
- Dumps from the Spanish [Wikipedia](https://es.wikipedia.org/wiki/Wikipedia:Portada), [Wikisource](https://es.wikisource.org/wiki/Portada) and [Wikibooks](https://es.wikibooks.org/wiki/Portada) on date 2015-09-01, parsed with the Wikipedia Extractor.
All the annotated corpora (like Ancora, SenSem and Tibidabo) were untagged and
the parallel corpora (most coming from the OPUS Project) was preprocessed to obtain only the Spanish portions of it.
Once the whole corpus was unannotated, all non-alphanumeric characters were replaced with whitespaces,
all numbers with the token “DIGITO” and all the multiple whitespaces with only one whitespace.
The capitalization of the words remained unchanged.
#### Who are the source language producers?
The data was compiled and processed by Cristian Cardellino.
### Annotations
The dataset is unannotated.
#### Annotation process
[N/A]
#### Who are the annotators?
[N/A]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The data was collected and processed by Cristian Cardellino.
### Licensing Information
The dataset is licensed under a Creative Commons Attribution-ShareAlike 4.0 International license
[(CC BY-SA 4.0)](https://creativecommons.org/licenses/by-sa/4.0/)
### Citation Information
```
@misc{cardellinoSBWCE,
author = {Cardellino, Cristian},
title = {Spanish {B}illion {W}ords {C}orpus and {E}mbeddings},
url = {https://crscardellino.github.io/SBWCE/},
month = {August},
year = {2019}
}
```
### Contributions
Thanks to [@mariagrandury](https://github.com/mariagrandury) for adding this dataset. |
false |
# Dataset Card for "opinosis"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://kavita-ganesan.com/opinosis-opinion-dataset/
- **Repository:** https://github.com/kavgan/opinosis-summarization
- **Paper:** [Opinosis: A Graph Based Approach to Abstractive Summarization of Highly Redundant Opinions](https://aclanthology.org/C10-1039/)
- **Point of Contact:** [Kavita Ganesan](mailto:kavita@opinosis.ai)
- **Size of downloaded dataset files:** 0.75 MB
- **Size of the generated dataset:** 0.74 MB
- **Total amount of disk used:** 1.50 MB
### Dataset Summary
The Opinosis Opinion Dataset consists of sentences extracted from reviews for 51 topics.
Topics and opinions are obtained from Tripadvisor, Edmunds.com and Amazon.com.
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 0.75 MB
- **Size of the generated dataset:** 0.74 MB
- **Total amount of disk used:** 1.50 MB
An example of 'train' looks as follows.
```
{
"review_sents": "This is a fake topic. \nThe topics have multiple sentence inputs. \n",
"summaries": ["This is a gold summary for topic 1. \nSentences in gold summaries are separated by newlines.", "This is another gold summary for topic 1. \nSentences in gold summaries are separated by newlines."]
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `review_sents`: a `string` feature.
- `summaries`: a `list` of `string` features.
### Data Splits
| name |train|
|-------|----:|
|default| 51|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
The license for this dataset is Apache License 2.0 and can be found [here](https://github.com/kavgan/opinosis-summarization/blob/master/LICENSE).
### Citation Information
```
@inproceedings{ganesan2010opinosis,
title={Opinosis: a graph-based approach to abstractive summarization of highly redundant opinions},
author={Ganesan, Kavita and Zhai, ChengXiang and Han, Jiawei},
booktitle={Proceedings of the 23rd International Conference on Computational Linguistics},
pages={340--348},
year={2010},
organization={Association for Computational Linguistics}
}
```
### Contributions
Thanks to [@thomwolf](https://github.com/thomwolf), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset. |
false |
# Dataset Card for Turku NER corpus
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://turkunlp.org/fin-ner.html
- **Repository:** https://github.com/TurkuNLP/turku-ner-corpus/
- **Paper:** https://www.aclweb.org/anthology/2020.lrec-1.567/
- **Leaderboard:** [If the dataset supports an active leaderboard, add link here]()
- **Point of Contact:** {jouni.a.luoma,mhtoin,maria.h.pyykonen,mavela,sampo.pyysalo}@utu.f
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false |
# Dataset Card for The Universal Declaration of Human Rights (UDHR)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.ohchr.org/en/universal-declaration-of-human-rights, https://unicode.org/udhr/index.html
- **Repository:** https://github.com/unicode-org/udhr
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
The Universal Declaration of Human Rights (UDHR) is a milestone document in the history of human rights. Drafted by
representatives with different legal and cultural backgrounds from all regions of the world, it set out, for the
first time, fundamental human rights to be universally protected. The Declaration was adopted by the UN General
Assembly in Paris on 10 December 1948 during its 183rd plenary meeting.
© 1996 – 2009 The Office of the High Commissioner for Human Rights
This plain text version prepared by the "UDHR in Unicode" project, https://www.unicode.org/udhr.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset includes translations of the document in over 400 languages and dialects. The list of languages can be found
[here](https://unicode.org/udhr/translations.html).
## Dataset Structure
### Data Instances
Each instance corresponds to a different language and includes information about the language and the full document
text.
### Data Fields
- `text`: The full document text with each line of text delimited by a newline (`\n`).
- `lang_key`: The unique identifier of a given translation.
- `lang_name`: The textual description of language/dialect.
- `iso639-3`: The [iso639-3](https://iso639-3.sil.org/) language identifier.
- `iso15924`: The [iso15924](https://unicode.org/iso15924/iso15924-codes.html) language identifier.
- `bcp47`: The [BCP 47](https://www.rfc-editor.org/info/bcp47) language identifier.
### Data Splits
Only a `train` split included which includes the full document in all languages.
| | train |
|--------------------|------:|
| Number of examples | 488 |
## Dataset Creation
### Curation Rationale
In addition to its social significance, the document set a world record in 1999 for being the most translated
document in the world and as such can be useful for settings requiring paired text between many languages.
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
In addition to the social and political significance of the United Nations' Universal Declaration of Human Rights,
the document set a world record in 1999 for being the most translated document in the world and as such can be useful
for settings requiring paired text between many languages including those that are low resource and significantly
underrepresented in NLP research.
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
Although the document is translated into a very large number of languages, the text is very short and therefore may
have limited usefulness for most types of modeling and evaluation.
## Additional Information
### Dataset Curators
The txt/xml data files used here were compiled by The Unicode Consortium, which can be found
[here](https://unicode.org/udhr/index.html). The original texts can be found on the
[United Nations website](https://www.ohchr.org/EN/UDHR/Pages/UDHRIndex.aspx).
### Licensing Information
Source text © 1996 – 2022 The Office of the High Commissioner for Human Rights
The [Unicode license](https://www.unicode.org/license.txt) applies to these translations.
### Citation Information
United Nations. (1998). The Universal Declaration of Human Rights, 1948-1998. New York: United Nations Dept. of Public Information.
### Contributions
Thanks to [@joeddav](https://github.com/joeddav) for adding this dataset. Updated May 2022 [@leondz](https://github.com/leondz). |
false |
## Dataset Description
- **Homepage:** [Cat and Dog](https://www.kaggle.com/datasets/tongpython/cat-and-dog)
- **Download Size** 217.30 MiB
- **Generated Size** 198.89 MiB
- **Total Size** 416.20 MiB
### Dataset Summary
A dataset from [kaggle](https://www.kaggle.com/datasets/tongpython/cat-and-dog) with duplicate data removed.
### Data Fields
The data instances have the following fields:
- `image`: A `PIL.Image.Image` object containing the image. Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `"image"` column, *i.e.* `dataset[0]["image"]` should **always** be preferred over `dataset["image"][0]`.
- `labels`: an `int` classification label.
### Class Label Mappings:
```
{
"cat": 0,
"dog": 1,
}
```
### Data Splits
| | train | test |
|---------------|-------|-----:|
| # of examples | 8000 | 2000 |
```python
>>> from datasets import load_dataset
>>> dataset = load_dataset("Bingsu/Cat_and_Dog")
>>> dataset
DatasetDict({
train: Dataset({
features: ['image', 'labels'],
num_rows: 8000
})
test: Dataset({
features: ['image', 'labels'],
num_rows: 2000
})
})
>>> dataset["train"].features
{'image': Image(decode=True, id=None), 'labels': ClassLabel(num_classes=2, names=['cat', 'dog'], id=None)}
``` |
true |
# Dataset Card for [Dataset Name]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Multilingual LAMA](http://cistern.cis.lmu.de/mlama/)
- **Repository:** [Github](https://github.com/norakassner/mlama)
- **Paper:** [Arxiv](https://arxiv.org/abs/2102.00894)
- **Point of Contact:** [Contact section](http://cistern.cis.lmu.de/mlama/)
### Dataset Summary
This dataset provides the data for mLAMA, a multilingual version of LAMA.
Regarding LAMA see https://github.com/facebookresearch/LAMA. For mLAMA
the TREx and GoogleRE part of LAMA was considered and machine translated using
Google Translate, and the Wikidata and Google Knowledge Graph API. The machine
translated templates were checked for validity, i.e., whether they contain
exactly one '[X]' and one '[Y]'.
This data can be used for creating fill-in-the-blank queries like
"Paris is the capital of [MASK]" across 53 languages. For more details see
the website http://cistern.cis.lmu.de/mlama/ or the github repo https://github.com/norakassner/mlama.
### Supported Tasks and Leaderboards
Language model knowledge probing.
### Languages
This dataset contains data in 53 languages:
af,ar,az,be,bg,bn,ca,ceb,cs,cy,da,de,el,en,es,et,eu,fa,fi,fr,ga,gl,he,hi,hr,hu,hy,id,it,ja,ka,ko,la,lt,lv,ms,nl,pl,pt,ro,ru,sk,sl,sq,sr,sv,ta,th,tr,uk,ur,vi,zh
## Dataset Structure
For each of the 53 languages and each of the 43 relations/predicates there is a set of triples.
### Data Instances
For each language and relation there are triples, that consists of an object, a predicate and a subject. For each predicate there is a template available. An example for `dataset["test"][0]` is given here:
```python
{
'language': 'af',
'lineid': 0,
'obj_label': 'Frankryk',
'obj_uri': 'Q142',
'predicate_id': 'P1001',
'sub_label': 'President van Frankryk',
'sub_uri': 'Q191954',
'template': "[X] is 'n wettige term in [Y].",
'uuid': '3fe3d4da-9df9-45ba-8109-784ce5fba38a'
}
```
### Data Fields
Each instance has the following fields
* "uuid": a unique identifier
* "lineid": a identifier unique to mlama
* "obj_id": knowledge graph id of the object
* "obj_label": surface form of the object
* "sub_id": knowledge graph id of the subject
* "sub_label": surface form of the subject
* "template": template
* "language": language code
* "predicate_id": relation id
### Data Splits
There is only one partition that is labelled as 'test data'.
## Dataset Creation
### Curation Rationale
The dataset was translated into 53 languages to investigate knowledge in pretrained language models
multilingually.
### Source Data
#### Initial Data Collection and Normalization
The data has several sources:
LAMA (https://github.com/facebookresearch/LAMA) licensed under Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
T-REx (https://hadyelsahar.github.io/t-rex/) licensed under Creative Commons Attribution-ShareAlike 4.0 International License
Google-RE (https://github.com/google-research-datasets/relation-extraction-corpus)
Wikidata (https://www.wikidata.org/) licensed under Creative Commons CC0 License and Creative Commons Attribution-ShareAlike License
#### Who are the source language producers?
See links above.
### Annotations
#### Annotation process
Crowdsourced (wikidata) and machine translated.
#### Who are the annotators?
Unknown.
### Personal and Sensitive Information
Names of (most likely) famous people who have entries in Google Knowledge Graph or Wikidata.
## Considerations for Using the Data
Data was created through machine translation and automatic processes.
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
Not all triples are available in all languages.
## Additional Information
### Dataset Curators
The authors of the mLAMA paper and the authors of the original datasets.
### Licensing Information
The Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0). https://creativecommons.org/licenses/by-nc-sa/4.0/
### Citation Information
```
@article{kassner2021multilingual,
author = {Nora Kassner and
Philipp Dufter and
Hinrich Sch{\"{u}}tze},
title = {Multilingual {LAMA:} Investigating Knowledge in Multilingual Pretrained
Language Models},
journal = {CoRR},
volume = {abs/2102.00894},
year = {2021},
url = {https://arxiv.org/abs/2102.00894},
archivePrefix = {arXiv},
eprint = {2102.00894},
timestamp = {Tue, 09 Feb 2021 13:35:56 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-00894.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
note = {to appear in EACL2021}
}
```
### Contributions
Thanks to [@pdufter](https://github.com/pdufter) for adding this dataset. |
true |
# Dataset Card for "SentNoB"
### Dataset Summary
Social Media User Comments' Sentiment Analysis Dataset. Each user comments are labeled with either positive (1), negative (2), or neutral (0).
### Citation Information
```
@inproceedings{islam2021sentnob,
title={SentNoB: A Dataset for Analysing Sentiment on Noisy Bangla Texts},
author={Islam, Khondoker Ittehadul and Kar, Sudipta and Islam, Md Saiful and Amin, Mohammad Ruhul},
booktitle={Findings of the Association for Computational Linguistics: EMNLP 2021},
pages={3265--3271},
year={2021}
}
``` |
false |
### Dataset Summary
This dataset contains 190,335 Russian Q&A posts from a medical related forum.
### Dataset Fields
* date: date and time of the asked question, like '26 Октября 2018, 08:30'
* categ: question category
* theme: question topic
* desc: question text
* ans: question answers separated with ';\n'
* spec10: if present, one of 10 medical specializations
|
false |
# Dataset Card for Curiosity Dataset
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Curiosity Dataset Homepage](https://www.pedro.ai/curiosity)
- **Repository:** [Curiosity Dataset Repository](https://github.com/facebookresearch/curiosity)
- **Paper:** [ACL Anthology](https://www.aclweb.org/anthology/2020.emnlp-main.655/)
- **Point of Contact:** [Pedro Rodriguez](https://mailhide.io/e/wbfjM)
### Dataset Summary
Curiosity dataset consists of 14K English dialogs (181K utterances) where users and assistants converse about geographic topics like geopolitical entities and locations. This dataset is annotated with pre-existing user knowledge, message-level dialog acts, grounding to Wikipedia, and user reactions to messages.
### Supported Tasks and Leaderboards
* `text-generation-other-conversational-curiosity`: The dataset can be used to train a model for Conversational Curiosity, which consists in the testing of the hypothesis that engagement increases when users are presented with facts related to what they know. Success on this task is typically measured by achieving a *high* [Accuracy](https://huggingface.co/metrics/accuracy) and [F1 Score](https://huggingface.co/metrics/f1).
### Languages
The text in the dataset is in English collected by crowd-souring. The associated BCP-47 code is `en`.
## Dataset Structure
### Data Instances
A typical data point consists of dialogs between an user and an assistant, which is followed by the different attributes of the particular dialog.
An example from the Curiosity Dataset train set looks as follows:
```
{'annotated': 1,
'aspects': ['Media', 'Politics and government'],
'assistant_dialog_rating': 5,
'assistant_id': 341,
'assistant_other_agent_rating': 5,
'created_time': 1571783665,
'dialog_id': 21922,
'first_aspect': 'Media',
'focus_entity': 'Namibia',
'inferred_steps': 1,
'is_annotated': 0,
'known_entities': ['South Africa', 'United Kingdom', 'Portugal'],
'messages': {'dialog_acts': [['request_topic'],
['inform_response'],
['request_aspect'],
['inform_response'],
['request_followup'],
['inform_response'],
['request_aspect', 'feedback_positive'],
['inform_response'],
['request_followup'],
['inform_response'],
[],
[]],
'facts': [{'fid': [], 'source': [], 'used': []},
{'fid': [77870, 77676, 77816, 77814, 77775, 77659, 77877, 77785, 77867],
'source': [0, 1, 2, 2, 0, 2, 0, 1, 1],
'used': [0, 0, 0, 0, 0, 0, 0, 0, 0]},
{'fid': [], 'source': [], 'used': []},
{'fid': [77725, 77870, 77676, 77863, 77814, 77775, 77659, 77877, 77867],
'source': [2, 0, 1, 1, 2, 0, 2, 0, 1],
'used': [0, 0, 0, 0, 0, 0, 0, 0, 0]},
{'fid': [], 'source': [], 'used': []},
{'fid': [77694, 77661, 77863, 77780, 77671, 77704, 77869, 77693, 77877],
'source': [1, 2, 1, 0, 2, 2, 0, 1, 0],
'used': [0, 0, 0, 0, 0, 0, 0, 0, 1]},
{'fid': [], 'source': [], 'used': []},
{'fid': [77816, 77814, 77864, 77659, 77877, 77803, 77738, 77784, 77789],
'source': [2, 2, 0, 2, 0, 1, 1, 0, 1],
'used': [0, 0, 0, 0, 0, 0, 0, 0, 0]},
{'fid': [], 'source': [], 'used': []},
{'fid': [77694, 77776, 77780, 77696, 77707, 77693, 77778, 77702, 77743],
'source': [1, 0, 0, 2, 1, 1, 0, 2, 2],
'used': [0, 0, 0, 0, 0, 0, 0, 0, 0]},
{'fid': [], 'source': [], 'used': []},
{'fid': [77662, 77779, 77742, 77734, 77663, 77777, 77702, 77731, 77778],
'source': [1, 0, 2, 1, 2, 0, 2, 1, 0],
'used': [0, 0, 0, 0, 0, 0, 0, 0, 1]}],
'liked': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
'message': ['Hi. I want information about Namibia.',
'Nmbia is a country in southern Africa.',
'Do you have information about the media there?',
'A mentional amount of foriegn',
'What about it?',
"Media and journalists in Namibia are represented by the Namibia chapter of the Media Institute of 'southern Africa and the Editors Forum of Namibia.",
'Interesting! What can you tell me about the politics and government?',
'Namibia formed the Namibian Defence Force, comprising former enemies in a 23-year bush war.',
'Do you have more information about it?',
"With a small army and a fragile economy , the Namibian government's principal foreign policy concern is developing strengthened ties within the Southern African region.",
"That's all I wanted to know. Thank you!",
'My pleasure!'],
'message_id': ['617343895',
'2842515356',
'4240816985',
'520711081',
'1292358002',
'3677078227',
'1563061125',
'1089028270',
'1607063839',
'113037558',
'1197873991',
'1399017322'],
'sender': [0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1]},
'related_entities': ['Western Roman Empire',
'United Kingdom',
'Portuguese language',
'Southern African Development Community',
'South Africa',
'Kalahari Desert',
'Namib Desert',
'League of Nations',
'Afrikaans',
'Sub-Saharan Africa',
'Portugal',
'South-West Africa',
'Warmbad, Namibia',
'German language',
'NBC'],
'reported': 0,
'second_aspect': 'Politics and government',
'shuffle_facts': 1,
'tag': 'round_2',
'user_dialog_rating': 5,
'user_id': 207,
'user_other_agent_rating': 5}
```
### Data Fields
* `messages`: List of dialogs between the user and the assistant and their associated attributes
* `dialog_acts`: List of actions performed in the dialogs
* `facts`: List of facts returned by the assistant
* `fid`: Fact ID
* `source`: Source for the fact
* `used`: Whether facts were used before in the same dialog
* `liked`: List of values indicating whether each dialog was liked
* `message`: List of dialogs (messages) between the user and the assistant
* `message_id`: Message ID
* `sender`: Message author ID (numeric)
* `known_entities`: Rooted facts about entities the user knows
* `focus_entity` : Entity in focus in the dialogs
* `dialog_id `: Dialog ID
* `inferred_steps`: Number of inferred steps
* `created_time`: Time of creation of the dialog
* `aspects`: List of two aspects which the dialog is about
* `first_aspect`: First aspect
* `second_aspect`: Second aspect
* `shuffle_facts`: Whether facts were shuffled
* `related_entities` : List of fifteen related entities to the focus entity
* `tag`: Conversation tag
* `user_id`: User ID
* `assistant_id`: Assistant ID
* `is_annotated`: 0 or 1 (More Information Needed)
* `user_dialog_rating`: 1 - 5 (More Information Needed)
* `user_other_agent_rating`: 1 - 5 (More Information Needed)
* `assistant_dialog_rating`: 1 - 5 (More Information Needed)
* `assistant_other_agent_rating`: 1 - 5 (More Information Needed)
* `reported`: Whether the dialog was reported inappropriate
* `annotated`: 0 or 1 (More Information Needed)
### Data Splits
The data is split into a training, validation, test and test_zero set as per the original dataset split.
| | train | validation | test | test_zero |
|-----------------------|------:|-----------:|-----:|----------:|
| Input dialog examples | 10287 | 1287 | 1287 | 1187 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[Attribution-NonCommercial 4.0 International](https://creativecommons.org/licenses/by-nc/4.0/legalcode)
### Citation Information
```
@inproceedings{rodriguez2020curiosity,
title = {Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity},
author = {Pedro Rodriguez and Paul Crook and Seungwhan Moon and Zhiguang Wang},
year = 2020,
booktitle = {Empirical Methods in Natural Language Processing}
}
```
### Contributions
Thanks to [@vineeths96](https://github.com/vineeths96) for adding this dataset. |
true |
# Dataset Card for SemEval-2020 Task 11
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [PTC TASKS ON "DETECTION OF PROPAGANDA TECHNIQUES IN NEWS ARTICLES"](https://propaganda.qcri.org/ptc/index.html)
- **Paper:** [SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles](https://arxiv.org/abs/2009.02696)
- **Leaderboard:** [PTC Tasks Leaderboard](https://propaganda.qcri.org/ptc/leaderboard.php)
- **Point of Contact:** [Task organizers contact](semeval-2020-task-11-organizers@googlegroups.com)
### Dataset Summary
Propagandistic news articles use specific techniques to convey their message, such as whataboutism, red Herring, and name calling, among many others. The Propaganda Techniques Corpus (PTC) allows to study automatic algorithms to detect them. We provide a permanent leaderboard to allow researchers both to advertise their progress and to be up-to-speed with the state of the art on the tasks offered (see below for a definition).
### Supported Tasks and Leaderboards
More information on scoring methodology can be found in [propaganda tasks evaluation document](https://propaganda.qcri.org/ptc/data/propaganda_tasks_evaluation.pdf)
### Languages
This dataset consists of English news articles
## Dataset Structure
### Data Instances
Each example is structured as follows:
```
{
"span_identification": {
"end_char_offset": [720, 6322, ...],
"start_char_offset": [683, 6314, ...]
},
"technique_classification": {
"end_char_offset": [720,6322, ...],
"start_char_offset": [683,6314, ...],
"technique": [7,8, ...]
},
"text": "Newt Gingrich: The truth about Trump, Putin, and Obama\n\nPresident Trump..."
}
```
### Data Fields
- `text`: The full text of the news article.
- `span_identification`: a dictionary feature containing:
- `start_char_offset`: The start character offset of the span for the SI task
- `end_char_offset`: The end character offset of the span for the SI task
- `technique_classification`: a dictionary feature containing:
- `start_char_offset`: The start character offset of the span for the TC task
- `end_char_offset`: The start character offset of the span for the TC task
- `technique`: the propaganda technique classification label, with possible values including `Appeal_to_Authority`, `Appeal_to_fear-prejudice`, `Bandwagon,Reductio_ad_hitlerum`, `Black-and-White_Fallacy`, `Causal_Oversimplification`.
### Data Splits
| | Train | Valid | Test |
| ----- | ------ | ----- | ---- |
| Input Sentences | 371 | 75 | 90 |
| Total Annotations SI | 5468 | 940 | 0 |
| Total Annotations TC | 6128 | 1063 | 0 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
In order to build the PTC-SemEval20 corpus, we retrieved a sample of news articles from the period
starting in mid-2017 and ending in early 2019. We selected 13 propaganda and 36 non-propaganda news
media outlets, as labeled by Media Bias/Fact Check,3
and we retrieved articles from these sources. We
deduplicated the articles on the basis of word n-grams matching (Barron-Cede ´ no and Rosso, 2009) and ˜
we discarded faulty entries (e.g., empty entries from blocking websites).
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
The annotation job consisted of both spotting a propaganda snippet and, at the same time, labeling
it with a specific propaganda technique. The annotation guidelines are shown in the appendix; they
are also available online.4 We ran the annotation in two phases: (i) two annotators label an article
independently and (ii) the same two annotators gather together with a consolidator to discuss dubious
instances (e.g., spotted only by one annotator, boundary discrepancies, label mismatch, etc.). This protocol
was designed after a pilot annotation stage, in which a relatively large number of snippets had been spotted
by one annotator only. The annotation team consisted of six professional annotators from A Data Pro trained to spot and label the propaganda snippets from free text. The job was carried out on an instance of
the Anafora annotation platform (Chen and Styler, 2013), which we tailored for our propaganda annotation
task.
We evaluated the annotation process in terms of γ agreement (Mathet et al., 2015) between each of
the annotators and the final gold labels. The γ agreement on the annotated articles is on average 0.6;
see (Da San Martino et al., 2019b) for a more detailed discussion of inter-annotator agreement. The
training and the development part of the PTC-SemEval20 corpus are the same as the training and the
testing datasets described in (Da San Martino et al., 2019b). The test part of the PTC-SemEval20 corpus
consists of 90 additional articles selected from the same sources as for training and development. For
the test articles, we further extended the annotation process by adding one extra consolidation step: we
revisited all the articles in that partition and we performed the necessary adjustments to the spans and to
the labels as necessary, after a thorough discussion and convergence among at least three experts who
were not involved in the initial annotations.
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```
@misc{martino2020semeval2020,
title={SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles},
author={G. Da San Martino and A. Barrón-Cedeño and H. Wachsmuth and R. Petrov and P. Nakov},
year={2020},
eprint={2009.02696},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@ZacharySBrown](https://github.com/ZacharySBrown) for adding this dataset. |
false |
# Dataset Card for "Weibo NER"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** None
- **Repository:** https://github.com/OYE93/Chinese-NLP-Corpus/tree/master/NER/Weibo
- **Paper:** [More Information Needed]
- **Leaderboard:** [If the dataset supports an active leaderboard, add link here]()
- **Point of Contact:** [More Information Needed]
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false | # Zeroth-Korean
## Dataset Description
- **Homepage:** [OpenSLR](https://www.openslr.org/40/)
- **Repository:** [goodatlas/zeroth](https://github.com/goodatlas/zeroth)
- **Download Size** 2.68 GiB
- **Generated Size** 2.85 GiB
- **Total Size** 5.52 GiB
## Zeroth-Korean
The data set contains transcriebed audio data for Korean. There are 51.6 hours transcribed Korean audio for training data (22,263 utterances, 105 people, 3000 sentences) and 1.2 hours transcribed Korean audio for testing data (457 utterances, 10 people). This corpus also contains pre-trained/designed language model, lexicon and morpheme-based segmenter(morfessor).
Zeroth project introduces free Korean speech corpus and aims to make Korean speech recognition more broadly accessible to everyone.
This project was developed in collaboration between Lucas Jo(@Atlas Guide Inc.) and Wonkyum Lee(@Gridspace Inc.).
Contact: Lucas Jo(lucasjo@goodatlas.com), Wonkyum Lee(wonkyum@gridspace.com)
### License
CC BY 4.0
## Dataset Structure
### Data Instance
```pycon
>>> from datasets import load_dataset
>>> dataset = load_dataset("Bingsu/zeroth-korean")
>>> dataset
DatasetDict({
train: Dataset({
features: ['audio', 'text'],
num_rows: 22263
})
test: Dataset({
features: ['text', 'audio'],
num_rows: 457
})
})
```
### Data Size
download: 2.68 GiB<br>
generated: 2.85 GiB<br>
total: 5.52 GiB
### Data Fields
- audio: `audio`, sampling rate = 16000
- A dictionary containing the path to the downloaded audio file, the decoded audio array, and the sampling rate.
- Note that when accessing the audio column: `dataset[0]["audio"]` the audio file is automatically decoded and resampled to `dataset.features["audio"].sampling_rate`. Decoding and resampling of a large number of audio files might take a significant amount of time. Thus it is important to first query the sample index before the "audio" column, i.e. `dataset[0]["audio"]` should always be preferred over `dataset["audio"][0]`.
- text: `string`
```pycon
>>> dataset["train"][0]
{'audio': {'path': None,
'array': array([-3.0517578e-05, 0.0000000e+00, -3.0517578e-05, ...,
0.0000000e+00, 0.0000000e+00, -6.1035156e-05], dtype=float32),
'sampling_rate': 16000},
'text': '인사를 결정하는 과정에서 당 지도부가 우 원내대표 및 원내지도부와 충분한 상의를 거치지 않은 채 일방적으로 인사를 했다는 불만도 원내지도부를 중심으로 흘러나왔다'}
```
### Data Splits
| | train | test |
| ---------- | -------- | ----- |
| # of data | 22263 | 457 |
|
true |
# Dataset Card for Disaster Response Messages
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [HomePage](https://appen.com/datasets/combined-disaster-response-data/)
- **Repository:** [Repo to Download the Dataset](https://datasets.appen.com/appen_datasets/disaster_response_data/disaster_response_messages_training.csv)
- **Paper:
- **Leaderboard:
- **Point of Contact:** [Darshan Gandhi](darshangandhi1151@gmail.com)
### Dataset Summary
This dataset contains 30,000 messages drawn from events including an earthquake in Haiti in 2010, an earthquake in Chile in 2010, floods in Pakistan in 2010, super-storm Sandy in the U.S.A. in 2012, and news articles spanning a large number of years and 100s of different disasters. The data has been encoded with 36 different categories related to disaster response and has been stripped of messages with sensitive information in their entirety. Upon release, this is the featured dataset of a new Udacity course on Data Science and the AI4ALL summer school and is especially utile for text analytics and natural language processing (NLP) tasks and models.The input data in this job contains thousands of untranslated disaster-related messages and their English translations. In the “Data” tab above, you’ll find the annotated data, with 40 class labels for intent and content.
### Supported Tasks and Leaderboards
The input data in this job contains thousands of untranslated disaster-related messages and their English translations. In the dataset, you’ll find the annotated data, with 40 class labels for intent and content. This dataset contains the original message in its original language, the English translation, and dozens of classes for message content. These classes are noted in column titles with a simple binary 1= yes, 0=no.
### Languages
The dataset is a multilingual dataset which has the messages in the original language and also it's translated English form.
## Dataset Structure
### Data Instances
The dataset consists of a message in English and also it's original language form. Adding on, there are 40 labels which help to understand more about the exact essence of the message.
Example of a Disaster Response : { 'split': 'train', 'message': 'Weather update - a cold front from Cuba that could pass over Haiti', 'original': 'Un front froid se retrouve sur Cuba ce matin. Il pourrait traverser Haiti demain. Des averses de pluie isolee sont encore prevues sur notre region ce soi', 'genre': 'direct', 'related': 1, 'PII': 0, 'request': 0, 'offer': 0, 'aid_related': 0, 'medical_help': 0, 'medical_products': 0, 'search_and_rescue': 0, 'security': 0, 'military': 0, 'child_alone': 0, 'water': 0, 'food': 0, 'shelter': 0, 'clothing': 0, 'money': 0, 'missing_people': 0, 'refugees': 0, 'death': 0, 'other_aid': 0, 'infrastructure_related': 0, 'transport': 0, 'buildings': 0, 'electricity': 0, 'tools': 0, 'hospitals': 0, 'shops': 0, 'aid_centers': 0, 'other_infrastructure': 0, 'weather_related': 0, 'floods': 0, 'storm': 0, 'fire': 0, 'earthquake': 0, 'cold': 0, 'other_weather': 0, 'direct_report': 0}
### Data Fields
*split: Train, Test split</br>
*message: English text of actual messages related to disaster </br>
*original: Text of column 3 in native language as originally written</br>
*genre: Type of message, including direct messages, social posting, and news stories or bulletins</br>
*related: Is the message disaster related? 1= yes, 0=no, 2=maybe</br>
*PII: Does the message contain PII? 1= yes, 0=no </br>
*request: Does the message contain a request? 1= yes, 0=no </br>
*offer: Does the message contain an offer? 1= yes, 0=no </br>
*aid_related: Is the message aid related? 1= yes, 0=no </br>
*medical_help: Does the message concern medical help? 1= yes, 0=no </br>
*medical_products: Does the message concern medical products? 1= yes, 0=no </br>
*search_and_rescue: Does the message concern search and rescue? 1= yes, 0=no </br>
*security: Does the message concern security? 1= yes, 0=no </br>
*military: Does the message concern military? 1= yes, 0=no </br>
*child_alone: Does the message mention a child alone? 1= yes, 0=no</br>
*water: Does the message concern water? 1= yes, 0=no</br>
*food: Does the message concern food? 1= yes, 0=no </br>
*shelter: Does the message concern shelter? 1= yes, 0=no </br>
*clothing: Does the message concern clothing? 1= yes, 0=no </br>
*money: Does the message concern money? 1= yes, 0=no </br>
*missing_people: Does the message indicate missing people? 1= yes, 0=no</br>
*refugees: Does the message concern refugess? 1= yes, 0=no</br>
*death: Does the message imply death? 1= yes, 0=no </br>
*other_aid: Is there any other aid needed? 1=yes, 0=no </br>
*infrastructure_related: Does the message concern infrastructure? 1= yes, 0=no </br>
*transport: Does the message concern transport? 1= yes, 0=no </br>
*buildings: Does the message concern buildings? 1= yes, 0=no </br>
*electricity: Does the message concern electricity? 1= yes, 0=no </br>
*tools: Does the message concern tools? 1= yes, 0=no </br>
*hospitals: Does the message concern clothing? 1= yes, 0=no </br>
*shops: Does the message concern clothing? 1= yes, 0=no </br>
*aid_centers:Does the message concern clothing? 1= yes, 0=no </br>
*other_infrastructure:Does the message concern clothing? 1= yes, 0=no </br>
*weather_related: Does the message concern weather? 1= yes, 0=no</br>
*floods: Does the message indicate there was a flood? 1= yes, 0=no</br>
*storm: Does the message indicate there was a storm? 1= yes, 0=no </br>
*fire: Does the message indicate there was a fire? 1= yes, 0=no</br>
*earthquake: Does the message indicate there was an earthquake? 1= yes, 0=no</br>
*cold: Does the message indicate there was a cold? 1= yes, 0=no</br>
*other_weather: Does the message indicate there was other weather issues? 1= yes, 0=no</br>
*direct_report: Does the show a direct report? 1= yes, 0=no
### Data Splits
|train|test |validation|
|:----:|:-----------:|:----:|
|21046|2629|2573|
## Dataset Creation
### Curation Rationale
The dataset was built to understand about the sentiments of the citizens and also more about want was the emergency about and what kind of help they were seeking
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
The dataset has a great usecase of understand more about the sentiments of the citizens around the globe during a disaster and how their responses are. Also, it helps the government to understand their citizens better and would eventually help to draft better policies accordingly.
### Discussion of Biases
The messages since have been translated in English may not be able to judically imply the exact significance of the individual when they would have posted the message
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The dataset was initially created by [Appen](https://appen.com/)
### Licensing Information
[More Information Needed]
### Citation Information
[Multilingual Disaster Response Messages](https://appen.com/datasets/combined-disaster-response-data/)
### Contributions
Thanks to [@darshan-gandhi](https://github.com/darshan-gandhi) for adding this dataset. |
true |
# Dataset Card for HateSpeechPl
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://zil.ipipan.waw.pl/HateSpeech
- **Repository:** [N/A]
- **Paper:** http://www.qualitativesociologyreview.org/PL/Volume38/PSJ_13_2_Troszynski_Wawer.pdf
- **Leaderboard:** [N/A]
- **Point of Contact:** [Marek Troszyński](mtroszynski@civitas.edu.pl), [Aleksander Wawer](axw@ipipan.waw.pl)
### Dataset Summary
The dataset was created to analyze the possibility of automating the recognition of hate speech in Polish. It was collected from the Polish forums and represents various types and degrees of offensive language, expressed towards minorities.
The original dataset is provided as an export of MySQL tables, what makes it hard to load. Due to that, it was converted to CSV and put to a Github repository.
### Supported Tasks and Leaderboards
- `text-classification`: The dataset might be used to perform the text classification on different target fields, like the presence of irony/sarcasm, minority it describes or a topic.
- `text-scoring`: The sentiment analysis is another task which might be solved on a dataset.
### Languages
Polish, collected from public forums, including the HTML formatting of the text.
## Dataset Structure
### Data Instances
The dataset consists of three collections, originally provided as separate MySQL tables. Here represented as three CSV files.
```
{
'id': 1,
'text_id': 121713,
'annotator_id': 1,
'minority_id': 72,
'negative_emotions': false,
'call_to_action': false,
'source_of_knowledge': 2,
'irony_sarcasm': false,
'topic': 18,
'text': ' <font color=\"blue\"> Niemiec</font> mówi co innego',
'rating': 0
}
```
### Data Fields
List and describe the fields present in the dataset. Mention their data type, and whether they are used as input or output in any of the tasks the dataset currently supports. If the data has span indices, describe their attributes, such as whether they are at the character level or word level, whether they are contiguous or not, etc. If the datasets contains example IDs, state whether they have an inherent meaning, such as a mapping to other datasets or pointing to relationships between data points.
- `id`: unique identifier of the entry
- `text_id`: text identifier, useful when a single text is rated several times by different annotators
- `annotator_id`: identifier of the person who annotated the text
- `minority_id`: the internal identifier of the minority described in the text
- `negative_emotions`: boolean indicator of the presence of negative emotions in the text
- `call_to_action`: boolean indicator set to true, if the text calls the audience to perform any action, typically with a negative emotions
- `source_of_knowledge`: categorical variable, describing the source of knowledge for the post rating - 0, 1 or 2 (direct, lexical or contextual, but the description of the meaning for different values couldn't be found)
- `irony_sarcasm`: boolean indicator of the present of irony or sarcasm
- `topic`: internal identifier of the topic the text is about
- `text`: post text content
- `rating`: integer value, from 0 to 4 - the higher the value, the more negative the text content is
### Data Splits
The dataset was not originally split at all.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
The dataset was collected from the public forums.
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
The dataset doesn't contain any personal or sensitive information.
## Considerations for Using the Data
### Social Impact of Dataset
The automated hate speech recognition is the main beneficial outcome of using the dataset.
### Discussion of Biases
The dataset contains negative posts only and due to that might underrepresent the whole language.
### Other Known Limitations
Dataset provided for research purposes only. Please check dataset license for additional information.
## Additional Information
### Dataset Curators
The dataset was created by Marek Troszyński and Aleksander Wawer, during work done at [IPI PAN](https://www.ipipan.waw.pl/).
### Licensing Information
According to [Metashare](http://metashare.nlp.ipipan.waw.pl/metashare/repository/browse/polish-hatespeech-corpus/21b7e2366b0011e284b6000423bfd61cbc7616f601724f09bafc8a62c42d56de/), the dataset is licensed under CC-BY-NC-SA, but the version is not mentioned.
### Citation Information
```
@article{troszynski2017czy,
title={Czy komputer rozpozna hejtera? Wykorzystanie uczenia maszynowego (ML) w jako{\'s}ciowej analizie danych},
author={Troszy{\'n}ski, Marek and Wawer, Aleksandra},
journal={Przegl{\k{a}}d Socjologii Jako{\'s}ciowej},
volume={13},
number={2},
pages={62--80},
year={2017},
publisher={Uniwersytet {\L}{\'o}dzki, Wydzia{\l} Ekonomiczno-Socjologiczny, Katedra Socjologii~…}
}
```
### Contributions
Thanks to [@kacperlukawski](https://github.com/kacperlukawski) for adding this dataset. |
false |
# Dataset Card for VCTK
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Edinburg DataShare](https://doi.org/10.7488/ds/2645)
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This CSTR VCTK Corpus includes speech data uttered by 110 English speakers with various accents. Each speaker reads out about 400 sentences, which were selected from a newspaper, the rainbow passage and an elicitation paragraph used for the speech accent archive.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
A data point comprises the path to the audio file, called `file` and its transcription, called `text`.
```
{
'speaker_id': 'p225',
'text_id': '001',
'text': 'Please call Stella.',
'age': '23',
'gender': 'F',
'accent': 'English',
'region': 'Southern England',
'file': '/datasets/downloads/extracted/8ed7dad05dfffdb552a3699777442af8e8ed11e656feb277f35bf9aea448f49e/wav48_silence_trimmed/p225/p225_001_mic1.flac',
'audio':
{
'path': '/datasets/downloads/extracted/8ed7dad05dfffdb552a3699777442af8e8ed11e656feb277f35bf9aea448f49e/wav48_silence_trimmed/p225/p225_001_mic1.flac',
'array': array([0.00485229, 0.00689697, 0.00619507, ..., 0.00811768, 0.00836182, 0.00854492], dtype=float32),
'sampling_rate': 48000
},
'comment': ''
}
```
Each audio file is a single-channel FLAC with a sample rate of 48000 Hz.
### Data Fields
Each row consists of the following fields:
- `speaker_id`: Speaker ID
- `audio`: Audio recording
- `file`: Path to audio file
- `text`: Text transcription of corresponding audio
- `text_id`: Text ID
- `age`: Speaker's age
- `gender`: Speaker's gender
- `accent`: Speaker's accent
- `region`: Speaker's region, if annotation exists
- `comment`: Miscellaneous comments, if any
### Data Splits
The dataset has no predefined splits.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
The dataset consists of people who have donated their voice online. You agree to not attempt to determine the identity of speakers in this dataset.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
Public Domain, Creative Commons Attribution 4.0 International Public License ([CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/legalcode))
### Citation Information
```bibtex
@inproceedings{Veaux2017CSTRVC,
title = {CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit},
author = {Christophe Veaux and Junichi Yamagishi and Kirsten MacDonald},
year = 2017
}
```
### Contributions
Thanks to [@jaketae](https://github.com/jaketae) for adding this dataset. |
false |
# Dataset Card for Narrative QA Manual
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [NarrativeQA Homepage](https://deepmind.com/research/open-source/narrativeqa)
- **Repository:** [NarrativeQA Repo](https://github.com/deepmind/narrativeqa)
- **Paper:** [The NarrativeQA Reading Comprehension Challenge](https://arxiv.org/pdf/1712.07040.pdf)
- **Leaderboard:**
- **Point of Contact:** [Tomáš Kočiský](mailto:tkocisky@google.com) [Jonathan Schwarz](mailto:schwarzjn@google.com) [Phil Blunsom](pblunsom@google.com) [Chris Dyer](cdyer@google.com) [Karl Moritz Hermann](mailto:kmh@google.com) [Gábor Melis](mailto:melisgl@google.com) [Edward Grefenstette](mailto:etg@google.com)
### Dataset Summary
NarrativeQA Manual is an English-language dataset of stories and corresponding questions designed to test reading comprehension, especially on long documents. THIS DATASET REQUIRES A MANUALLY DOWNLOADED FILE! Because of a script in the original repository which downloads the stories from original URLs everytime, the links are sometimes broken or invalid. Therefore, you need to manually download the stories for this dataset using the script provided by the authors (https://github.com/deepmind/narrativeqa/blob/master/download_stories.sh). Running the shell script creates a folder named "tmp" in the root directory and downloads the stories there. This folder containing the stories can be used to load the dataset via `datasets.load_dataset("narrativeqa_manual", data_dir="<path/to/folder>")`.
### Supported Tasks and Leaderboards
The dataset is used to test reading comprehension. There are 2 tasks proposed in the paper: "summaries only" and "stories only", depending on whether the human-generated summary or the full story text is used to answer the question.
### Languages
English
## Dataset Structure
### Data Instances
A typical data point consists of a question and answer pair along with a summary/story which can be used to answer the question. Additional information such as the url, word count, wikipedia page, are also provided.
A typical example looks like this:
```
{
"document": {
"id": "23jncj2n3534563110",
"kind": "movie",
"url": "https://www.imsdb.com/Movie%20Scripts/Name%20of%20Movie.html",
"file_size": 80473,
"word_count": 41000,
"start": "MOVIE screenplay by",
"end": ". THE END",
"summary": {
"text": "Joe Bloggs begins his journey exploring...",
"tokens": ["Joe", "Bloggs", "begins", "his", "journey", "exploring",...],
"url": "http://en.wikipedia.org/wiki/Name_of_Movie",
"title": "Name of Movie (film)"
},
"text": "MOVIE screenplay by John Doe\nSCENE 1..."
},
"question": {
"text": "Where does Joe Bloggs live?",
"tokens": ["Where", "does", "Joe", "Bloggs", "live", "?"],
},
"answers": [
{"text": "At home", "tokens": ["At", "home"]},
{"text": "His house", "tokens": ["His", "house"]}
]
}
```
### Data Fields
- `document.id` - Unique ID for the story.
- `document.kind` - "movie" or "gutenberg" depending on the source of the story.
- `document.url` - The URL where the story was downloaded from.
- `document.file_size` - File size (in bytes) of the story.
- `document.word_count` - Number of tokens in the story.
- `document.start` - First 3 tokens of the story. Used for verifying the story hasn't been modified.
- `document.end` - Last 3 tokens of the story. Used for verifying the story hasn't been modified.
- `document.summary.text` - Text of the wikipedia summary of the story.
- `document.summary.tokens` - Tokenized version of `document.summary.text`.
- `document.summary.url` - Wikipedia URL of the summary.
- `document.summary.title` - Wikipedia Title of the summary.
- `question` - `{"text":"...", "tokens":[...]}` for the question about the story.
- `answers` - List of `{"text":"...", "tokens":[...]}` for valid answers for the question.
### Data Splits
The data is split into training, valiudation, and test sets based on story (i.e. the same story cannot appear in more than one split):
| Train | Valid | Test |
| ------ | ----- | ----- |
| 32747 | 3461 | 10557 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
Stories and movies scripts were downloaded from [Project Gutenburg](https://www.gutenberg.org) and a range of movie script repositories (mainly [imsdb](http://www.imsdb.com)).
#### Who are the source language producers?
The language producers are authors of the stories and scripts as well as Amazon Turk workers for the questions.
### Annotations
#### Annotation process
Amazon Turk Workers were provided with human written summaries of the stories (To make the annotation tractable and to lead annotators towards asking non-localized questions). Stories were matched with plot summaries from Wikipedia using titles and verified the matching with help from human annotators. The annotators were asked to determine if both the story and the summary refer to a movie or a book (as some books are made into movies), or if they are the same part in a series produced in the same year. Annotators on Amazon Mechanical Turk were instructed to write 10 question–answer pairs each based solely on a given summary. Annotators were instructed to imagine that they are writing questions to test students who have read the full stories but not the summaries. We required questions that are specific enough, given the length and complexity of the narratives, and to provide adiverse set of questions about characters, events, why this happened, and so on. Annotators were encouraged to use their own words and we prevented them from copying. We asked for answers that are grammatical, complete sentences, and explicitly allowed short answers (one word, or a few-word phrase, or ashort sentence) as we think that answering with a full sentence is frequently perceived as artificial when asking about factual information. Annotators were asked to avoid extra, unnecessary information in the question or the answer, and to avoid yes/no questions or questions about the author or the actors.
#### Who are the annotators?
Amazon Mechanical Turk workers.
### Personal and Sensitive Information
None
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
The dataset is released under a [Apache-2.0 License](https://github.com/deepmind/narrativeqa/blob/master/LICENSE).
### Citation Information
```
@article{narrativeqa,
author = {Tom\'a\v s Ko\v cisk\'y and Jonathan Schwarz and Phil Blunsom and
Chris Dyer and Karl Moritz Hermann and G\'abor Melis and
Edward Grefenstette},
title = {The {NarrativeQA} Reading Comprehension Challenge},
journal = {Transactions of the Association for Computational Linguistics},
url = {https://TBD},
volume = {TBD},
year = {2018},
pages = {TBD},
}
```
### Contributions
Thanks to [@rsanjaykamath](https://github.com/rsanjaykamath) for adding this dataset. |
false | # RuTurboAlpaca
Dataset of ChatGPT-generated instructions in Russian.
<img src="https://cdn.midjourney.com/770a35fa-00c0-4214-bb88-727dbc7cfaf3/0_0.png" >
* Code: [rulm/self_instruct](https://github.com/IlyaGusev/rulm/tree/master/self_instruct)
* Code is based on [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) and [self-instruct](https://github.com/yizhongw/self-instruct/).
* 29822 examples
Preliminary evaluation by an expert based on 400 samples:
* 83% of samples contain correct instructions
* 63% of samples have correct instructions and outputs
Crowdsouring-based evaluation on 3500 samples:
* 90% of samples contain correct instructions
* 68% of samples have correct instructions and outputs
Prompt template:
```
Составь набор из {{num_tasks}} разных заданий для дообучения языковой модели:
1. Делай задания максимально непохожими друг на друга: по типу, по запрашиваемым действиям, по формулировке, по наличию входа.
2. Задания должны быть выполнимы языковой моделью, которая не умеет работать с картинками, видео, и аудио, и не имеет доступа ко внешнему миру.
3. Используй хороший грамотный русский язык.
4. Делай задания в одно или два предложения.
5. Генерируй подходящие реалистичные входные данные, не используй общие шаблоны типа \"Имя человека\" или [имя] вместо реального имени.
6. Задание может быть без входных данных, в таком случае используй токен <noinput> вместо них.
7. На выходе сгенерируй подходящий длинный ответ.
8. Следуй тому же шаблону, который приведен в примерах, разделяй задания с помощью ###. Это важно!
Примеры заданий:
{% for task in example_tasks %}
{{task.index}}. Задание: {{task.instruction}}
{{task.index}}. Вход: {{task.input}}
{{task.index}}. Выход: {{task.output}}
{{ "###" if not loop.last else "" }}
{% endfor %}
```
## Legal disclaimer
Data is based on OpenAI’s gpt-3.5-turbo, whose [terms of use](https://openai.com/policies/terms-of-use) prohibit for us developing models that compete with OpenAI. Not for you. |
false |
# Dataset Card for FarsiNews
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** []()
- **Repository:** [link](https://github.com/sci2lab/Farsi-datasets)
- **Paper:** []()
- **Leaderboard:** []()
- **Point of Contact:** []()
### Dataset Summary
https://github.com/sci2lab/Farsi-datasets
Contains Farsi (Persian) datasets for Machine Learning tasks, particularly NLP.
These datasets have been extracted from the RSS feed of two Farsi news agency websites:
- Hamshahri
- RadioFarda
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
[More Information Needed]
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
https://github.com/sci2lab/Farsi-datasets
### Contributions
Thanks to [@Narsil](https://github.com/Narsil) for adding this dataset. |
false |
# Dataset Card for [ms_terms]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:**
[Microsoft Terminology Collection](https://www.microsoft.com/en-us/language/terminology)
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
The Microsoft Terminology Collection can be used to develop localized versions of applications that integrate with Microsoft products. It can also be used to integrate Microsoft terminology into other terminology collections or serve as a base IT glossary for language development in the nearly 100 languages available. Terminology is provided in .tbx format, an industry standard for terminology exchange.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Nearly 100 Languages.
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@leoxzhao](https://github.com/leoxzhao), [@lhoestq](https://github.com/lhoestq) for adding this dataset. |
true |
# Dataset Card for PerSenT
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [PerSenT](https://stonybrooknlp.github.io/PerSenT/)
- **Repository:** [https://github.com/MHDBST/PerSenT](https://github.com/MHDBST/PerSenT)
- **Paper:** [arXiv](https://arxiv.org/abs/2011.06128)
- **Leaderboard:** NA
- **Point of Contact:** [Mohaddeseh Bastan](mbastan@cs.stonybrook.edu)
### Dataset Summary
PerSenT is a crowd-sourced dataset that captures the sentiment of an author towards the main entity in a news article. This dataset contains annotations for 5.3k documents and 38k paragraphs covering 3.2k unique entities. For each article, annotators judge what the author’s sentiment is towards the main
(target) entity of the article. The annotations also include similar judgments on paragraphs within the article.
### Supported Tasks and Leaderboards
Sentiment Classification: Each document consists of multiple paragraphs. Each paragraph is labeled separately (Positive, Neutral, Negative) and the author’s sentiment towards the whole document is included as a document-level label.
### Languages
English
## Dataset Structure
### Data Instances
```json
{'DOCUMENT': "Germany's Landesbank Baden Wuertemberg won EU approval Tuesday for a state bailout after it promised to shrink its balance sheet by 40 percent and refocus on lending to companies.\n The bank was several state-owned German institutions to run into trouble last year after it ran up more huge losses from investing in high-risk proprietary trading and capital market activities -- a business the EU has now told it to shun.\n Seven current and former managers of the bank are also being investigated by German authorities for risking or damaging the bank's capital by carrying out or failing to block investments in high-risk deals worth hundreds of millions from 2006.\n The European Commission said its Tuesday approval for the state rescue of the bank and its new restructuring plan would allow it become a viable business again -- and that the cutbacks would help limit the unfair advantage over rivals that the bank would get from the state aid.\n Stuttgart-based LBBW earlier this year received a capital injection of (EURO)5 billion from the bank's shareholders all of them public authorities or state-owned including the state of Baden-Wuerttemberg the region's savings bank association and the city of Stuttgart.",
'DOCUMENT_INDEX': 1,
'MASKED_DOCUMENT': "[TGT] won EU approval Tuesday for a state bailout after it promised to shrink its balance sheet by 40 percent and refocus on lending to companies.\n [TGT] was several state-owned German institutions to run into trouble last year after [TGT] ran up more huge losses from investing in high-risk proprietary trading and capital market activities -- a business the EU has now told it to shun.\n Seven current and former managers of [TGT] are also being investigated by German authorities for risking or damaging [TGT]'s capital by carrying out or failing to block investments in high-risk deals worth hundreds of millions from 2006.\n The European Commission said its Tuesday approval for the state rescue of [TGT] and its new restructuring plan would allow it become a viable business again -- and that the cutbacks would help limit the unfair advantage over rivals that [TGT] would get from the state aid.\n Stuttgart-based LBBW earlier this year received a capital injection of (EURO)5 billion from [TGT]'s shareholders all of them public authorities or state-owned including the state of Baden-Wuerttemberg the region's savings bank association and the city of Stuttgart.",
'Paragraph0': 2,
'Paragraph1': 0,
'Paragraph10': -1,
'Paragraph11': -1,
'Paragraph12': -1,
'Paragraph13': -1,
'Paragraph14': -1,
'Paragraph15': -1,
'Paragraph2': 0,
'Paragraph3': 1,
'Paragraph4': 1,
'Paragraph5': -1,
'Paragraph6': -1,
'Paragraph7': -1,
'Paragraph8': -1,
'Paragraph9': -1,
'TARGET_ENTITY': 'Landesbank Baden Wuertemberg',
'TITLE': 'German bank LBBW wins EU bailout approval',
'TRUE_SENTIMENT': 0}
```
### Data Fields
- DOCUMENT_INDEX: ID of the document per original dataset
- TITLE: Title of the article
- DOCUMENT: Text of the article
- MASKED_DOCUMENT: Text of the article with the target entity masked with `[TGT]` token
- TARGET_ENTITY: The entity that the author is expressing opinion about
- TRUE_SENTIMENT: Label for entire article
- Paragraph{0..15}: Label for each paragraph in the article
**Note**: Labels are one of `[Negative, Neutral, Positive]`. Missing labels were replaced with `-1`.
### Data Splits
To split the dataset, entities were split into 4 mutually exclusive sets. Due to the nature of news collections, some entities tend to dominate the collection. In the collection, there were four entities which were the main entity in nearly 800 articles. To avoid these entities from dominating the train or test splits, these were moved them to a separate test collection. The remaining was split into a training, dev, and test sets at random. Thus the collection includes one standard test set consisting of articles drawn at random (Test Standard), while the other is a test set which contains multiple articles about a small number of popular entities (Test Frequent).
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
Articles were selected from 3 sources:
1. MPQA (Deng and Wiebe, 2015; Wiebe et al., 2005): This dataset contains news articles manually annotated for opinions, beliefs, emotions, sentiments, speculations, etc. It also has target annotations which are entities and event anchored to the heads of noun or verb phrases. All decisions on this dataset are made on sentence-level and over short spans.
2. KBP Challenge (Ellis et al., 2014): This resource contains TAC 2014 KBP English sentiment slot filling challenge dataset. This is a document-level sentiment filling dataset. In this task, given an entity and a sentiment (positive/negative) from the document, the goal is to find entities toward which
the original entity holds the given sentimental view. We selected documents from this resource which have been used in the following similar work in sentiment analysis task (Choi et al., 2016).
3. Media Rank (Ye and Skiena, 2019): This dataset ranks about 50k news sources along different aspects. It is also used for classifying political ideology of news articles (Kulkarni et al., 2018).
Pre-processing steps:
- First we find all the person entities in each article, using Stanford NER (Name Entity Resolution) tagger (Finkel et al., 2005) and all mentions of them using co-reference resolution (Clark and Manning, 2016; Co, 2017).
- We removed articles which are not likely to have a main entity of focus. We used a simple heuristic of removing articles in which the most frequent person entity is mentioned only three times or less (even when counting co-referent mentions).
- For the articles that remain we deemed the most frequent entity to be the main entity of the article. We also filtered out extremely long and extremely short articles to keep the articles which have at least 3 paragraphs and at most 16 paragraphs.
Documents are randomly separated into train, dev, and two test sets. We ensure that each entity appears in only one of the sets. Our goal here is to avoid easy to learn biases over entities. To avoid the most frequent entities from dominating the training or the test sets, we remove articles that covered the most frequent entities and use them as a separate test set (referred to as frequent test set) in addition to the randomly drawn standard test set.
### Annotations
#### Annotation process
We obtained document and paragraph level annotations with the help of Amazon Mechanical Turk workers. The workers first verified if the target entity we provide is indeed the main entity in the document. Then, they rated each paragraph in a document that contained a direct mention or a reference to the target
entity. Last, they rated the sentiment towards the entity based on the entire document. In both cases, the workers made assessments about the authors view based on what they said about the target entity. For both paragraph and document level sentiment, the workers chose from five rating categories: Negative,
Slightly Negative, Neutral, Slightly Positive, or Positive. We then combine the fine-grained annotations to obtain three coarse-grained classes Negative, Neutral, or Positive.
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
[More Information Needed]
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[Creative Commons Attribution 4.0 International License](http://creativecommons.org/licenses/by/4.0/)
### Citation Information
```
@inproceedings{bastan2020authors,
title={Author's Sentiment Prediction},
author={Mohaddeseh Bastan and Mahnaz Koupaee and Youngseo Son and Richard Sicoli and Niranjan Balasubramanian},
year={2020},
eprint={2011.06128},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@jeromeku](https://github.com/jeromeku) for adding this dataset. |
true |
# Dataset Card for RoSent
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [GitHub](https://github.com/dumitrescustefan/Romanian-Transformers/tree/examples/examples/sentiment_analysis)
- **Repository:** [GitHub](https://github.com/dumitrescustefan/Romanian-Transformers/tree/examples/examples/sentiment_analysis)
- **Paper:** [arXiv preprint](https://arxiv.org/pdf/2009.08712.pdf)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This dataset is a Romanian Sentiment Analysis dataset. It is present in a processed form, as used by the authors of [`Romanian Transformers`](https://github.com/dumitrescustefan/Romanian-Transformers) in their examples and based on the original data present in at [this GitHub repository](https://github.com/katakonst/sentiment-analysis-tensorflow). The original data contains product and movie reviews in Romanian.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
This dataset is present in Romanian language.
## Dataset Structure
### Data Instances
An instance from the `train` split:
```
{'id': '0', 'label': 1, 'original_id': '0', 'sentence': 'acest document mi-a deschis cu adevarat ochii la ceea ce oamenii din afara statelor unite s-au gandit la atacurile din 11 septembrie. acest film a fost construit in mod expert si prezinta acest dezastru ca fiind mai mult decat un atac asupra pamantului american. urmarile acestui dezastru sunt previzionate din multe tari si perspective diferite. cred ca acest film ar trebui sa fie mai bine distribuit pentru acest punct. de asemenea, el ajuta in procesul de vindecare sa vada in cele din urma altceva decat stirile despre atacurile teroriste. si unele dintre piese sunt de fapt amuzante, dar nu abuziv asa. acest film a fost extrem de recomandat pentru mine, si am trecut pe acelasi sentiment.'}
```
### Data Fields
- `original_id`: a `string` feature containing the original id from the file.
- `id`: a `string` feature .
- `sentence`: a `string` feature.
- `label`: a classification label, with possible values including `negative` (0), `positive` (1).
### Data Splits
This dataset has two splits: `train` with 17941 examples, and `test` with 11005 examples.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
The source dataset is present at the [this GitHub repository](https://github.com/katakonst/sentiment-analysis-tensorflow) and is based on product and movie reviews. The original source is unknown.
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Stefan Daniel Dumitrescu, Andrei-Marious Avram, Sampo Pyysalo, [@katakonst](https://github.com/katakonst)
### Licensing Information
[More Information Needed]
### Citation Information
```
@article{dumitrescu2020birth,
title={The birth of Romanian BERT},
author={Dumitrescu, Stefan Daniel and Avram, Andrei-Marius and Pyysalo, Sampo},
journal={arXiv preprint arXiv:2009.08712},
year={2020}
}
```
### Contributions
Thanks to [@gchhablani](https://github.com/gchhablani) and [@iliemihai](https://github.com/iliemihai) for adding this dataset. |
false | # Dataset Card for "dev_sft"
[Tigerbot模型](https://github.com/TigerResearch/TigerBot#%E6%A8%A1%E5%9E%8B%E4%B8%8B%E8%BD%BD)develop sft数据。
在[train_sft.py](https://github.com/TigerResearch/TigerBot/blob/main/train/train_sft.py)中被使用。
## Usage
```python
import datasets
ds_sft = datasets.load_dataset('TigerResearch/dev_sft')
```
## Field
- instruction: 指令
- input: 上下文信息(Optional)
- output: 生成目标 |
true |
# Dataset Card for wordsim-353 in Yorùbá (yoruba_wordsim353)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** -
- **Repository:** https://github.com/ajesujoba/YorubaTwi-Embedding
- **Paper:** https://www.aclweb.org/anthology/2020.lrec-1.335/
- **Leaderboard:** -
- **Point of Contact:** Jesujoba Alabi ( jesujobaoluwadara.alabi (at) dfki.de ) and David Adelani ( didelani (at) lsv.uni-saarland.de )
### Dataset Summary
A translation of the word pair similarity dataset wordsim-353 to Yorùbá.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Yorùbá (ISO 639-1: yo)
## Dataset Structure
### Data Instances
An instance consists of a pair of words as well as their similarity. The dataset contains both the original English words (from wordsim-353) as well as their translation to Yorùbá.
### Data Fields
- `english1`: the first word of the pair; the original English word
- `english2`: the second word of the pair; the original English word
- `yoruba1`: the first word of the pair; translation to Yorùbá
- `yoruba2`: the second word of the pair; translation to Yorùbá
- `similarity`: similarity rating according to the English dataset
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@michael-aloys](https://github.com/michael-aloys) for adding this dataset. |
true |
# Dataset Card for Emotional Tone in Arabic
## Table of Contents
- [Dataset Card for Emotional Tone in Arabic](#dataset-card-for-emotional-tone-in-arabic)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [|split|num examples|](#splitnum-examples)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Initial Data Collection and Normalization](#initial-data-collection-and-normalization)
- [Who are the source language producers?](#who-are-the-source-language-producers)
- [Annotations](#annotations)
- [Annotation process](#annotation-process)
- [Who are the annotators?](#who-are-the-annotators)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Repository:** [Repository](https://github.com/AmrMehasseb/Emotional-Tone)
- **Paper:** [Emotional Tone Detection in Arabic Tweets](https://www.researchgate.net/publication/328164296_Emotional_Tone_Detection_in_Arabic_Tweets_18th_International_Conference_CICLing_2017_Budapest_Hungary_April_17-23_2017_Revised_Selected_Papers_Part_II)
- **Point of Contact:** [Amr Al-Khatib](https://github.com/AmrMehasseb)
### Dataset Summary
Dataset of 10065 tweets in Arabic for Emotion detection in Arabic text
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is based on Arabic.
## Dataset Structure
### Data Instances
example:
```
>>> {'label': 0, 'tweet': 'الاوليمبياد الجايه هكون لسه ف الكليه ..'}
```
### Data Fields
- "tweet": plain text tweet in Arabic
- "label": emotion class label
the dataset distribution and balance for each class looks like the following
|label||Label description | Count |
|---------|---------| ------- |
|0 |none | 1550 |
|1 |anger | 1444 |
|2 |joy | 1281 |
|3 |sadness | 1256 |
|4 |love | 1220 |
|5 |sympathy | 1062 |
|6 |surprise | 1045 |
|7 |fear | 1207 |
### Data Splits
The dataset is not split.
| | train |
|----------|--------:|
| no split | 10,065 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[Needs More Information]
### Discussion of Biases
[Needs More Information]
### Other Known Limitations
[Needs More Information]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```
@inbook{inbook,
author = {Al-Khatib, Amr and El-Beltagy, Samhaa},
year = {2018},
month = {01},
pages = {105-114},
title = {Emotional Tone Detection in Arabic Tweets: 18th International Conference, CICLing 2017, Budapest, Hungary, April 17–23, 2017, Revised Selected Papers, Part II},
isbn = {978-3-319-77115-1},
doi = {10.1007/978-3-319-77116-8_8}
}
```
### Contributions
Thanks to [@abdulelahsm](https://github.com/abdulelahsm) for adding this dataset. |
false |
# Dataset Card for GEM/wiki_auto_asset_turk
## Dataset Description
- **Homepage:** n/a
- **Repository:** https://github.com/chaojiang06/wiki-auto, [ASSET repository
- **Paper:** https://aclanthology.org/2020.acl-main.709/, [ASSET
- **Leaderboard:** N/A
- **Point of Contact:** WikiAuto: Chao Jiang; ASSET: Fernando Alva-Manchego and Louis Martin; TURK: Wei Xu
### Link to Main Data Card
You can find the main data card on the [GEM Website](https://gem-benchmark.com/data_cards/wiki_auto_asset_turk).
### Dataset Summary
WikiAuto is an English simplification dataset that we paired with ASSET and TURK, two very high-quality evaluation datasets, as test sets. The input is an English sentence taken from Wikipedia and the target a simplified sentence. ASSET and TURK contain the same test examples but have references that are simplified in different ways (splitting sentences vs. rewriting and splitting).
You can load the dataset via:
```
import datasets
data = datasets.load_dataset('GEM/wiki_auto_asset_turk')
```
The data loader can be found [here](https://huggingface.co/datasets/GEM/wiki_auto_asset_turk).
#### website
n/a
#### paper
[WikiAuto](https://aclanthology.org/2020.acl-main.709/), [ASSET](https://aclanthology.org/2020.acl-main.424/), [TURK](https://aclanthology.org/Q16-1029/)
#### authors
WikiAuto: Chao Jiang, Mounica Maddela, Wuwei Lan, Yang Zhong, Wei Xu; ASSET: Fernando Alva-Manchego, Louis Martin, Antoine Bordes, Carolina Scarton, and Benoîıt Sagot, and Lucia Specia; TURK: Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, and Chris Callison-Burch
## Dataset Overview
### Where to find the Data and its Documentation
#### Download
<!-- info: What is the link to where the original dataset is hosted? -->
<!-- scope: telescope -->
[Wiki-Auto repository](https://github.com/chaojiang06/wiki-auto), [ASSET repository](https://github.com/facebookresearch/asset), [TURKCorpus](https://github.com/cocoxu/simplification)
#### Paper
<!-- info: What is the link to the paper describing the dataset (open access preferred)? -->
<!-- scope: telescope -->
[WikiAuto](https://aclanthology.org/2020.acl-main.709/), [ASSET](https://aclanthology.org/2020.acl-main.424/), [TURK](https://aclanthology.org/Q16-1029/)
#### BibTex
<!-- info: Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex. -->
<!-- scope: microscope -->
WikiAuto:
```
@inproceedings{jiang-etal-2020-neural,
title = "Neural {CRF} Model for Sentence Alignment in Text Simplification",
author = "Jiang, Chao and
Maddela, Mounica and
Lan, Wuwei and
Zhong, Yang and
Xu, Wei",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.acl-main.709",
doi = "10.18653/v1/2020.acl-main.709",
pages = "7943--7960",
}
```
ASSET:
```
@inproceedings{alva-manchego-etal-2020-asset,
title = "{ASSET}: {A} Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations",
author = "Alva-Manchego, Fernando and
Martin, Louis and
Bordes, Antoine and
Scarton, Carolina and
Sagot, Beno{\^\i}t and
Specia, Lucia",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.acl-main.424",
pages = "4668--4679",
}
```
TURK:
```
@article{Xu-EtAl:2016:TACL,
author = {Wei Xu and Courtney Napoles and Ellie Pavlick and Quanze Chen and Chris Callison-Burch},
title = {Optimizing Statistical Machine Translation for Text Simplification},
journal = {Transactions of the Association for Computational Linguistics},
volume = {4},
year = {2016},
url = {https://cocoxu.github.io/publications/tacl2016-smt-simplification.pdf},
pages = {401--415}
}
```
#### Contact Name
<!-- quick -->
<!-- info: If known, provide the name of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
WikiAuto: Chao Jiang; ASSET: Fernando Alva-Manchego and Louis Martin; TURK: Wei Xu
#### Contact Email
<!-- info: If known, provide the email of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
jiang.1530@osu.edu, f.alva@sheffield.ac.uk, louismartincs@gmail.com, wei.xu@cc.gatech.edu
#### Has a Leaderboard?
<!-- info: Does the dataset have an active leaderboard? -->
<!-- scope: telescope -->
no
### Languages and Intended Use
#### Multilingual?
<!-- quick -->
<!-- info: Is the dataset multilingual? -->
<!-- scope: telescope -->
no
#### Covered Languages
<!-- quick -->
<!-- info: What languages/dialects are covered in the dataset? -->
<!-- scope: telescope -->
`English`
#### Whose Language?
<!-- info: Whose language is in the dataset? -->
<!-- scope: periscope -->
Wiki-Auto contains English text only (BCP-47: `en`). It is presented as a translation task where Wikipedia Simple English is treated as its own idiom. For a statement of what is intended (but not always observed) to constitute Simple English on this platform, see [Simple English in Wikipedia](https://simple.wikipedia.org/wiki/Wikipedia:About#Simple_English).
Both ASSET and TURK use crowdsourcing to change references, and their language is thus a combination of the WikiAuto data and the language of the demographic on mechanical Turk
#### License
<!-- quick -->
<!-- info: What is the license of the dataset? -->
<!-- scope: telescope -->
other: Other license
#### Intended Use
<!-- info: What is the intended use of the dataset? -->
<!-- scope: microscope -->
WikiAuto provides a set of aligned sentences from English Wikipedia and Simple English Wikipedia as a resource to train sentence simplification systems.
The authors first crowd-sourced a set of manual alignments between sentences in a subset of the Simple English Wikipedia and their corresponding versions in English Wikipedia (this corresponds to the `manual` config in this version of the dataset), then trained a neural CRF system to predict these alignments.
The trained alignment prediction model was then applied to the other articles in Simple English Wikipedia with an English counterpart to create a larger corpus of aligned sentences (corresponding to the `auto` and `auto_acl` configs here).
[ASSET](https://github.com/facebookresearch/asset) [(Alva-Manchego et al., 2020)](https://www.aclweb.org/anthology/2020.acl-main.424.pdf) is multi-reference dataset for the evaluation of sentence simplification in English. The dataset uses the same 2,359 sentences from [TurkCorpus](https://github.com/cocoxu/simplification/) [(Xu et al., 2016)](https://www.aclweb.org/anthology/Q16-1029.pdf) and each sentence is associated with 10 crowdsourced simplifications. Unlike previous simplification datasets, which contain a single transformation (e.g., lexical paraphrasing in TurkCorpus or sentence
splitting in [HSplit](https://www.aclweb.org/anthology/D18-1081.pdf)), the simplifications in ASSET encompass a variety of rewriting transformations.
TURKCorpus is a high quality simplification dataset where each source (not simple) sentence is associated with 8 human-written simplifications that focus on lexical paraphrasing. It is one of the two evaluation datasets for the text simplification task in GEM. It acts as the validation and test set for paraphrasing-based simplification that does not involve sentence splitting and deletion.
#### Add. License Info
<!-- info: What is the 'other' license of the dataset? -->
<!-- scope: periscope -->
WikiAuto: `CC BY-NC 3.0`, ASSET: `CC BY-NC 4.0`, TURK: `GNU General Public License v3.0`
#### Primary Task
<!-- info: What primary task does the dataset support? -->
<!-- scope: telescope -->
Simplification
#### Communicative Goal
<!-- quick -->
<!-- info: Provide a short description of the communicative goal of a model trained for this task on this dataset. -->
<!-- scope: periscope -->
The goal is to communicate the main ideas of source sentence in a way that is easier to understand by non-native speakers of English.
### Credit
#### Curation Organization Type(s)
<!-- info: In what kind of organization did the dataset curation happen? -->
<!-- scope: telescope -->
`academic`, `industry`
#### Curation Organization(s)
<!-- info: Name the organization(s). -->
<!-- scope: periscope -->
Ohio State University, University of Sheffield, Inria, Facebook AI Research, Imperial College London, University of Pennsylvania, John Hopkins University
#### Dataset Creators
<!-- info: Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s). -->
<!-- scope: microscope -->
WikiAuto: Chao Jiang, Mounica Maddela, Wuwei Lan, Yang Zhong, Wei Xu; ASSET: Fernando Alva-Manchego, Louis Martin, Antoine Bordes, Carolina Scarton, and Benoîıt Sagot, and Lucia Specia; TURK: Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, and Chris Callison-Burch
#### Funding
<!-- info: Who funded the data creation? -->
<!-- scope: microscope -->
WikiAuto: NSF, ODNI, IARPA, Figure Eight AI, and Criteo. ASSET: PRAIRIE Institute, ANR. TURK: NSF
#### Who added the Dataset to GEM?
<!-- info: Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM. -->
<!-- scope: microscope -->
GEM v1 had separate data cards for WikiAuto, ASSET, and TURK. They were contributed by Dhruv Kumar and Mounica Maddela. The initial data loader was written by Yacine Jernite. Sebastian Gehrmann merged and extended the data cards and migrated the loader to the v2 infrastructure.
### Dataset Structure
#### Data Fields
<!-- info: List and describe the fields present in the dataset. -->
<!-- scope: telescope -->
- `source`: A source sentence from one of the datasets
- `target`: A single simplified sentence corresponding to `source`
- `references`: In the case of ASSET/TURK, references is a list of strings corresponding to the different references.
#### Reason for Structure
<!-- info: How was the dataset structure determined? -->
<!-- scope: microscope -->
The underlying datasets have extensive secondary annotations that can be used in conjunction with the GEM version. We omit those annotations to simplify the format into one that can be used by seq2seq models.
#### Example Instance
<!-- info: Provide a JSON formatted example of a typical instance in the dataset. -->
<!-- scope: periscope -->
```
{
'source': 'In early work, Rutherford discovered the concept of radioactive half-life , the radioactive element radon, and differentiated and named alpha and beta radiation .',
'target': 'Rutherford discovered the radioactive half-life, and the three parts of radiation which he named Alpha, Beta, and Gamma.'
}
```
#### Data Splits
<!-- info: Describe and name the splits in the dataset if there are more than one. -->
<!-- scope: periscope -->
In WikiAuto, which is used as training and validation set, the following splits are provided:
| | Tain | Dev | Test |
| ----- | ------ | ----- | ---- |
| Total sentence pairs | 373801 | 73249 | 118074 |
| Aligned sentence pairs | 1889 | 346 | 677 |
ASSET does not contain a training set; many models use [WikiLarge](https://github.com/XingxingZhang/dress) (Zhang and Lapata, 2017) for training. For GEM, [Wiki-Auto](https://github.com/chaojiang06/wiki-auto) will be used for training the model.
Each input sentence has 10 associated reference simplified sentences. The statistics of ASSET are given below.
| | Dev | Test | Total |
| ----- | ------ | ---- | ----- |
| Input Sentences | 2000 | 359 | 2359 |
| Reference Simplifications | 20000 | 3590 | 23590 |
The test and validation sets are the same as those of [TurkCorpus](https://github.com/cocoxu/simplification/). The split was random.
There are 19.04 tokens per reference on average (lower than 21.29 and 25.49 for TurkCorpus and HSplit, respectively). Most (17,245) of the referece sentences do not involve sentence splitting.
TURKCorpus does not contain a training set; many models use [WikiLarge](https://github.com/XingxingZhang/dress) (Zhang and Lapata, 2017) or [Wiki-Auto](https://github.com/chaojiang06/wiki-auto) (Jiang et. al 2020) for training.
Each input sentence has 8 associated reference simplified sentences. 2,359 input sentences are randomly split into 2,000 validation and 359 test sentences.
| | Dev | Test | Total |
| ----- | ------ | ---- | ----- |
| Input Sentences | 2000 | 359 | 2359 |
| Reference Simplifications | 16000 | 2872 | 18872 |
There are 21.29 tokens per reference on average.
#### Splitting Criteria
<!-- info: Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here. -->
<!-- scope: microscope -->
In our setup, we use WikiAuto as training/validation corpus and ASSET and TURK as test corpora. ASSET and TURK have the same inputs but differ in their reference style. Researchers can thus conduct targeted evaluations based on the strategies that a model should learn.
## Dataset in GEM
### Rationale for Inclusion in GEM
#### Why is the Dataset in GEM?
<!-- info: What does this dataset contribute toward better generation evaluation and why is it part of GEM? -->
<!-- scope: microscope -->
WikiAuto is the largest open text simplification dataset currently available. ASSET and TURK are high quality test sets that are compatible with WikiAuto.
#### Similar Datasets
<!-- info: Do other datasets for the high level task exist? -->
<!-- scope: telescope -->
yes
#### Unique Language Coverage
<!-- info: Does this dataset cover other languages than other datasets for the same task? -->
<!-- scope: periscope -->
no
#### Difference from other GEM datasets
<!-- info: What else sets this dataset apart from other similar datasets in GEM? -->
<!-- scope: microscope -->
It's unique setup with multiple test sets makes the task interesting since it allows for evaluation of multiple generations and systems that simplify in different ways.
#### Ability that the Dataset measures
<!-- info: What aspect of model ability can be measured with this dataset? -->
<!-- scope: periscope -->
simplification
### GEM-Specific Curation
#### Modificatied for GEM?
<!-- info: Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data? -->
<!-- scope: telescope -->
yes
#### GEM Modifications
<!-- info: What changes have been made to he original dataset? -->
<!-- scope: periscope -->
`other`
#### Modification Details
<!-- info: For each of these changes, described them in more details and provided the intended purpose of the modification -->
<!-- scope: microscope -->
We removed secondary annotations and focus on the simple `input->output` format, but combine the different sub-datasets.
#### Additional Splits?
<!-- info: Does GEM provide additional splits to the dataset? -->
<!-- scope: telescope -->
yes
#### Split Information
<!-- info: Describe how the new splits were created -->
<!-- scope: periscope -->
we split the original test set according to syntactic complexity of the source sentences. To characterize sentence syntactic complexity, we use the 8-level developmental level (d-level) scale proposed by [Covington et al. (2006)](https://www.researchgate.net/publication/254033869_How_complex_is_that_sentence_A_proposed_revision_of_the_Rosenberg_and_Abbeduto_D-Level_Scale) and the implementation of [Lu, Xiaofei (2010)](https://www.jbe-platform.com/content/journals/10.1075/ijcl.15.4.02lu).
We thus split the original test set into 8 subsets corresponding to the 8 d-levels assigned to source sentences. We obtain the following number of instances per level and average d-level of the dataset:
| Total nb. sentences | L0 | L1 | L2 | L3 | L4 | L5 | L6 | L7 | Mean Level |
|-------------------- | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ---------- |
| 359 | 166 | 0 | 58 | 32 | 5 | 28 | 7 | 63 | 2.38 |
#### Split Motivation
<!-- info: What aspects of the model's generation capacities were the splits created to test? -->
<!-- scope: periscope -->
The goal was to assess performance when simplifying source sentences with different syntactic structure and complexity.
### Getting Started with the Task
#### Pointers to Resources
<!-- info: Getting started with in-depth research on the task. Add relevant pointers to resources that researchers can consult when they want to get started digging deeper into the task. -->
<!-- scope: microscope -->
There are recent supervised ([Martin et al., 2019](https://arxiv.org/abs/1910.02677), [Kriz et al., 2019](https://www.aclweb.org/anthology/N19-1317/), [Dong et al., 2019](https://www.aclweb.org/anthology/P19-1331/), [Zhang and Lapata, 2017](https://www.aclweb.org/anthology/D17-1062/)) and unsupervised ([Martin et al., 2020](https://arxiv.org/abs/2005.00352v1), [Kumar et al., 2020](https://www.aclweb.org/anthology/2020.acl-main.707/), [Surya et al., 2019](https://www.aclweb.org/anthology/P19-1198/)) text simplification models that can be used as baselines.
#### Technical Terms
<!-- info: Technical terms used in this card and the dataset and their definitions -->
<!-- scope: microscope -->
The common metric used for automatic evaluation is SARI [(Xu et al., 2016)](https://www.aclweb.org/anthology/Q16-1029/).
## Previous Results
### Previous Results
#### Measured Model Abilities
<!-- info: What aspect of model ability can be measured with this dataset? -->
<!-- scope: telescope -->
Simplification
#### Metrics
<!-- info: What metrics are typically used for this task? -->
<!-- scope: periscope -->
`Other: Other Metrics`, `BLEU`
#### Other Metrics
<!-- info: Definitions of other metrics -->
<!-- scope: periscope -->
SARI: A simplification metric that considers both input and references to measure the "goodness" of words that are added, deleted, and kept.
#### Proposed Evaluation
<!-- info: List and describe the purpose of the metrics and evaluation methodology (including human evaluation) that the dataset creators used when introducing this task. -->
<!-- scope: microscope -->
The original authors of WikiAuto and ASSET used human evaluation to assess the fluency, adequacy, and simplicity (details provided in the paper). For TURK, the authors measured grammaticality, meaning-preservation, and simplicity gain (details in the paper).
#### Previous results available?
<!-- info: Are previous results available? -->
<!-- scope: telescope -->
no
## Dataset Curation
### Original Curation
#### Original Curation Rationale
<!-- info: Original curation rationale -->
<!-- scope: telescope -->
Wiki-Auto provides a new version of the Wikipedia corpus that is larger, contains 75% less defective pairs and has more complex rewrites than the previous WIKILARGE dataset.
ASSET was created in order to improve the evaluation of sentence simplification. It uses the same input sentences as the [TurkCorpus](https://github.com/cocoxu/simplification/) dataset from [(Xu et al., 2016)](https://www.aclweb.org/anthology/Q16-1029.pdf). The 2,359 input sentences of TurkCorpus are a sample of "standard" (not simple) sentences from the [Parallel Wikipedia Simplification (PWKP)](https://www.informatik.tu-darmstadt.de/ukp/research_6/data/sentence_simplification/simple_complex_sentence_pairs/index.en.jsp) dataset [(Zhu et al., 2010)](https://www.aclweb.org/anthology/C10-1152.pdf), which come from the August 22, 2009 version of Wikipedia. The sentences of TurkCorpus were chosen to be of similar length [(Xu et al., 2016)](https://www.aclweb.org/anthology/Q16-1029.pdf). No further information is provided on the sampling strategy.
The TurkCorpus dataset was developed in order to overcome some of the problems with sentence pairs from Standard and Simple Wikipedia: a large fraction of sentences were misaligned, or not actually simpler [(Xu et al., 2016)](https://www.aclweb.org/anthology/Q16-1029.pdf). However, TurkCorpus mainly focused on *lexical paraphrasing*, and so cannot be used to evaluate simplifications involving *compression* (deletion) or *sentence splitting*. HSplit [(Sulem et al., 2018)](https://www.aclweb.org/anthology/D18-1081.pdf), on the other hand, can only be used to evaluate sentence splitting. The reference sentences in ASSET include a wider variety of sentence rewriting strategies, combining splitting, compression and paraphrasing. Annotators were given examples of each kind of transformation individually, as well as all three transformations used at once, but were allowed to decide which transformations to use for any given sentence.
An example illustrating the differences between TurkCorpus, HSplit and ASSET is given below:
> **Original:** He settled in London, devoting himself chiefly to practical teaching.
>
> **TurkCorpus:** He rooted in London, devoting himself mainly to practical teaching.
>
> **HSplit:** He settled in London. He devoted himself chiefly to practical teaching.
>
> **ASSET:** He lived in London. He was a teacher.
#### Communicative Goal
<!-- info: What was the communicative goal? -->
<!-- scope: periscope -->
The goal is to communicate the same information as the source sentence using simpler words and grammar.
#### Sourced from Different Sources
<!-- info: Is the dataset aggregated from different data sources? -->
<!-- scope: telescope -->
yes
#### Source Details
<!-- info: List the sources (one per line) -->
<!-- scope: periscope -->
Wikipedia
### Language Data
#### How was Language Data Obtained?
<!-- info: How was the language data obtained? -->
<!-- scope: telescope -->
`Found`
#### Where was it found?
<!-- info: If found, where from? -->
<!-- scope: telescope -->
`Single website`
#### Language Producers
<!-- info: What further information do we have on the language producers? -->
<!-- scope: microscope -->
The dataset uses language from Wikipedia: some demographic information is provided [here](https://en.wikipedia.org/wiki/Wikipedia:Who_writes_Wikipedia%3F).
#### Data Validation
<!-- info: Was the text validated by a different worker or a data curator? -->
<!-- scope: telescope -->
not validated
#### Was Data Filtered?
<!-- info: Were text instances selected or filtered? -->
<!-- scope: telescope -->
algorithmically
#### Filter Criteria
<!-- info: What were the selection criteria? -->
<!-- scope: microscope -->
The authors mention that they "extracted 138,095 article pairs from the 2019/09 Wikipedia dump using an improved version of the [WikiExtractor](https://github.com/attardi/wikiextractor) library". The [SpaCy](https://spacy.io/) library is used for sentence splitting.
### Structured Annotations
#### Additional Annotations?
<!-- quick -->
<!-- info: Does the dataset have additional annotations for each instance? -->
<!-- scope: telescope -->
crowd-sourced
#### Number of Raters
<!-- info: What is the number of raters -->
<!-- scope: telescope -->
11<n<50
#### Rater Qualifications
<!-- info: Describe the qualifications required of an annotator. -->
<!-- scope: periscope -->
WikiAuto (Figure Eight): No information provided.
ASSET (MTurk):
- Having a HIT approval rate over 95%, and over 1000 HITs approved. No other demographic or compensation information is provided.
- Passing a Qualification Test (appropriately simplifying sentences). Out of 100 workers, 42 passed the test.
- Being a resident of the United States, United Kingdom or Canada.
TURK (MTurk):
- Reference sentences were written by workers with HIT approval rate over 95%. No other demographic or compensation information is provided.
#### Raters per Training Example
<!-- info: How many annotators saw each training example? -->
<!-- scope: periscope -->
1
#### Raters per Test Example
<!-- info: How many annotators saw each test example? -->
<!-- scope: periscope -->
>5
#### Annotation Service?
<!-- info: Was an annotation service used? -->
<!-- scope: telescope -->
yes
#### Which Annotation Service
<!-- info: Which annotation services were used? -->
<!-- scope: periscope -->
`Amazon Mechanical Turk`, `Appen`
#### Annotation Values
<!-- info: Purpose and values for each annotation -->
<!-- scope: microscope -->
WikiAuto: Sentence alignment labels were crowdsourced for 500 randomly sampled document pairs (10,123 sentence pairs total). The authors pre-selected several alignment candidates from English Wikipedia for each Simple Wikipedia sentence based on various similarity metrics, then asked the crowd-workers to annotate these pairs. Finally, they trained their alignment model on this manually annotated dataset to obtain automatically aligned sentences (138,095 document pairs, 488,332 sentence pairs).
No demographic annotation is provided for the crowd workers. The [Figure Eight](https://www.figure-eight.com/) platform now part of Appen) was used for the annotation process.
ASSET: The instructions given to the annotators are available [here](https://github.com/facebookresearch/asset/blob/master/crowdsourcing/AMT_AnnotationInstructions.pdf).
TURK: The references are crowdsourced from Amazon Mechanical Turk. The annotators were asked to provide simplifications without losing any information or splitting the input sentence. No other demographic or compensation information is provided in the TURKCorpus paper. The instructions given to the annotators are available in the paper.
#### Any Quality Control?
<!-- info: Quality control measures? -->
<!-- scope: telescope -->
none
### Consent
#### Any Consent Policy?
<!-- info: Was there a consent policy involved when gathering the data? -->
<!-- scope: telescope -->
yes
#### Consent Policy Details
<!-- info: What was the consent policy? -->
<!-- scope: microscope -->
Both Figure Eight and Amazon Mechanical Turk raters forfeit the right to their data as part of their agreements.
### Private Identifying Information (PII)
#### Contains PII?
<!-- quick -->
<!-- info: Does the source language data likely contain Personal Identifying Information about the data creators or subjects? -->
<!-- scope: telescope -->
no PII
#### Justification for no PII
<!-- info: Provide a justification for selecting `no PII` above. -->
<!-- scope: periscope -->
Since the dataset is created from Wikipedia/Simple Wikipedia, all the information contained in the dataset is already in the public domain.
### Maintenance
#### Any Maintenance Plan?
<!-- info: Does the original dataset have a maintenance plan? -->
<!-- scope: telescope -->
no
## Broader Social Context
### Previous Work on the Social Impact of the Dataset
#### Usage of Models based on the Data
<!-- info: Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems? -->
<!-- scope: telescope -->
no
### Impact on Under-Served Communities
#### Addresses needs of underserved Communities?
<!-- info: Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models). -->
<!-- scope: telescope -->
no
### Discussion of Biases
#### Any Documented Social Biases?
<!-- info: Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group. -->
<!-- scope: telescope -->
yes
#### Links and Summaries of Analysis Work
<!-- info: Provide links to and summaries of works analyzing these biases. -->
<!-- scope: microscope -->
The dataset may contain some social biases, as the input sentences are based on Wikipedia. Studies have shown that the English Wikipedia contains both gender biases [(Schmahl et al., 2020)](https://research.tudelft.nl/en/publications/is-wikipedia-succeeding-in-reducing-gender-bias-assessing-changes) and racial biases [(Adams et al., 2019)](https://journals.sagepub.com/doi/pdf/10.1177/2378023118823946).
## Considerations for Using the Data
### PII Risks and Liability
#### Potential PII Risk
<!-- info: Considering your answers to the PII part of the Data Curation Section, describe any potential privacy to the data subjects and creators risks when using the dataset. -->
<!-- scope: microscope -->
All the data is in the public domain.
### Licenses
#### Copyright Restrictions on the Dataset
<!-- info: Based on your answers in the Intended Use part of the Data Overview Section, which of the following best describe the copyright and licensing status of the dataset? -->
<!-- scope: periscope -->
`open license - commercial use allowed`
#### Copyright Restrictions on the Language Data
<!-- info: Based on your answers in the Language part of the Data Curation Section, which of the following best describe the copyright and licensing status of the underlying language data? -->
<!-- scope: periscope -->
`open license - commercial use allowed`
### Known Technical Limitations
#### Technical Limitations
<!-- info: Describe any known technical limitations, such as spurrious correlations, train/test overlap, annotation biases, or mis-annotations, and cite the works that first identified these limitations when possible. -->
<!-- scope: microscope -->
The dataset may contain some social biases, as the input sentences are based on Wikipedia. Studies have shown that the English Wikipedia contains both gender biases [(Schmahl et al., 2020)](https://research.tudelft.nl/en/publications/is-wikipedia-succeeding-in-reducing-gender-bias-assessing-changes) and racial biases [(Adams et al., 2019)](https://journals.sagepub.com/doi/pdf/10.1177/2378023118823946).
#### Unsuited Applications
<!-- info: When using a model trained on this dataset in a setting where users or the public may interact with its predictions, what are some pitfalls to look out for? In particular, describe some applications of the general task featured in this dataset that its curation or properties make it less suitable for. -->
<!-- scope: microscope -->
Since the test datasets contains only 2,359 sentences that are derived from Wikipedia, they are limited to a small subset of topics present on Wikipedia.
|
false |
# Dataset Card for bc2gm_corpus
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Github](https://github.com/spyysalo/bc2gm-corpus/)
- **Repository:** [Github](https://github.com/spyysalo/bc2gm-corpus/)
- **Paper:** [NCBI](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2559986/)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
- `id`: Sentence identifier.
- `tokens`: Array of tokens composing a sentence.
- `ner_tags`: Array of tags, where `0` indicates no disease mentioned, `1` signals the first token of a disease and `2` the subsequent disease tokens.
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@mahajandiwakar](https://github.com/mahajandiwakar) for adding this dataset. |
false | # Dataset Card for NbAiLab/NPSC
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Data Fields](#data-fiels)
- [Dataset Creation](#dataset-creation)
- [Statistics](#statistics)
- [Document Types](#document-types)
- [Languages](#languages)
- [Publish Periode](#publish-periode)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** https://www.nb.no/sprakbanken/
- **Repository:** https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-58/
- **Paper:** https://www.nb.no/sprakbanken/
- **Point of Contact:** [Per Erik Solberg](mailto:per.solberg@nb.no)
The Norwegian Parliamentary Speech Corpus (NPSC) is a speech corpus made by the Norwegian Language Bank at the National Library of Norway in 2019-2021. The NPSC consists of recordings of speech from Stortinget, the Norwegian parliament, and corresponding orthographic transcriptions to Norwegian Bokmål and Norwegian Nynorsk. All transcriptions are done manually by trained linguists or philologists, and the manual transcriptions are subsequently proofread to ensure consistency and accuracy. Entire days of Parliamentary meetings are transcribed in the dataset.
This repository contains a version of the NPSC in the 🤗 Dataset Format. Note that the official release of the dataset, which can be found in [the repository of the Norwegian Language Bank](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-58/), contains more information than the version found here, including word-level metadata, metadata about the speakers, and detailed documentation.
## How to Use
```python
# Loads the 16K Bokmål corpus in streaming mode
from datasets import load_dataset
data = load_dataset("NbAiLab/NPSC", config="16K_mp3_bokmaal", streaming=True)
```
## Dataset Summary
The NPSC dataset contains JSON lines with language training data. The data loader will add audio data to this structure. Here is an example json object:
```json
{
"sentence_id": 49853,
"sentence_order": 0,
"speaker_id": 32,
"meeting_date": "20170110",
"speaker_name": "Olemic Thommessen",
"sentence_text": "Stortingets møte er lovlig satt",
"sentence_language_code": "nb-NO",
"text": "Stortingets møte er lovlig satt",
"start_time": 320246,
"end_time": 323590,
"normsentence_text": "Stortingets møte er lovlig satt",
"transsentence_text": "Stortingets møte er lovleg sett",
"translated": 1,
"audio": {"path": "audio/20170110-095504_320246_323590.wav","array": [.......]}
}
```
## Data Fields
|**Key** | **Type** | **Description** |
|:-----------|:------------|:------------|
|**sentence_id:** | Integer | Unique identifier of the sentence |
|**sentence_order** | Integer | A number indicating the order of the sentences in the meeting |
|**speaker_id** | Integer | The ID of the speaker. This can be linked to the original dataset containing thorough demographic and dialectal information about the speaker. |
|**meeting_date** | String | The date for the meeting in the format __yyyymmdd__ |
| **speaker_name** | String | Name of the speaker. All speakers were members of the Norwegian Parliament or members of the Norwegian Government at the meeting date |
| **sentence_text** | String | The sentence text. The transcribed text string of the sentence in non-normalized form. This is the text of the manual transcriptions, without any postprocessing (apart from corrections of known errors). It may contain interrupted words, non-standard words and function words with a pronunciation deviating from the written form. Detailed metadata about the words in the sentence can be found in the word-tokenized version of the corpus in the official release of the dataset. |
| **sentence_language_code** | String | The language code of the sentence. The following alternatives exists in the file: ['nb-NO'. 'nn-NO', 'en-US']|
| **text** | String | sentence text. This is a copy of "sentence_text". It is included here to make it more convenient to interleave with other datasets.|
| **start_time** | Integer | The start time of the sentence in milliseconds. This time is relative to the start of audiofile of the entire meeting, which can be accessed in the official release |
| **end_time** | Integer | End time. See comment above. |
| **normsentence_text** | String | Normalized sentence text. In this version of the transcription, numbers and dates are written in digits on standardized formats, and common abbreviations are used. These modifications to the original transcriptions are produced automatically using normalization grammars |
| **transsentence_text** | String | Translated sentence text. Whenever the original transcription is in Bokmål (nb-NO), this field contains a machine-translated version in Nynorsk (nn-NO), and vice versa |
| **translated** | Integer | A flag indicating whether a machine-translated version has been produced or not. Sentences in en-US have not been translated |
| **audio** | Array | The dataloader will encode the accociated audio files and provide them as an array containing 'path', 'sound array','sampling_rate' |
#### Initial Data Collection
The procedure for the dataset creation is described in detail in our paper.
## Statistics
| Feature | Value |
|:---------|-----------:|
| Duration, pauses included | 140,3 hours|
| Duration, pauses not included | 125,7 hours |
| Word count | 1,2 million |
| Sentence count | 64.531 |
| Language distribution | Nynorsk: 12,8%|
| | Bokmål: 87,2%|
| Gender distribution | Female: 38,3% |
| | Male: 61.7% |
## Considerations for Using the Data
This corpus contains speech data. All recordings are of members of Parliament in a public setting, and can be distributed without any restrains.
### Dataset Creators and Curators
The content of the dataset was created by the Norwegian Language Bank (Språkbanken) at the National Library of Norway. [Javier de la Rosa](mailto:versae@nb.no), [Freddy Wetjen](mailto:freddy.wetjen@nb.no), [Per Egil Kummervold](mailto:per.kummervold@nb.no), and [Andre Kaasen](mailto:andre.kasen@nb.no) all contributed in making this into a HuggingFace Dataset. Thanks to the HuggingFace team for assistance.
## License
The sound and the transcriptions are released under the [CC-ZERO-license](https://creativecommons.org/publicdomain/zero/1.0/). The curation of the HuggingFace Dataset is released under [CC-BY-SA-3-license](https://creativecommons.org/licenses/by-sa/3.0/).
### Citation Information
The following article gives detailed information about the corpus. Please refer to the article and this page if you are using this dataset:
```
@inproceedings{solberg2022norwegian,
title={The Norwegian Parliamentary Speech Corpus},
author={Solberg, Per Erik and Ortiz, Pablo},
booktitle={Proceedings of the 13th Language Resources and Evaluation Conference},
url={http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.106.pdf},
year={2022}
}
```
|
false |
# Dataset Card for "MobIE"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [https://github.com/dfki-nlp/mobie](https://github.com/dfki-nlp/mobie)
- **Repository:** [https://github.com/dfki-nlp/mobie](https://github.com/dfki-nlp/mobie)
- **Paper:** [https://aclanthology.org/2021.konvens-1.22/](https://aclanthology.org/2021.konvens-1.22/)
- **Point of Contact:** See [https://github.com/dfki-nlp/mobie](https://github.com/dfki-nlp/mobie)
- **Size of downloaded dataset files:** 7.8 MB
- **Size of the generated dataset:** 1.9 MB
- **Total amount of disk used:** 9.7 MB
### Dataset Summary
This script is for loading the MobIE dataset from https://github.com/dfki-nlp/mobie.
MobIE is a German-language dataset which is human-annotated with 20 coarse- and fine-grained entity types and entity linking information for geographically linkable entities. The dataset consists of 3,232 social media texts and traffic reports with 91K tokens, and contains 20.5K annotated entities, 13.1K of which are linked to a knowledge base. A subset of the dataset is human-annotated with seven mobility-related, n-ary relation types, while the remaining documents are annotated using a weakly-supervised labeling approach implemented with the Snorkel framework. The dataset combines annotations for NER, EL and RE, and thus can be used for joint and multi-task learning of these fundamental information extraction tasks.
This version of the dataset loader provides NER tags only. NER tags use the `BIO` tagging scheme.
For more details see https://github.com/dfki-nlp/mobie and https://aclanthology.org/2021.konvens-1.22/.
### Supported Tasks and Leaderboards
- **Tasks:** Named Entity Recognition
- **Leaderboards:**
### Languages
German
## Dataset Structure
### Data Instances
- **Size of downloaded dataset files:** 7.8 MB
- **Size of the generated dataset:** 1.9 MB
- **Total amount of disk used:** 9.7 MB
An example of 'train' looks as follows.
```json
{
'id': 'http://www.ndr.de/nachrichten/verkehr/index.html#2@2016-05-04T21:02:14.000+02:00',
'tokens': ['Vorsicht', 'bitte', 'auf', 'der', 'A28', 'Leer', 'Richtung', 'Oldenburg', 'zwischen', 'Zwischenahner', 'Meer', 'und', 'Neuenkruge', 'liegen', 'Gegenstände', '!'],
'ner_tags': [0, 0, 0, 0, 19, 13, 0, 13, 0, 11, 12, 0, 11, 0, 0, 0]
}
```
### Data Fields
The data fields are the same among all splits.
- `id`: a `string` feature.
- `tokens`: a `list` of `string` features.
- `ner_tags`: a `list` of classification labels, with possible values including `O` (0), `B-date` (1), `I-date` (2), `B-disaster-type` (3), `I-disaster-type` (4), ...
### Data Splits
| | Train | Dev | Test |
| ----- | ------ | ----- | ---- |
| MobIE | 4785 | 1082 | 1210 |
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[CC BY-SA 4.0 license](https://creativecommons.org/licenses/by-sa/4.0/)
### Citation Information
```
@inproceedings{hennig-etal-2021-mobie,
title = "{M}ob{IE}: A {G}erman Dataset for Named Entity Recognition, Entity Linking and Relation Extraction in the Mobility Domain",
author = "Hennig, Leonhard and
Truong, Phuc Tran and
Gabryszak, Aleksandra",
booktitle = "Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021)",
month = "6--9 " # sep,
year = "2021",
address = {D{\"u}sseldorf, Germany},
publisher = "KONVENS 2021 Organizers",
url = "https://aclanthology.org/2021.konvens-1.22",
pages = "223--227",
}
```
### Contributions
|
true |
# klej-polemo2-in
## Description
The PolEmo2.0 is a dataset of online consumer reviews from four domains: medicine, hotels, products, and university. It is human-annotated on a level of full reviews and individual sentences. It comprises over 8000 reviews, about 85% from the medicine and hotel domains.
We use the PolEmo2.0 dataset to form two tasks. Both use the same training dataset, i.e., reviews from medicine and hotel domains, but are evaluated on a different test set.
**In-Domain** is the first task, and we use accuracy to evaluate model performance within the in-domain context, i.e., on a test set of reviews from medicine and hotels domains.
## Tasks (input, output, and metrics)
The task is to predict the correct label of the review.
**Input** ('*text'* column): sentence
**Output** ('*target'* column): label for sentence sentiment ('zero': neutral, 'minus': negative, 'plus': positive, 'amb': ambiguous)
**Domain**: Online reviews
**Measurements**: Accuracy
**Example**:
Input: `Lekarz zalecił mi kurację alternatywną do dotychczasowej , więc jeszcze nie daję najwyższej oceny ( zobaczymy na ile okaże się skuteczna ) . Do Pana doktora nie mam zastrzeżeń : bardzo profesjonalny i kulturalny . Jedyny minus dotyczy gabinetu , który nie jest nowoczesny , co może zniechęcać pacjentki .`
Input (translated by DeepL): `The doctor recommended me an alternative treatment to the current one , so I do not yet give the highest rating ( we will see how effective it turns out to be ) . To the doctor I have no reservations : very professional and cultured . The only minus is about the office , which is not modern , which may discourage patients .`
Output: `amb` (ambiguous)
## Data splits
| Subset | Cardinality |
|:-----------|--------------:|
| train | 5783 |
| test | 722 |
| validation | 723 |
## Class distribution in train
| Class | Sentiment | train | validation | test |
|:------|:----------|------:|-----------:|------:|
| minus | positive | 0.379 | 0.375 | 0.416 |
| plus | negative | 0.271 | 0.289 | 0.273 |
| amb | ambiguous | 0.182 | 0.160 | 0.150 |
| zero | neutral | 0.168 | 0.176 | 0.162 |
## Citation
```
@inproceedings{kocon-etal-2019-multi,
title = "Multi-Level Sentiment Analysis of {P}ol{E}mo 2.0: Extended Corpus of Multi-Domain Consumer Reviews",
author = "Koco{\'n}, Jan and
Mi{\l}kowski, Piotr and
Za{\'s}ko-Zieli{\'n}ska, Monika",
booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K19-1092",
doi = "10.18653/v1/K19-1092",
pages = "980--991",
abstract = "In this article we present an extended version of PolEmo {--} a corpus of consumer reviews from 4 domains: medicine, hotels, products and school. Current version (PolEmo 2.0) contains 8,216 reviews having 57,466 sentences. Each text and sentence was manually annotated with sentiment in 2+1 scheme, which gives a total of 197,046 annotations. We obtained a high value of Positive Specific Agreement, which is 0.91 for texts and 0.88 for sentences. PolEmo 2.0 is publicly available under a Creative Commons copyright license. We explored recent deep learning approaches for the recognition of sentiment, such as Bi-directional Long Short-Term Memory (BiLSTM) and Bidirectional Encoder Representations from Transformers (BERT).",
}
```
## License
```
Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
```
## Links
[HuggingFace](https://huggingface.co/datasets/allegro/klej-polemo2-in)
[Source](https://clarin-pl.eu/dspace/handle/11321/710)
[Paper](https://aclanthology.org/K19-1092/)
## Examples
### Loading
```python
from pprint import pprint
from datasets import load_dataset
dataset = load_dataset("allegro/klej-polemo2-in")
pprint(dataset['train'][0])
# {'sentence': 'Super lekarz i człowiek przez duże C . Bardzo duże doświadczenie '
# 'i trafne diagnozy . Wielka cierpliwość do ludzi starszych . Od '
# 'lat opiekuje się moją Mamą staruszką , i twierdzę , że mamy duże '
# 'szczęście , że mamy takiego lekarza . Naprawdę nie wiem cobyśmy '
# 'zrobili , gdyby nie Pan doktor . Dzięki temu , moja mama żyje . '
# 'Każda wizyta u specjalisty jest u niego konsultowana i uważam , '
# 'że jest lepszy od każdego z nich . Mamy do Niego prawie '
# 'nieograniczone zaufanie . Można wiele dobrego o Panu doktorze '
# 'jeszcze napisać . Niestety , ma bardzo dużo pacjentów , jest '
# 'przepracowany ( z tego powodu nawet obawiam się o jego zdrowie ) '
# 'i dostęp do niego jest trudny , ale zawsze możliwy .',
# 'target': '__label__meta_plus_m'}
```
### Evaluation
```python
import random
from pprint import pprint
from datasets import load_dataset, load_metric
dataset = load_dataset("allegro/klej-polemo2-in")
dataset = dataset.class_encode_column("target")
references = dataset["test"]["target"]
# generate random predictions
predictions = [random.randrange(max(references) + 1) for _ in range(len(references))]
acc = load_metric("accuracy")
f1 = load_metric("f1")
acc_score = acc.compute(predictions=predictions, references=references)
f1_score = f1.compute(predictions=predictions, references=references, average="macro")
pprint(acc_score)
pprint(f1_score)
# {'accuracy': 0.25069252077562326}
# {'f1': 0.23760962219870274}
``` |
false |
# Dataset Card for cocktails_recipe
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Source Data](#source-data)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This dataset contains a list of cocktails and how to do them.
### Languages
The language is english.
## Dataset Structure
### Data Fields
- Title: name of the cocktail
- Glass: type of glass to use
- Garnish: garnish to use for the glass
- Recipe: how to do the cocktail
- Ingredients: ingredients required
### Data Splits
Currently, there is no splits.
## Dataset Creation
### Source Data
#### Initial Data Collection and Normalization
The dataset was created by scraping the Diffords cocktail website.
### Personal and Sensitive Information
It should not contain any personal or sensitive information.
### Contributions
Thanks to [@github-erwanlc](https://github.com/erwanlc) for adding this dataset. |
false |
# textures-color-normal-1k
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
The `textures-color-normal-1k` dataset is an image dataset of 1000+ color and normal map textures in 512x512 resolution.
The dataset was created for use in image to image tasks.
It contains a combination of CC0 procedural and photoscanned PBR materials from [ambientCG](https://ambientcg.com/).
## Dataset Structure
### Data Instances
Each data point contains a 512x512 color texture and the corresponding 512x512 normal map.
### Data Fields
* `color`: the color texture as a PIL image
* `normal`: the normal map as a PIL image
### Data Splits
| | train |
| -- | ----- |
| ambientCG | 1426 |
## Dataset Creation
### Curation Rationale
`textures-color-normal-1k` was created to provide an accesible source of data for automating 3D-asset creation workflows.
The [Dream Textures](https://github.com/carson-katri/dream-textures) add-on is one such tool providing AI automation in Blender.
By training models designed for image to image tasks, this particular use-case can be more accurately automated.
### Source Data
#### Initial Data Collection and Normalization
The data was obtained from [ambientCG](https://ambientcg.com/)'s CC0 textures. Only the color and normal maps were included in this dataset.
## Additional Information
### Dataset Curators
The dataset was created by Carson Katri, with the images being provided by [ambientCG](https://ambientcg.com/).
### Licensing Information
All of the images used in this dataset are CC0.
### Citation Information
[N/A]
### Contributions
Thanks to [@carson-katri](https://github.com/carson-katri) for adding this dataset. |
false |
# Dataset Card for Swedish NER Corpus
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [https://github.com/klintan/swedish-ner-corpus]()
- **Repository:** [https://github.com/klintan/swedish-ner-corpus]()
- **Point of contact:** [Andreas Klintberg](ankl@kth.se)
### Dataset Summary
Webbnyheter 2012 from Spraakbanken, semi-manually annotated and adapted for CoreNLP Swedish NER. Semi-manually defined in this case as: Bootstrapped from Swedish Gazetters then manually correcte/reviewed by two independent native speaking swedish annotators. No annotator agreement calculated.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Swedish
## Dataset Structure
### Data Instances
A sample dataset instance is provided below:
```json
{'id': '3',
'ner_tags': [4, 4, 0, 0, 0, 0, 0, 0, 3, 3, 0],
'tokens': ['Margaretha',
'Fahlgren',
',',
'professor',
'i',
'litteraturvetenskap',
',',
'vice-rektor',
'Uppsala',
'universitet',
'.']}
```
### Data Fields
- `id`: id of the sentence
- `token`: current token
- `ner_tag`: ner tag of the token
Full fields:
```json
{
"id":{
"feature_type":"Value"
"dtype":"string"
}
"tokens":{
"feature_type":"Sequence"
"feature":{
"feature_type":"Value"
"dtype":"string"
}
}
"ner_tags":{
"feature_type":"Sequence"
"dtype":"int32"
"feature":{
"feature_type":"ClassLabel"
"dtype":"int32"
"class_names":[
0:"0"
1:"LOC"
2:"MISC"
3:"ORG"
4:"PER"
]
}
}
}
```
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The original dataset was provided by Språkbanken which consists of news from Swedish newspapers' websites.
### Licensing Information
https://github.com/klintan/swedish-ner-corpus/blob/master/LICENSE
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false |
# Dataset Card for Dataset Name
## Dataset Description
- **Homepage:** [https://satinbenchmark.github.io](https://satinbenchmark.github.io)
- **Repository:**
- **Paper:** [SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models](https://arxiv.org/pdf/2304.11619.pdf)
- **Leaderboard:** [SATIN Leaderboard](https://satinbenchmark.github.io/leaderboard.md)
### Dataset Summary
SATIN (SATellite ImageNet) is a metadataset containing 27 constituent satellite and aerial image datasets spanning 6 distinct tasks: Land Cover, Land Use,
Hierarchical Land Use, Complex Scenes, Rare Scenes, and False Colour Scenes. The imagery is globally distributed, comprised of resolutions spanning 5 orders
of magnitude, multiple fields of view sizes, and over 250 distinct class labels.
## Dataset Structure
The SATIN benchmark is comprised of the following datasets:
#### Task 1: Land Cover
- SAT-4
- SAT-6
- NASC-TG2
#### Task 2: Land Use
- WHU-RS19
- RSSCN7
- RS_C11
- SIRI-WHU
- EuroSAT
- NWPU-RESISC45
- PatternNet
- RSD46-WHU
- GID
- CLRS
- Optimal-31
#### Task 3: Hierarchical Land Use
- Million-AID
- RSI-CB256
#### Task 4: Complex Scenes
- UC_Merced_LandUse_MultiLabel
- MLRSNet
- MultiScene
- AID_MultiLabel
#### Task 5: Rare Scenes
- Airbus-Wind-Turbines-Patches
- USTC_SmokeRS
- Canadian_Cropland
- Ships-In-Satellite-Imagery
- Satellite-Images-of-Hurricane-Damage
#### Task 6: False Colour Scenes
- Brazilian_Coffee_Scenes
- Brazilian_Cerrado-Savanna_Scenes
For ease of use and to avoid having to download the entire benchmark for each use, in this dataset repository, each of the 27 datasets is included as a separate
'config'.
### Example Usage
```python
from datasets import load_dataset
hf_dataset = load_dataset('jonathan-roberts1/SATIN', DATASET_NAME, split='train') # for DATASET_NAME use one of the configs listed above (e.g., EuroSAT)
features = hf_dataset.features
class_labels = features['label'].names # Note for the Hierarchical Land Use datasets, the label field is replaced with label1, label2, ...
random_index = 5
example = hf_dataset[random_index]
image, label = example['image'], example['label']
```
### Data Splits
For each config, there is just the single, default 'train' split.
### Source Data
More information regarding the source data can be found in our paper. Additionally, each of the constituent datasets have been uploaded to HuggingFace datasets.
They can be accessed at: huggingface.co/datasets/jonathan-roberts1/DATASET_NAME.
### Dataset Curators
This dataset was curated by Jonathan Roberts, Kai Han, and Samuel Albanie
### Licensing Information
As SATIN is comprised of existing datasets with differing licenses, there is not a single license for SATIN. All of the datasets in SATIN can be used
for research purposes; usage information of specific constituent datasets can be found in the Appendix of our paper.
### Citation Information
```
@article{roberts2023satin,
title = {SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models},
author = {Jonathan Roberts, Kai Han, and Samuel Albanie},
year = {2023},
eprint = {2304.11619},
archivePrefix= {arXiv},
primaryClass = {cs.CV}
}
``` |
false |
# Dataset Card for [DialogRE]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [DialogRE Homepage](https://dataset.org/dialogre/)
- **Repository:** [DialogRE Repository](https://github.com/nlpdata/dialogre)
- **Paper:** [Arxiv](https://arxiv.org/abs/2004.08056v1)
- **Point of Contact:** [dialogre@dataset.org](mailto:dialogre@dataset.org)
### Dataset Summary
The DialogRE dataset is the first human-annotated dialogue-based relation extraction (RE) dataset, aiming to support the prediction of relation(s) between two arguments that appear in a dialogue. DialogRE can also act as a platform for studying cross-sentence RE as most facts span multiple sentences. Specifically, the dataset annotate all occurrences of 36 possible relation types that exist between pairs of arguments in the 1,788 dialogues originating from the complete transcripts of Friends (in English).
### Supported Tasks and Leaderboards
* `other-other-relation-extraction`: The dataset can be used to train a model for Relation Extraction, which consists of the prediction of relation between two arguments that appear in a dialogue. Success on this task is typically measured by achieving a *high* [F1 Score](https://huggingface.co/metrics/f1).
### Languages
The dialogues in the dataset is in English originating from the transcripts of Friends. The associated BCP-47 code is `en`.
## Dataset Structure
### Data Instances
A typical data point consists of a dialogue between speakers as a list of sentences. This is followed by the annotations of the relations between the entities in the dialog.
An example from the DialogRE train set looks as follows:
```
{'dialog': ["Speaker 1: It's been an hour and not one of my classmates has shown up! I tell you, when I actually die some people are gonna get seriously haunted!",
'Speaker 2: There you go! Someone came!',
"Speaker 1: Ok, ok! I'm gonna go hide! Oh, this is so exciting, my first mourner!",
'Speaker 3: Hi, glad you could come.',
'Speaker 2: Please, come in.',
"Speaker 4: Hi, you're Chandler Bing, right? I'm Tom Gordon, I was in your class.",
'Speaker 2: Oh yes, yes... let me... take your coat.',
"Speaker 4: Thanks... uh... I'm so sorry about Ross, it's...",
'Speaker 2: At least he died doing what he loved... watching blimps.',
'Speaker 1: Who is he?',
'Speaker 2: Some guy, Tom Gordon.',
"Speaker 1: I don't remember him, but then again I touched so many lives.",
'Speaker 3: So, did you know Ross well?',
"Speaker 4: Oh, actually I barely knew him. Yeah, I came because I heard Chandler's news. D'you know if he's seeing anyone?",
'Speaker 3: Yes, he is. Me.',
'Speaker 4: What? You... You... Oh! Can I ask you a personal question? Ho-how do you shave your beard so close?',
"Speaker 2: Ok Tommy, that's enough mourning for you! Here we go, bye bye!!",
'Speaker 4: Hey, listen. Call me.',
'Speaker 2: Ok!'],
'relation_data': {'r': [['per:alternate_names'],
['per:alumni'],
['per:alternate_names'],
['per:alumni', 'per:positive_impression'],
['per:alternate_names'],
['unanswerable']],
'rid': [[30], [4], [30], [4, 1], [30], [37]],
't': [[''], [''], [''], ['', 'call me'], [''], ['']],
'x': ['Speaker 2',
'Speaker 2',
'Speaker 4',
'Speaker 4',
'Speaker 4',
'Speaker 1'],
'x_type': ['PER', 'PER', 'PER', 'PER', 'PER', 'PER'],
'y': ['Chandler Bing',
'Speaker 4',
'Tom Gordon',
'Speaker 2',
'Tommy',
'Tommy'],
'y_type': ['PER', 'PER', 'PER', 'PER', 'PER', 'PER']}}
```
### Data Fields
* `dialog`
* List of dialog spoken between the speakers
* List of annotations per dialog per argument
* `x` : First entity
* `y` : Second entity
* `x_type` : Type of the first entity
* `y_type`: Type of the second entity
* `r` : List of relations
* `rid`: List of relation IDs
* `t`: List of relation Trigger words
### Data Splits
The data is split into a training, validation and test set as per the original dataset split.
| | train | validation | test |
| --------------------- |-------:|------------:|------:|
| Input dialog examples | 1073 | 358 | 357 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
DialogRE dataset is intended for non-commercial research purpose only
### Citation Information
```
@inproceedings{yu2020dialogue,
title={Dialogue-Based Relation Extraction},
author={Yu, Dian and Sun, Kai and Cardie, Claire and Yu, Dong},
booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
year={2020},
url={https://arxiv.org/abs/2004.08056v1}
}
```
### Contributions
Thanks to [@vineeths96](https://github.com/vineeths96) for adding this dataset. |
true |
# Dataset Card for Hard
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Hard](https://github.com/elnagara/HARD-Arabic-Dataset)
- **Repository:** [Hard](https://github.com/elnagara/HARD-Arabic-Dataset)
- **Paper:** [Hotel Arabic-Reviews Dataset Construction for Sentiment Analysis Applications](https://link.springer.com/chapter/10.1007/978-3-319-67056-0_3)
- **Point of Contact:** [Ashraf Elnagar](ashraf@sharjah.ac.ae)
### Dataset Summary
This dataset contains 93,700 hotel reviews in Arabic language.The hotel reviews were collected from Booking.com website during June/July 2016.The reviews are expressed in Modern Standard Arabic as well as dialectal Arabic.The following table summarize some tatistics on the HARD Dataset.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is based on Arabic.
## Dataset Structure
### Data Instances
A typical data point comprises a rating from 1 to 5 for hotels.
### Data Fields
[More Information Needed]
### Data Splits
The dataset is not split.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
### Contributions
Thanks to [@zaidalyafeai](https://github.com/zaidalyafeai) for adding this dataset. |
true |
# Dataset Card for [Dataset Name]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Github](https://github.com/songys/Question_pair)
- **Repository:** [Github](https://github.com/songys/Question_pair)
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
Each row in the dataset contains two questions and a `is_duplicate` label.
- `question1`: The first question
- `question2`: The second question
- `is_duplicate`: 0 if `question1` and `question2` are semantically similar; 1 otherwise
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@jaketae](https://github.com/jaketae) for adding this dataset. |
false |
# Dataset Card for DISFL-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Disfl-QA](https://github.com/google-research-datasets/disfl-qa)
- **Paper:** [Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering](https://arxiv.org/pdf/2106.04016.pdf)
- **Point of Contact:** [disfl-qa team](disfl-qa@google.com)
### Dataset Summary
Disfl-QA is a targeted dataset for contextual disfluencies in an information seeking setting, namely question answering over Wikipedia passages. Disfl-QA builds upon the SQuAD-v2 ([Rajpurkar et al., 2018](https://www.aclweb.org/anthology/P18-2124/)) dataset, where each question in the dev set is annotated to add a contextual disfluency using the paragraph as a source of distractors.
The final dataset consists of ~12k (disfluent question, answer) pairs. Over 90\% of the disfluencies are corrections or restarts, making it a much harder test set for disfluency correction. Disfl-QA aims to fill a major gap between speech and NLP research community. The authors hope the dataset can serve as a benchmark dataset for testing robustness of models against disfluent inputs.
The expriments reveal that the state-of-the-art models are brittle when subjected to disfluent inputs from Disfl-QA. Detailed experiments and analyses can be found in the [paper](https://arxiv.org/pdf/2106.04016.pdf).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is in English only.
## Dataset Structure
### Data Instances
This example was too long and was cropped:
```
{
"answers": {
"answer_start": [94, 87, 94, 94],
"text": ["10th and 11th centuries", "in the 10th and 11th centuries", "10th and 11th centuries", "10th and 11th centuries"]
},
"context": "\"The Normans (Norman: Nourmands; French: Normands; Latin: Normanni) were the people who in the 10th and 11th centuries gave thei...",
"id": "56ddde6b9a695914005b9629",
"original question": "When were the Normans in Normandy?",
"disfluent question": "From which countries no tell me when were the Normans in Normandy?"
"title": "Normans"
}
```
### Data Fields
- `id`: a `string` feature.
- `title`: a `string` feature.
- `context`: a `string` feature.
- `original question`: Original question from SQuAD-v2 (a `string` feature)
- `disfluent question`: Disfluent question from Disfl-QA (a `string` feature)
- `answers`: a dictionary feature containing:
- `text`: a `string` feature.
- `answer_start`: a `int32` feature.
### Data Splits
Disfl-QA consists of ~12k disfluent questions with the following train/dev/test splits:
| File | Questions |
|-----|-----|
|train.json | 7182 |
|dev.json | 1000 |
|test.json | 3643 |
## Dataset Creation
### Curation Rationale
The research in NLP and speech community has been impeded by the lack of curated datasets containing such disfluencies. The datasets available today are mostly conversational in nature, and span a limited number of very specific domains (e.g., telephone conversations, court proceedings). Furthermore, only a small fraction of the utterances in these datasets contain disfluencies, with a limited and skewed distribution of disfluencies types. In the most popular dataset in the literature, the SWITCHBOARD corpus (Godfrey et al., 1992), only 5.9% of the words are disfluencies (Charniak and Johnson, 2001), of which > 50% are repetitions (Shriberg, 1996), which has been shown to be the relatively simpler form of disfluencies (Zayats et al., 2014; Jamshid Lou et al., 2018; Zayats et al., 2019). To fill this gap, the authors presented DISFL-QA, the first dataset containing contextual disfluencies in an information seeking setting, namely question answering over Wikipedia passages.
### Source Data
#### Initial Data Collection and Normalization
DISFL-QA is constructed by asking human raters to insert disfluencies in questions from SQUAD-v2, a popular question answering dataset, using the passage and remaining questions as context. These contextual disfluencies lend naturalness to DISFL-QA, and challenge models relying on shallow matching between question and context to predict an answer.
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
Each question associated with the paragraph is sent for a human annotation task to add a contextual disfluency using the paragraph as a source of distractors. Finally, to ensure the quality of the dataset, a subsequent round of human evaluation with an option to re-annotate is conducted.
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
Disfl-QA dataset is licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).
### Citation Information
```
@inproceedings{gupta-etal-2021-disflqa,
title = "{Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering}",
author = "Gupta, Aditya and Xu, Jiacheng and Upadhyay, Shyam and Yang, Diyi and Faruqui, Manaal",
booktitle = "Findings of ACL",
year = "2021"
}
```
### Contributions
Thanks to [@bhavitvyamalik](https://github.com/bhavitvyamalik) for adding this dataset. |
false |
# Dataset Card for Visual Genome
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Dataset Preprocessing](#dataset-preprocessing)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://visualgenome.org/
- **Repository:**
- **Paper:** https://visualgenome.org/static/paper/Visual_Genome.pdf
- **Leaderboard:**
- **Point of Contact:** ranjaykrishna [at] gmail [dot] com
### Dataset Summary
Visual Genome is a dataset, a knowledge base, an ongoing effort to connect structured image concepts to language.
From the paper:
> Despite progress in perceptual tasks such as
image classification, computers still perform poorly on
cognitive tasks such as image description and question
answering. Cognition is core to tasks that involve not
just recognizing, but reasoning about our visual world.
However, models used to tackle the rich content in images for cognitive tasks are still being trained using the
same datasets designed for perceptual tasks. To achieve
success at cognitive tasks, models need to understand
the interactions and relationships between objects in an
image. When asked “What vehicle is the person riding?”,
computers will need to identify the objects in an image
as well as the relationships riding(man, carriage) and
pulling(horse, carriage) to answer correctly that “the
person is riding a horse-drawn carriage.”
Visual Genome has:
- 108,077 image
- 5.4 Million Region Descriptions
- 1.7 Million Visual Question Answers
- 3.8 Million Object Instances
- 2.8 Million Attributes
- 2.3 Million Relationships
From the paper:
> Our dataset contains over 108K images where each
image has an average of 35 objects, 26 attributes, and 21
pairwise relationships between objects. We canonicalize
the objects, attributes, relationships, and noun phrases
in region descriptions and questions answer pairs to
WordNet synsets.
### Dataset Preprocessing
### Supported Tasks and Leaderboards
### Languages
All of annotations use English as primary language.
## Dataset Structure
### Data Instances
When loading a specific configuration, users has to append a version dependent suffix:
```python
from datasets import load_dataset
load_dataset("visual_genome", "region_description_v1.2.0")
```
#### region_descriptions
An example of looks as follows.
```
{
"image": <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=800x600 at 0x7F2F60698610>,
"image_id": 1,
"url": "https://cs.stanford.edu/people/rak248/VG_100K_2/1.jpg",
"width": 800,
"height": 600,
"coco_id": null,
"flickr_id": null,
"regions": [
{
"region_id": 1382,
"image_id": 1,
"phrase": "the clock is green in colour",
"x": 421,
"y": 57,
"width": 82,
"height": 139
},
...
]
}
```
#### objects
An example of looks as follows.
```
{
"image": <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=800x600 at 0x7F2F60698610>,
"image_id": 1,
"url": "https://cs.stanford.edu/people/rak248/VG_100K_2/1.jpg",
"width": 800,
"height": 600,
"coco_id": null,
"flickr_id": null,
"objects": [
{
"object_id": 1058498,
"x": 421,
"y": 91,
"w": 79,
"h": 339,
"names": [
"clock"
],
"synsets": [
"clock.n.01"
]
},
...
]
}
```
#### attributes
An example of looks as follows.
```
{
"image": <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=800x600 at 0x7F2F60698610>,
"image_id": 1,
"url": "https://cs.stanford.edu/people/rak248/VG_100K_2/1.jpg",
"width": 800,
"height": 600,
"coco_id": null,
"flickr_id": null,
"attributes": [
{
"object_id": 1058498,
"x": 421,
"y": 91,
"w": 79,
"h": 339,
"names": [
"clock"
],
"synsets": [
"clock.n.01"
],
"attributes": [
"green",
"tall"
]
},
...
}
]
```
#### relationships
An example of looks as follows.
```
{
"image": <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=800x600 at 0x7F2F60698610>,
"image_id": 1,
"url": "https://cs.stanford.edu/people/rak248/VG_100K_2/1.jpg",
"width": 800,
"height": 600,
"coco_id": null,
"flickr_id": null,
"relationships": [
{
"relationship_id": 15927,
"predicate": "ON",
"synsets": "['along.r.01']",
"subject": {
"object_id": 5045,
"x": 119,
"y": 338,
"w": 274,
"h": 192,
"names": [
"shade"
],
"synsets": [
"shade.n.01"
]
},
"object": {
"object_id": 5046,
"x": 77,
"y": 328,
"w": 714,
"h": 262,
"names": [
"street"
],
"synsets": [
"street.n.01"
]
}
}
...
}
]
```
#### question_answers
An example of looks as follows.
```
{
"image": <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=800x600 at 0x7F2F60698610>,
"image_id": 1,
"url": "https://cs.stanford.edu/people/rak248/VG_100K_2/1.jpg",
"width": 800,
"height": 600,
"coco_id": null,
"flickr_id": null,
"qas": [
{
"qa_id": 986768,
"image_id": 1,
"question": "What color is the clock?",
"answer": "Green.",
"a_objects": [],
"q_objects": []
},
...
}
]
```
### Data Fields
When loading a specific configuration, users has to append a version dependent suffix:
```python
from datasets import load_dataset
load_dataset("visual_genome", "region_description_v1.2.0")
```
#### region_descriptions
- `image`: A `PIL.Image.Image` object containing the image. Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `"image"` column, *i.e.* `dataset[0]["image"]` should **always** be preferred over `dataset["image"][0]`
- `image_id`: Unique numeric ID of the image.
- `url`: URL of source image.
- `width`: Image width.
- `height`: Image height.
- `coco_id`: Id mapping to MSCOCO indexing.
- `flickr_id`: Id mapping to Flicker indexing.
- `regions`: Holds a list of `Region` dataclasses:
- `region_id`: Unique numeric ID of the region.
- `image_id`: Unique numeric ID of the image.
- `x`: x coordinate of bounding box's top left corner.
- `y`: y coordinate of bounding box's top left corner.
- `width`: Bounding box width.
- `height`: Bounding box height.
#### objects
- `image`: A `PIL.Image.Image` object containing the image. Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `"image"` column, *i.e.* `dataset[0]["image"]` should **always** be preferred over `dataset["image"][0]`
- `image_id`: Unique numeric ID of the image.
- `url`: URL of source image.
- `width`: Image width.
- `height`: Image height.
- `coco_id`: Id mapping to MSCOCO indexing.
- `flickr_id`: Id mapping to Flicker indexing.
- `objects`: Holds a list of `Object` dataclasses:
- `object_id`: Unique numeric ID of the object.
- `x`: x coordinate of bounding box's top left corner.
- `y`: y coordinate of bounding box's top left corner.
- `w`: Bounding box width.
- `h`: Bounding box height.
- `names`: List of names associated with the object. This field can hold multiple values in the sense the multiple names are considered as acceptable. For example: ['monitor', 'computer'] at https://cs.stanford.edu/people/rak248/VG_100K/3.jpg
- `synsets`: List of `WordNet synsets`.
#### attributes
- `image`: A `PIL.Image.Image` object containing the image. Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `"image"` column, *i.e.* `dataset[0]["image"]` should **always** be preferred over `dataset["image"][0]`
- `image_id`: Unique numeric ID of the image.
- `url`: URL of source image.
- `width`: Image width.
- `height`: Image height.
- `coco_id`: Id mapping to MSCOCO indexing.
- `flickr_id`: Id mapping to Flicker indexing.
- `attributes`: Holds a list of `Object` dataclasses:
- `object_id`: Unique numeric ID of the region.
- `x`: x coordinate of bounding box's top left corner.
- `y`: y coordinate of bounding box's top left corner.
- `w`: Bounding box width.
- `h`: Bounding box height.
- `names`: List of names associated with the object. This field can hold multiple values in the sense the multiple names are considered as acceptable. For example: ['monitor', 'computer'] at https://cs.stanford.edu/people/rak248/VG_100K/3.jpg
- `synsets`: List of `WordNet synsets`.
- `attributes`: List of attributes associated with the object.
#### relationships
- `image`: A `PIL.Image.Image` object containing the image. Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `"image"` column, *i.e.* `dataset[0]["image"]` should **always** be preferred over `dataset["image"][0]`
- `image_id`: Unique numeric ID of the image.
- `url`: URL of source image.
- `width`: Image width.
- `height`: Image height.
- `coco_id`: Id mapping to MSCOCO indexing.
- `flickr_id`: Id mapping to Flicker indexing.
- `relationships`: Holds a list of `Relationship` dataclasses:
- `relationship_id`: Unique numeric ID of the object.
- `predicate`: Predicate defining relationship between a subject and an object.
- `synsets`: List of `WordNet synsets`.
- `subject`: Object dataclass. See subsection on `objects`.
- `object`: Object dataclass. See subsection on `objects`.
#### question_answers
- `image`: A `PIL.Image.Image` object containing the image. Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `"image"` column, *i.e.* `dataset[0]["image"]` should **always** be preferred over `dataset["image"][0]`
- `image_id`: Unique numeric ID of the image.
- `url`: URL of source image.
- `width`: Image width.
- `height`: Image height.
- `coco_id`: Id mapping to MSCOCO indexing.
- `flickr_id`: Id mapping to Flicker indexing.
- `qas`: Holds a list of `Question-Answering` dataclasses:
- `qa_id`: Unique numeric ID of the question-answer pair.
- `image_id`: Unique numeric ID of the image.
- `question`: Question.
- `answer`: Answer.
- `q_objects`: List of object dataclass associated with `question` field. See subsection on `objects`.
- `a_objects`: List of object dataclass associated with `answer` field. See subsection on `objects`.
### Data Splits
All the data is contained in training set.
## Dataset Creation
### Curation Rationale
### Source Data
#### Initial Data Collection and Normalization
#### Who are the source language producers?
### Annotations
#### Annotation process
#### Who are the annotators?
From the paper:
> We used Amazon Mechanical Turk (AMT) as our primary source of annotations. Overall, a total of over
33, 000 unique workers contributed to the dataset. The
dataset was collected over the course of 6 months after
15 months of experimentation and iteration on the data
representation. Approximately 800, 000 Human Intelligence Tasks (HITs) were launched on AMT, where
each HIT involved creating descriptions, questions and
answers, or region graphs. Each HIT was designed such
that workers manage to earn anywhere between $6-$8
per hour if they work continuously, in line with ethical
research standards on Mechanical Turk (Salehi et al.,
2015). Visual Genome HITs achieved a 94.1% retention
rate, meaning that 94.1% of workers who completed one
of our tasks went ahead to do more. [...] 93.02% of workers contributed from the United States.
The majority of our workers were
between the ages of 25 and 34 years old. Our youngest
contributor was 18 years and the oldest was 68 years
old. We also had a near-balanced split of 54.15% male
and 45.85% female workers.
### Personal and Sensitive Information
## Considerations for Using the Data
### Social Impact of Dataset
### Discussion of Biases
### Other Known Limitations
## Additional Information
### Dataset Curators
### Licensing Information
Visual Genome by Ranjay Krishna is licensed under a Creative Commons Attribution 4.0 International License.
### Citation Information
```bibtex
@inproceedings{krishnavisualgenome,
title={Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations},
author={Krishna, Ranjay and Zhu, Yuke and Groth, Oliver and Johnson, Justin and Hata, Kenji and Kravitz, Joshua and Chen, Stephanie and Kalantidis, Yannis and Li, Li-Jia and Shamma, David A and Bernstein, Michael and Fei-Fei, Li},
year = {2016},
url = {https://arxiv.org/abs/1602.07332},
}
```
### Contributions
Due to limitation of the dummy_data creation, we provide a `fix_generated_dummy_data.py` script that fix the dataset in-place.
Thanks to [@thomasw21](https://github.com/thomasw21) for adding this dataset. |
true |
# Dataset Card for Roman Urdu Dataset
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Repository:** [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/datasets/Roman+Urdu+Data+Set)
- **Point of Contact:** [Zareen Sharf](mailto:zareensharf76@gmail.com)
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Urdu
## Dataset Structure
[More Information Needed]
### Data Instances
```
Wah je wah,Positive,
```
### Data Fields
Each row consists of a short Urdu text, followed by a sentiment label. The labels are one of `Positive`, `Negative`, and `Neutral`. Note that the original source file is a comma-separated values file.
* `sentence`: A short Urdu text
* `label`: One of `Positive`, `Negative`, and `Neutral`, indicating the polarity of the sentiment expressed in the sentence
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```
@InProceedings{Sharf:2018,
title = "Performing Natural Language Processing on Roman Urdu Datasets",
authors = "Zareen Sharf and Saif Ur Rahman",
booktitle = "International Journal of Computer Science and Network Security",
volume = "18",
number = "1",
pages = "141-148",
year = "2018"
}
@misc{Dua:2019,
author = "Dua, Dheeru and Graff, Casey",
year = "2017",
title = "{UCI} Machine Learning Repository",
url = "http://archive.ics.uci.edu/ml",
institution = "University of California, Irvine, School of Information and Computer Sciences"
}
```
### Contributions
Thanks to [@jaketae](https://github.com/jaketae) for adding this dataset. |
false |
# Dataset Card for GEM/viggo
## Dataset Description
- **Homepage:** https://nlds.soe.ucsc.edu/viggo
- **Repository:** [Needs More Information]
- **Paper:** https://aclanthology.org/W19-8623/
- **Leaderboard:** N/A
- **Point of Contact:** Juraj Juraska
### Link to Main Data Card
You can find the main data card on the [GEM Website](https://gem-benchmark.com/data_cards/viggo).
### Dataset Summary
ViGGO is an English data-to-text generation dataset in the video game domain, with target responses being more conversational than information-seeking, yet constrained to the information presented in a meaning representation. The dataset is relatively small with about 5,000 datasets but very clean, and can thus serve for evaluating transfer learning, low-resource, or few-shot capabilities of neural models.
You can load the dataset via:
```
import datasets
data = datasets.load_dataset('GEM/viggo')
```
The data loader can be found [here](https://huggingface.co/datasets/GEM/viggo).
#### website
[Wesbite](https://nlds.soe.ucsc.edu/viggo)
#### paper
[ACL Anthology](https://aclanthology.org/W19-8623/)
#### authors
Juraj Juraska, Kevin K. Bowden, Marilyn Walker
## Dataset Overview
### Where to find the Data and its Documentation
#### Webpage
<!-- info: What is the webpage for the dataset (if it exists)? -->
<!-- scope: telescope -->
[Wesbite](https://nlds.soe.ucsc.edu/viggo)
#### Paper
<!-- info: What is the link to the paper describing the dataset (open access preferred)? -->
<!-- scope: telescope -->
[ACL Anthology](https://aclanthology.org/W19-8623/)
#### BibTex
<!-- info: Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex. -->
<!-- scope: microscope -->
```
@inproceedings{juraska-etal-2019-viggo,
title = "{V}i{GGO}: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation",
author = "Juraska, Juraj and
Bowden, Kevin and
Walker, Marilyn",
booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
month = oct # "{--}" # nov,
year = "2019",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-8623",
doi = "10.18653/v1/W19-8623",
pages = "164--172",
}
```
#### Contact Name
<!-- quick -->
<!-- info: If known, provide the name of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
Juraj Juraska
#### Contact Email
<!-- info: If known, provide the email of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
jjuraska@ucsc.edu
#### Has a Leaderboard?
<!-- info: Does the dataset have an active leaderboard? -->
<!-- scope: telescope -->
no
### Languages and Intended Use
#### Multilingual?
<!-- quick -->
<!-- info: Is the dataset multilingual? -->
<!-- scope: telescope -->
no
#### Covered Languages
<!-- quick -->
<!-- info: What languages/dialects are covered in the dataset? -->
<!-- scope: telescope -->
`English`
#### License
<!-- quick -->
<!-- info: What is the license of the dataset? -->
<!-- scope: telescope -->
cc-by-sa-4.0: Creative Commons Attribution Share Alike 4.0 International
#### Intended Use
<!-- info: What is the intended use of the dataset? -->
<!-- scope: microscope -->
ViGGO was designed for the task of data-to-text generation in chatbots (as opposed to task-oriented dialogue systems), with target responses being more conversational than information-seeking, yet constrained to the information presented in a meaning representation. The dataset, being relatively small and clean, can also serve for demonstrating transfer learning capabilities of neural models.
#### Primary Task
<!-- info: What primary task does the dataset support? -->
<!-- scope: telescope -->
Data-to-Text
### Credit
#### Curation Organization Type(s)
<!-- info: In what kind of organization did the dataset curation happen? -->
<!-- scope: telescope -->
`academic`
#### Curation Organization(s)
<!-- info: Name the organization(s). -->
<!-- scope: periscope -->
University of California, Santa Cruz
#### Dataset Creators
<!-- info: Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s). -->
<!-- scope: microscope -->
Juraj Juraska, Kevin K. Bowden, Marilyn Walker
#### Who added the Dataset to GEM?
<!-- info: Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM. -->
<!-- scope: microscope -->
Juraj Juraska
### Dataset Structure
#### Data Fields
<!-- info: List and describe the fields present in the dataset. -->
<!-- scope: telescope -->
Each example in the dataset has the following two fields:
- `mr`: A meaning representation (MR) that, in a structured format, provides the information to convey, as well as the desired dialogue act (DA) type.
- `ref`: A reference output, i.e., a corresponding utterance realizing all the information in the MR.
Each MR is a flattened dictionary of attribute-and-value pairs, "wrapped" in the dialogue act type indication. This format was chosen primarily for its compactness, but also to allow for easy concatenation of multiple DAs (each with potentially different attributes) in a single MR.
Following is the list of all possible attributes (which are also refered to as "slots") in ViGGO along with their types/possible values:
- `name`: The name of a video game (e.g., Rise of the Tomb Raider).
- `release_year`: The year a video game was released in (e.g., 2015).
- `exp_release_date`: For a not-yet-released game, the date when it is expected to be released (e.g., February 22, 2019). *Note: This slot cannot appear together with `release_year` in the same dialogue act.*
- `developer`: The name of the studio/person that created the game (e.g., Crystal Dynamics).
- `genres`: A list of one or more genre labels from a set of possible values (e.g., action-adventure, shooter).
- `player_perspective`: A list of one or more perspectives from which the game is/can be played (possible values: first person, third person, side view, bird view).
- `platforms`: A list of one or more gaming platforms the game was officially released for (possible values: PC, PlayStation, Xbox, Nintendo, Nintendo Switch).
- `esrb`: A game's content rating as determined by the ESRB (possible values: E (for Everyone), E 10+ (for Everyone 10 and Older), T (for Teen), M (for Mature)).
- `rating`: Depending on the dialogue act this slot is used with, it is a categorical representation of either the game's average rating or the game's liking (possible values: excellent, good, average, poor).
- `has_multiplayer`: Indicates whether a game supports multiplayer or can only be played in single-player mode (possible values: yes, no).
- `available_on_steam`: Indicates whether a game can be purchased through the Steam digital distribution service (possible values: yes, no).
- `has_linux_release`: Indicates whether a game is supported on Linux operating systems (possible values: yes, no).
- `has_mac_release`: Indicates whether a game is supported on macOS (possible values: yes, no).
- `specifier`: A game specifier used by the `request` DA, typically an adjective (e.g., addictive, easiest, overrated, visually impressive).
Each MR in the dataset has 3 distinct reference utterances, which are represented as 3 separate examples with the same MR.
#### Reason for Structure
<!-- info: How was the dataset structure determined? -->
<!-- scope: microscope -->
The dataset structure mostly follows the format of the popular E2E dataset, however, with added dialogue act type indications, new list-type attributes introduced, and unified naming convention for multi-word attribute names.
#### Example Instance
<!-- info: Provide a JSON formatted example of a typical instance in the dataset. -->
<!-- scope: periscope -->
```
{
"mr": "give_opinion(name[SpellForce 3], rating[poor], genres[real-time strategy, role-playing], player_perspective[bird view])",
"ref": "I think that SpellForce 3 is one of the worst games I've ever played. Trying to combine the real-time strategy and role-playing genres just doesn't work, and the bird view perspective makes it near impossible to play."
}
```
#### Data Splits
<!-- info: Describe and name the splits in the dataset if there are more than one. -->
<!-- scope: periscope -->
ViGGO is split into 3 partitions, with no MRs in common between the training set and either of the validation and the test set (and that *after* delexicalizing the `name` and `developer` slots). The ratio of examples in the partitions is approximately 7.5 : 1 : 1.5, with their exact sizes listed below:
- **Train:** 5,103 (1,675 unique MRs)
- **Validation:** 714 (238 unique MRs)
- **Test:** 1,083 (359 unique MRs)
- **TOTAL:** 6,900 (2,253 unique MRs)
*Note: The reason why the number of unique MRs is not exactly one third of all examples is that for each `request_attribute` DA (which only has one slot, and that without a value) 12 reference utterances were collected instead of 3.*
#### Splitting Criteria
<!-- info: Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here. -->
<!-- scope: microscope -->
A similar MR length and slot distribution was preserved across the partitions. The distribution of DA types, on the other hand, is skewed slightly toward fewer `inform` DA instances (the most prevalent DA type) and a higher proportion of the less prevalent DAs in the validation and the test set.
####
<!-- info: What does an outlier of the dataset in terms of length/perplexity/embedding look like? -->
<!-- scope: microscope -->
```
{
"mr": "request_attribute(player_perspective[])",
"ref": "Is there a certain player perspective that you prefer over others in games you play?"
},
{
"mr": "inform(name[FIFA 12], esrb[E (for Everyone)], genres[simulation, sport], player_perspective[bird view, side view], platforms[PlayStation, Xbox, Nintendo, PC], available_on_steam[no])",
"ref": "Fifa 12 is a decent sports simulator. It's pretty cool how the game swaps from the bird's eye perspective down to a side view while you're playing. You can get the game for PlayStation, Xbox, Nintendo consoles, and PC, but unfortunately it's not on Steam. Of course, as a sports game there's not much objectionable content so it's rated E."
},
{
"mr": "inform(name[Super Bomberman], release_year[1993], genres[action, strategy], has_multiplayer[no], platforms[Nintendo, PC], available_on_steam[no], has_linux_release[no], has_mac_release[no])",
"ref": "Super Bomberman is one of my favorite Nintendo games, also available on PC, though not through Steam. It came out all the way back in 1993, and you can't get it for any modern consoles, unfortunately, so no online multiplayer, or of course Linux or Mac releases either. That said, it's still one of the most addicting action-strategy games out there."
}
```
## Dataset in GEM
### Rationale for Inclusion in GEM
#### Why is the Dataset in GEM?
<!-- info: What does this dataset contribute toward better generation evaluation and why is it part of GEM? -->
<!-- scope: microscope -->
ViGGO is a fairly small dataset but includes a greater variety of utterance types than most other datasets for NLG from structured meaning representations. This makes it more interesting from the perspective of model evaluation, since models have to learn to differentiate between various dialogue act types that share the same slots.
#### Similar Datasets
<!-- info: Do other datasets for the high level task exist? -->
<!-- scope: telescope -->
yes
#### Unique Language Coverage
<!-- info: Does this dataset cover other languages than other datasets for the same task? -->
<!-- scope: periscope -->
no
#### Difference from other GEM datasets
<!-- info: What else sets this dataset apart from other similar datasets in GEM? -->
<!-- scope: microscope -->
ViGGO's language is more casual and conversational -- as opposed to information-seeking -- which differentiates it from the majority of popular datasets for the same type of data-to-text task. Moreover, the video game domain is a rather uncommon one in the NLG community, despite being very well-suited for data-to-text generation, considering it offers entities with many attributes to talk about, which can be described in a structured format.
### GEM-Specific Curation
#### Modificatied for GEM?
<!-- info: Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data? -->
<!-- scope: telescope -->
no
#### Additional Splits?
<!-- info: Does GEM provide additional splits to the dataset? -->
<!-- scope: telescope -->
no
### Getting Started with the Task
#### Pointers to Resources
<!-- info: Getting started with in-depth research on the task. Add relevant pointers to resources that researchers can consult when they want to get started digging deeper into the task. -->
<!-- scope: microscope -->
- [E2E NLG Challenge](http://www.macs.hw.ac.uk/InteractionLab/E2E/)
#### Technical Terms
<!-- info: Technical terms used in this card and the dataset and their definitions -->
<!-- scope: microscope -->
- MR = meaning representation
- DA = dialogue act
## Previous Results
### Previous Results
#### Metrics
<!-- info: What metrics are typically used for this task? -->
<!-- scope: periscope -->
`BLEU`, `METEOR`, `ROUGE`, `BERT-Score`, `BLEURT`, `Other: Other Metrics`
#### Other Metrics
<!-- info: Definitions of other metrics -->
<!-- scope: periscope -->
SER (slot error rate): Indicates the proportion of missing/incorrect/duplicate/hallucinated slot mentions in the utterances across a test set. The closer to zero a model scores in this metric, the more semantically accurate its outputs are. This metric is typically calculated either manually on a small sample of generated outputs, or heuristically using domain-specific regex rules and gazetteers.
#### Previous results available?
<!-- info: Are previous results available? -->
<!-- scope: telescope -->
yes
#### Relevant Previous Results
<!-- info: What are the most relevant previous results for this task/dataset? -->
<!-- scope: microscope -->
- [Juraska et al., 2019. ViGGO: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation.](https://aclanthology.org/W19-8623/)
- [Harkous et al., 2020. Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity.](https://aclanthology.org/2020.coling-main.218/)
- [Kedzie and McKeown, 2020. Controllable Meaning Representation to Text Generation: Linearization and Data Augmentation Strategies.](https://aclanthology.org/2020.emnlp-main.419/)
- [Juraska and Walker, 2021. Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG.](https://aclanthology.org/2021.inlg-1.45/)
## Dataset Curation
### Original Curation
#### Original Curation Rationale
<!-- info: Original curation rationale -->
<!-- scope: telescope -->
The primary motivation behind ViGGO was to create a data-to-text corpus in a new but conversational domain, and intended for use in open-domain chatbots rather than task-oriented dialogue systems. To this end, the dataset contains utterances of 9 generalizable and conversational dialogue act types, revolving around various aspects of video games. The idea is that similar, relatively small datasets could fairly easily be collected for other conversational domains -- especially other entertainment domains (such as music or books), but perhaps also topics like animals or food -- to support an open-domain conversational agent with controllable neural NLG.
Another desired quality of the ViGGO dataset was cleanliness (no typos and grammatical errors) and semantic accuracy, which has often not been the case with other crowdsourced data-to-text corpora. In general, for the data-to-text generation task, there is arguably no need to put the burden on the generation model to figure out the noise, since the noise would not be expected to be there in a real-world system whose dialogue manager that creates the input for the NLG module is usually configurable and tightly controlled.
#### Communicative Goal
<!-- info: What was the communicative goal? -->
<!-- scope: periscope -->
Produce a response from a structured meaning representation in the context of a conversation about video games. It can be a brief opinion or a description of a game, as well as a request for attribute (e.g., genre, player perspective, or platform) preference/confirmation or an inquiry about liking a particular type of games.
#### Sourced from Different Sources
<!-- info: Is the dataset aggregated from different data sources? -->
<!-- scope: telescope -->
no
### Language Data
#### How was Language Data Obtained?
<!-- info: How was the language data obtained? -->
<!-- scope: telescope -->
`Crowdsourced`
#### Where was it crowdsourced?
<!-- info: If crowdsourced, where from? -->
<!-- scope: periscope -->
`Amazon Mechanical Turk`
#### Language Producers
<!-- info: What further information do we have on the language producers? -->
<!-- scope: microscope -->
The paid crowdworkers who produced the reference utterances were from English-speaking countries, and they had at least 1,000 HITs approved and a HIT approval rate of 98% or more. Furthermore, in the instructions, crowdworkers were discouraged from taking on the task unless they considered themselves a gamer.
#### Topics Covered
<!-- info: Does the language in the dataset focus on specific topics? How would you describe them? -->
<!-- scope: periscope -->
The dataset focuses on video games and their various aspects, and hence the language of the utterances may contain video game-specific jargon.
#### Data Validation
<!-- info: Was the text validated by a different worker or a data curator? -->
<!-- scope: telescope -->
validated by data curator
#### Data Preprocessing
<!-- info: How was the text data pre-processed? (Enter N/A if the text was not pre-processed) -->
<!-- scope: microscope -->
First, regular expressions were used to enforce several standardization policies regarding special characters, punctuation, and the correction of undesired abbreviations/misspellings of standard domain-specific terms (e.g., terms like "Play station" or "PS4" would be changed to the uniform "PlayStation"). At the same time, hyphens were removed or enforced uniformly in certain terms, for example, "single-player". Although phrases such as "first person" should correctly have a hyphen when used as adjective, the crowdworkers used this rule very inconsistently. In order to avoid model outputs being penalized during the evaluation by the arbitrary choice of a hyphen presence or absence in the reference utterances, the hyphen was removed in all such phrases regardless of the noun vs. adjective use.
Second, an extensive set of heuristics was developed to identify slot-related errors. This process revealed the vast majority of missing or incorrect slot mentions, which were subsequently fixed according to the corresponding MRs. This eventually led to the development of a robust, cross-domain, heuristic slot aligner that can be used for automatic slot error rate evaluation. For details, see the appendix in [Juraska and Walker, 2021](https://aclanthology.org/2021.inlg-1.45/).
Crowdworkers would sometimes also inject a piece of information which was not present in the MR, some of which is not even represented by any of the slots, e.g., plot or main characters. This unsolicited information was removed from the utterances so as to avoid confusing the neural model. Finally, any remaining typos and grammatical errors were resolved.
#### Was Data Filtered?
<!-- info: Were text instances selected or filtered? -->
<!-- scope: telescope -->
manually
#### Filter Criteria
<!-- info: What were the selection criteria? -->
<!-- scope: microscope -->
Compliance with the indicated dialogue act type, semantic accuracy (i.e., all information in the corresponding MR mentioned and that correctly), and minimal extraneous information (e.g., personal experience/opinion). Whenever it was within a reasonable amount of effort, the utterances were manually fixed instead of being discarded/crowdsourced anew.
### Structured Annotations
#### Additional Annotations?
<!-- quick -->
<!-- info: Does the dataset have additional annotations for each instance? -->
<!-- scope: telescope -->
none
#### Annotation Service?
<!-- info: Was an annotation service used? -->
<!-- scope: telescope -->
no
### Consent
#### Any Consent Policy?
<!-- info: Was there a consent policy involved when gathering the data? -->
<!-- scope: telescope -->
no
### Private Identifying Information (PII)
#### Contains PII?
<!-- quick -->
<!-- info: Does the source language data likely contain Personal Identifying Information about the data creators or subjects? -->
<!-- scope: telescope -->
no PII
#### Justification for no PII
<!-- info: Provide a justification for selecting `no PII` above. -->
<!-- scope: periscope -->
Crowdworkers were instructed to only express the information in the provided meaning representation, which never prompted them to mention anything about themselves. Occasionally, they would still include a bit of personal experience (e.g., "I used to like the game as a kid.") or opinion, but these would be too general to be considered PII.
### Maintenance
#### Any Maintenance Plan?
<!-- info: Does the original dataset have a maintenance plan? -->
<!-- scope: telescope -->
no
## Broader Social Context
### Previous Work on the Social Impact of the Dataset
#### Usage of Models based on the Data
<!-- info: Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems? -->
<!-- scope: telescope -->
no
### Impact on Under-Served Communities
#### Addresses needs of underserved Communities?
<!-- info: Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models). -->
<!-- scope: telescope -->
no
### Discussion of Biases
#### Any Documented Social Biases?
<!-- info: Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group. -->
<!-- scope: telescope -->
no
## Considerations for Using the Data
### PII Risks and Liability
### Licenses
### Known Technical Limitations
#### Technical Limitations
<!-- info: Describe any known technical limitations, such as spurrious correlations, train/test overlap, annotation biases, or mis-annotations, and cite the works that first identified these limitations when possible. -->
<!-- scope: microscope -->
The dataset is limited to a single domain: video games. One caveat of using a language generator trained on this dataset in a dialogue system as-is is that multiple subsequent turns discussing the same video game would be repeating its full name. ViGGO was designed for generation without context, and therefore it is up to the dialogue manager to ensure that pronouns are substituted for the names whenever it would sound more natural in a dialogue. Alternately, the dataset can easily be augmented with automatically constructed samples which omit the `name` slot in the MR and replace the name with a pronoun in the reference utterance.
|
false |
# Dataset Card for SmartData
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.dfki.de/web/forschung/projekte-publikationen/publikationen-uebersicht/publikation/9427/
- **Repository:** https://github.com/DFKI-NLP/smartdata-corpus
- **Paper:** https://www.dfki.de/fileadmin/user_upload/import/9427_lrec_smartdata_corpus.pdf
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
DFKI SmartData Corpus is a dataset of 2598 German-language documents
which has been annotated with fine-grained geo-entities, such as streets,
stops and routes, as well as standard named entity types. It has also
been annotated with a set of 15 traffic- and industry-related n-ary
relations and events, such as Accidents, Traffic jams, Acquisitions,
and Strikes. The corpus consists of newswire texts, Twitter messages,
and traffic reports from radio stations, police and railway companies.
It allows for training and evaluating both named entity recognition
algorithms that aim for fine-grained typing of geo-entities, as well
as n-ary relation extraction systems.
### Supported Tasks and Leaderboards
NER
### Languages
German
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
- id: an identifier for the article the text came from
- tokens: a list of string tokens for the text of the article
- ner_tags: a corresponding list of NER tags in the BIO format
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
CC-BY 4.0
### Citation Information
```
@InProceedings{SCHIERSCH18.85,
author = {Martin Schiersch and Veselina Mironova and Maximilian Schmitt and Philippe Thomas and Aleksandra Gabryszak and Leonhard Hennig},
title = "{A German Corpus for Fine-Grained Named Entity Recognition and Relation Extraction of Traffic and Industry Events}",
booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
year = {2018},
month = {May 7-12, 2018},
address = {Miyazaki, Japan},
editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
publisher = {European Language Resources Association (ELRA)},
isbn = {979-10-95546-00-9},
language = {english}
}
```
### Contributions
Thanks to [@aseifert](https://github.com/aseifert) for adding this dataset. |
false |
# Dataset Card for "bbaw_egyptian"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [https://edoc.bbaw.de/frontdoor/index/index/docId/2919](https://edoc.bbaw.de/frontdoor/index/index/docId/2919)
- **Repository:** [Github](https://phiwi.github.io/all.json)
- **Paper:** [Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyph](https://zenodo.org/record/3524924)
- **Point of Contact:** [Philipp Wiesenbach](https://www.cl.uni-heidelberg.de/~wiesenbach/index.html)
- **Size of downloaded dataset files:** 35.65 MB
### Dataset Summary
This dataset comprises parallel sentences of hieroglyphic encodings, transcription and translation as used in the paper [Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyph](https://zenodo.org/record/3524924). The data triples are extracted from the [digital corpus of Egyptian texts](https://edoc.bbaw.de/frontdoor/index/index/docId/2919) compiled by the project "Strukturen und Transformationen des Wortschatzes der ägyptischen Sprache".
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
The dataset consists of parallel triples of
- `hieroglyphs`: [Encoding of the hieroglyphs with the [Gardiner's sign list](https://en.wikipedia.org/wiki/Gardiner%27s_sign_list)
- `transcription`: Transliteration of the above mentioned hieroglyphs with a [transliteration scheme](https://en.wikipedia.org/wiki/Transliteration_of_Ancient_Egyptian)
- `translation`: Translation in mostly German language (with some English mixed in)
## Dataset Structure
The dataset is not divided into 'train', 'dev' and 'test' splits as it was not built for competitive purposes and we encourage all scientists to use individual partitioning schemes to suit their needs (due to the low resource setting it might be advisable to use cross validation anyway). The only available split 'all' therefore comprises the full 100,708 translation triples, 35,503 of which possess hieroglyphic encodings (the remaining 65,205 triples have empty `hieroglyph` entries).
### Data Instances
An example of a data triple looks the following way:
```
{
"transcription": "n rḏi̯(.w) gꜣ =j r dbḥ.t m pr-ḥḏ",
"translation": "I was not let to suffer lack in the treasury with respect to what was needed;",
"hieroglyphs": "D35 D21 -D37 G1&W11 -V32B A1 D21 D46 -D58 *V28 -F18 *X1 -A2 G17 [? *O2 *?]"
}
```
*Important*: Only about a third of the instance actually cover hieroglyphic encodings (the rest is the empty string `""`) as the leftover encodings have not yet been incorporated into the BBAW's project database.
### Data Fields
#### plain_text
- `transcription`: a `string` feature.
- `translation`: a `string` feature.
- `hieroglyphs`: a `string` feature.
### Data Splits
| name |all|
|----------|----:|
|plain_text|100708|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
The data source comes from the project "Strukturen und Transformationen des Wortschatzes der ägyptischen Sprache" which is compiling an extensively annotated digital corpus of Egyptian texts. Their [publication](https://edoc.bbaw.de/frontdoor/index/index/docId/2919) comprises an excerpt of the internal database's contents.
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
The corpus has not been preprocessed as we encourage every scientist to prepare the corpus to their desired needs. This means, that all textcritic symbols are still included in the transliteration and translation. This concerns the following annotations:
- `()`: defective
- `[]`: lost
- `{}`: surplus
- `〈〉`: omitted
- `⸢⸣`: damaged
- `⸮?`: unclear
- `{{}}`: erasure
- `(())`: above
- `[[]]`: overstrike
- `〈〈〉〉`: haplography
Their exists a similar sign list for the annotation of the hieroglyphic encoding. If you wish access to this list, please get in contact with the author.
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
Source corpus:
```
@misc{OPUS4-2919,
title = {Teilauszug der Datenbank des Vorhabens "Strukturen und Transformationen des Wortschatzes der {\"a}gyptischen Sprache" vom Januar 2018},
institution = {Akademienvorhaben Strukturen und Transformationen des Wortschatzes der {\"a}gyptischen Sprache. Text- und Wissenskultur im alten {\"A}gypten},
type = {other},
year = {2018},
}
```
Translation paper:
```
@article{wiesenbach19,
title = {Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs},
author = {Wiesenbach, Philipp and Riezler, Stefan},
journal = {Proceedings of the International Workshop on Spoken Language Translation},
journal-abbrev = {IWSLT},
year = {2019},
url = {https://www.cl.uni-heidelberg.de/statnlpgroup/publications/IWSLT2019_v2.pdf}
}
```
### Contributions
Thanks to [@phiwi](https://github.com/phiwi) for adding this dataset. |
false |
# Dataset Card for "com_qa"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [http://qa.mpi-inf.mpg.de/comqa/](http://qa.mpi-inf.mpg.de/comqa/)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Size of downloaded dataset files:** 1.67 MB
- **Size of the generated dataset:** 1.10 MB
- **Total amount of disk used:** 2.78 MB
### Dataset Summary
ComQA is a dataset of 11,214 questions, which were collected from WikiAnswers, a community question answering website.
By collecting questions from such a site we ensure that the information needs are ones of interest to actual users.
Moreover, questions posed there are often cannot be answered by commercial search engines or QA technology, making them
more interesting for driving future research compared to those collected from an engine's query log. The dataset contains
questions with various challenging phenomena such as the need for temporal reasoning, comparison (e.g., comparatives,
superlatives, ordinals), compositionality (multiple, possibly nested, subquestions with multiple entities), and
unanswerable questions (e.g., Who was the first human being on Mars?). Through a large crowdsourcing effort, questions
in ComQA are grouped into 4,834 paraphrase clusters that express the same information need. Each cluster is annotated
with its answer(s). ComQA answers come in the form of Wikipedia entities wherever possible. Wherever the answers are
temporal or measurable quantities, TIMEX3 and the International System of Units (SI) are used for normalization.
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 1.67 MB
- **Size of the generated dataset:** 1.10 MB
- **Total amount of disk used:** 2.78 MB
An example of 'validation' looks as follows.
```
{
"answers": ["https://en.wikipedia.org/wiki/north_sea"],
"cluster_id": "cluster-922",
"questions": ["what sea separates the scandinavia peninsula from britain?", "which sea separates britain from scandinavia?"]
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `cluster_id`: a `string` feature.
- `questions`: a `list` of `string` features.
- `answers`: a `list` of `string` features.
### Data Splits
| name |train|validation|test|
|-------|----:|---------:|---:|
|default| 3966| 966|2243|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
```
@inproceedings{abujabal-etal-2019-comqa,
title = "{ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters",
author = {Abujabal, Abdalghani and
Saha Roy, Rishiraj and
Yahya, Mohamed and
Weikum, Gerhard},
booktitle = {Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)},
month = {jun},
year = {2019},
address = {Minneapolis, Minnesota},
publisher = {Association for Computational Linguistics},
url = {https://www.aclweb.org/anthology/N19-1027},
doi = {10.18653/v1/N19-1027{,
pages = {307--317},
}
```
### Contributions
Thanks to [@lewtun](https://github.com/lewtun), [@thomwolf](https://github.com/thomwolf), [@mariamabarham](https://github.com/mariamabarham), [@patrickvonplaten](https://github.com/patrickvonplaten), [@albertvillanova](https://github.com/albertvillanova) for adding this dataset. |
true |
# Dataset Card for Dutch Social Media Collection
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Dutch Social Media Collection](http://datasets.coronawhy.org/dataset.xhtml?persistentId=doi:10.5072/FK2/MTPTL7)
- **Repository:**
- **Paper:** *(in-progress)* https://doi.org/10.5072/FK2/MTPTL7
- **Leaderboard:**
- **Point of Contact:** [Aakash Gupta](mailto:aakashg80@gmail.com)
### Dataset Summary
The dataset contains 10 files with around 271,342 tweets. The tweets are filtered via the official Twitter API to contain tweets in Dutch language or by users who have specified their location information within Netherlands geographical boundaries. Using natural language processing we have classified the tweets for their HISCO codes. If the user has provided their location within Dutch boundaries, we have also classified them to their respective provinces The objective of this dataset is to make research data available publicly in a FAIR (Findable, Accessible, Interoperable, Reusable) way. Twitter's Terms of Service Licensed under Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (2020-10-27)
### Supported Tasks and Leaderboards
`sentiment analysis`, `multi-label classification`, `entity-extraction`
### Languages
The text is primarily in Dutch with some tweets in English and other languages. The BCP 47 code is `nl` and `en`
## Dataset Structure
### Data Instances
An example of the data field will be:
```
{
"full_text": "@pflegearzt @Friedelkorn @LAguja44 Pardon, wollte eigentlich das zitieren: \nhttps://t.co/ejO7bIMyj8\nMeine mentions sind inzw komplett undurchschaubar weil da Leute ihren supporterclub zwecks Likes zusammengerufen haben.",
"text_translation": "@pflegearzt @Friedelkorn @ LAguja44 Pardon wollte zitieren eigentlich das:\nhttps://t.co/ejO7bIMyj8\nMeine mentions inzw sind komplett undurchschaubar weil da Leute ihren supporter club Zwecks Likes zusammengerufen haben.",
"created_at": 1583756789000,
"screen_name": "TheoRettich",
"description": "I ❤️science, therefore a Commie. ☭ FALGSC: Part of a conspiracy which wants to achieve world domination. Tankie-Cornucopian. Ecology is a myth",
"desc_translation": "I ❤️science, Therefore a Commie. ☭ FALGSC: Part of a conspiracy How many followers wants to Achieve World Domination. Tankie-Cornucopian. Ecology is a myth",
"weekofyear": 11,
"weekday": 0,
"day": 9,
"month": 3,
"year": 2020,
"location": "Netherlands",
"point_info": "Nederland",
"point": "(52.5001698, 5.7480821, 0.0)",
"latitude": 52.5001698,
"longitude": 5.7480821,
"altitude": 0,
"province": "Flevoland",
"hisco_standard": null,
"hisco_code": null,
"industry": false,
"sentiment_pattern": 0,
"subjective_pattern": 0
}
```
### Data Fields
| Column Name | Description |
| --- | --- |
| full_text | Original text in the tweet |
| text_translation | English translation of the full text |
| created_at | Date of tweet creation |
| screen_name | username of the tweet author |
| description | description as provided in the users bio |
| desc_translation | English translation of user's bio/ description |
| location | Location information as provided in the user's bio |
| weekofyear | week of the year |
| weekday | Day of the week information; Monday=0....Sunday = 6|
| month | Month of tweet creation |
| year | year of tweet creation |
| day | day of tweet creation |
| point_info | point information from location columnd |
| point | tuple giving lat, lon & altitude information |
| latitude | geo-referencing information derived from location data |
| longitude | geo-referencing information derived from location data |
| altitude | geo-referencing information derived from location data|
| province | Province given location data of user |
| hisco_standard | HISCO standard key word; if available in tweet |
| hisco_code| HISCO standard code as derived from `hisco_standard`|
| industry | Whether the tweet talks about industry `(True/False)` |
| sentiment_score | Sentiment score -1.0 to 1.0 |
| subjectivity_score | Subjectivity scores 0 to 1 |
Missing values are replaced with empty strings or -1 (-100 for missing sentiment_score).
### Data Splits
Data has been split into Train: 60%, Validation: 20% and Test: 20%
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
The tweets were hydrated using Twitter's API and then filtered for those which were in Dutch language and/or for users who had mentioned that they were from within Netherlands geographical borders.
#### Who are the source language producers?
The language producers are twitter users who have identified their location within the geographical boundaries of Netherland. Or those who have tweeted in the dutch language!
### Annotations
Using Natural language processing, we have classified the tweets on industry and for HSN HISCO codes.
Depending on the user's location, their provincial information is also added. Please check the file/column for detailed information.
The tweets are also classified on the sentiment & subjectivity scores.
Sentiment scores are between -1 to +1
Subjectivity scores are between 0 to 1
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
As of writing this data card no anonymization has been carried out on the tweets or user data. As such, if the twitter user has shared any personal & sensitive information, then it may be available in this dataset.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
Dataset provided for research purposes only. Please check dataset license for additional information.
## Additional Information
### Dataset Curators
[Aakash Gupta](mailto:aakashg80@gmail.com)
*Th!nkEvolve Consulting* and Researcher at CoronaWhy
### Licensing Information
CC BY-NC 4.0
### Citation Information
@data{FK2/MTPTL7_2020,
author = {Gupta, Aakash},
publisher = {COVID-19 Data Hub},
title = {{Dutch social media collection}},
year = {2020},
version = {DRAFT VERSION},
doi = {10.5072/FK2/MTPTL7},
url = {https://doi.org/10.5072/FK2/MTPTL7}
}
### Contributions
Thanks to [@skyprince999](https://github.com/skyprince999) for adding this dataset. |
true |
# Dataset Card for Hausa VOA News Topic Classification dataset (hausa_voa_topics)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** -
- **Repository:** https://github.com/uds-lsv/transfer-distant-transformer-african
- **Paper:** https://www.aclweb.org/anthology/2020.emnlp-main.204/
- **Leaderboard:** -
- **Point of Contact:** Michael A. Hedderich and David Adelani
{mhedderich, didelani} (at) lsv.uni-saarland.de
### Dataset Summary
A news headline topic classification dataset, similar to AG-news, for Hausa. The news headlines were collected from [VOA Hausa](https://www.voahausa.com/).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Hausa (ISO 639-1: ha)
## Dataset Structure
### Data Instances
An instance consists of a news title sentence and the corresponding topic label.
### Data Fields
- `news_title`: A news title
- `label`: The label describing the topic of the news title. Can be one of the following classes: Nigeria, Africa, World, Health or Politics.
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@michael-aloys](https://github.com/michael-aloys) for adding this dataset. |
false |
# Dataset Card for Hebrew Projectbenyehuda
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://github.com/projectbenyehuda/public_domain_dump
- **Repository:** https://github.com/projectbenyehuda/public_domain_dump
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This repository contains a dump of thousands of public domain works in Hebrew, from Project Ben-Yehuda, in plaintext UTF-8 files, with and without diacritics (nikkud), and in HTML files. The pseudocatalogue.csv file is a list of titles, authors, genres, and file paths, to help you process the dump.
The Releases tab contains a downloadable ZIP archive of the full release. The git repo can be used to track individual file changes, or for incremenetal updates. In the ZIPs, each format (plaintext, plaintext stripped of diacritics, and HTML) has a ZIP file containing one directory per author, with all the author's works under that directory.
To request changes or improvements to this dump, file an issue against this repository.
All these works are in the public domain, so you are free to make any use of them, and do not need to ask for permission.
If you would like to give credit, please credit "Project Ben-Yehuda volunteers", and include a link to the site. We'd also love to hear about the uses you've made of this dump, as it encourages us to keep producing the dump. E-mail us with a brief description (and links, if/as appropriate) of your re-use, at editor@benyehuda.org.
There are 10078 files, 3181136 lines
Data Annotation:
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Hebrew
## Dataset Structure
### Data Instances
Sample:
```
{
'id': 10,
'url': 'https://raw.githubusercontent.com/projectbenyehuda/public_domain_dump/master/txt/p23/m10.txt',
'title': 'חצי-נחמה',
'authors': 'אחד העם',
'translators': '',
'original_language': '',
'genre': 'מאמרים ומסות',
'source_edition': '',
'text': '\n\n\n\t\n\tחצי-נחמה\n\t\n\n\n\n1\n\nבין כל הצרות שנתחדשו עלינו בעת האחרונה תעשׂה ביחוד רושם מעציב בלב כל איש ישׂראל התחדשות ‘עלילת־הדם’. העלילה הנתעבה הזאת, בכל יָשנה, היתה ותהיה תמיד בעינינו כחדשה, ומימי הבינים ועד עתה תצטין בפעולתה החזקה על רוח עמנו, לא רק במקום המעשׂה, כי אם גם בארצות רחוקות שהגיעה אליהן השמועה.\n\nאמרתי: ‘על רוח עמנו’, כי אמנם רואה אני מקור החזיון הזה לא בסבּות חיצוניות, כי אם עמוק ברוח העם. בימי הבינים, שהיה כלל ישׂראל במקרים כאלה רגיל לחשוב עצמו כעומד במשפט ביחד עם אותם האומללים שעלה עליהם הגורל להיות כפּרותו, – יש מקום אמנם לראות בזה רק תוצאת הסכנה הגשמית הגדולה להכלל כולו, שהיתה כרוכה אז באמת בעקב כל עלילה כזו. גם לפני חמשים שנה, בימי מנוחה ושלוה, שעוררה עלילת דמשׂק רעש גדול כל־כך בארצות המערב, עדיין יש מקום לאמר, כי היתה בזה, להפך, יד הקנאה הגדולה לכבודם וזכויותיהם ששׂררה אז בלבות אחינו המערביים, אשר זה מעט יצאו מעבדות לחרות. אך בימינו אלה הרי מצד אחד אין הסכנה הגשמית גדולה עוד הרבה, ביחוד לקהלות רחוקות, ומצד אחר כבר הורגלנו לשמוע חרפתנו בקור רוח וקנאת כבודנו לא תאכלנו עוד, ואם בכל זאת גם עתה עודנו מתעוררים ומתנודדים בחזקה לשמע ‘עלילת־דם’, ורגש הכלל יתפרץ החוצה מכל עברים להשליך מעליו את החלאה הזאת, – אות הוא, כי לא הפחד ולא הכבוד החיצוני הם המניעים לזה, כי אם רוח העם הוא המרגיש פה את קלונו והוא זה המתעורר והמעורר; כי אעפ"י שבכל יתר הדברים כבר הביאונו צרותינו לאותו המצב שעליו אמר הנשׂיא החכם בימי קדם: ‘אין בשׂר המת מרגיש באיזמל’, – הנה פה אין ‘האיזמל’ חותך את ‘הבשׂר’ בלבד, כי אם עד הנפש יגע…\n\nאבל – ‘אין רע בלא טוב’, כלומר, בלא לקח טוב. גם הרע הגדול הזה שאנו עסוקים בו אינו ריק מלקח טוב, ואנחנו, אשר לא אדונים אנחנו לגורלנו וגם את הטוב גם את הרע נקבל מן החוץ שלא בטובתנו, ראוי לנו לבקש ברעותינו תמיד את התועלת הלמודית הצפונה בהן, והיתה לנו זאת, לפחות, חצי נחמה.\n\n\n\nאחד הכוחות היותר גדולים בחיי החברה הוא – ‘ההסכמה הכללית’. היו ימים שגם הפלוסופים ראו בהסכמה זו מופת נאמן על הדבר המוסכם ונתנו לה מקום בתוך שאר מופתיהם על מציאות האלהות. עתה אמנם יודעים הפלוסופים , שאין שקר ואין אולת אשר לא תוכל לבוא עליו ‘ההסכמה הכללית’, אם אך תנאי החיים נאותים לזה. אבל רק הפלוסופים יודעים זאת, ובעיני ההמון עוד גם עתה אין אַבטוֹריטט גדול מן ‘ההסכמה’: אם ‘כל העולם’ מאמינים שהדבר כן, בודאי כן הוא; ואם אני איני מבינו, אחרים מבינים; ואם אני רואה כעין סתירה לו, הרי ‘הכל’ רואים גם כן ואעפ"כ מאמינים, וכי חכם אני מכל העולם? – זה הוא בקירוב מהלך הרעיונות של האיש הפשוט, בדעת או בלי דעת ברורה, ומתוך כך הוא מסכים גם מצדו ונעשׂה בעצמו חלק מן ‘ההסכמה’.\n\nוכל־כך גדול כוח ‘ההסכמה’, עד שעל הרוב לא יוכל האדם למַלט נפשו מפעולתה גם כשהוא עצמו הוא ‘הדבר המוסכם’. אם ‘כל העולם’ אומרים על פלוני שגדול הוא בחכמה או ביראה, שיש בו מדה פלונית, טובה או רעה, – סופו להסכים לזה גם בעצמו, אע"פ שמתחלה לא מצא בנפשו אותו היתרון או החסרון שאחרים מיחסים לו. ולא זו בלבד אלא שההסכמה הזאת מצד ‘המוסכם’ עצמו פועלת מעט מעט על תכונת רוחו עד שמקרבתו באמת (או, לפחות, מולידה בו נטיה להתקרב) אל המצב ההוא שרואה בו ‘כל העולם’. על כן יזהירו הפדגוגים בצדק, לבלתי עורר את הילדים על מגרעותיהם המוסריות בראשית התפתחותן, וכל שכּן לבלתי יחס להם מגרעות שאין בהם, כי על ידי זה אפשר שנחזק בלבם את הראשונות ונוליד בם נטיה להאחרונות.\n\nואולם, הדבר מובן, כי ‘כל העולם’ אינו אחד לכל אחד. האדם רואה ‘עולמו’ רק באותה החברה שהוא חושב עצמו לחלק ממנה ורואה באישיה אנשים הקרובים לו מאיזה צד; אבל אין אדם חושב למאומה הסכמת אנשים שרוחם זרה לו לגמרי, שאינו מרגיש בנפשו שום יחס פנימי בינו ובינם. ככה אין האוֹרתוֹדוֹכּסים והמשׂכילים שלנו שׂמים לב כלל אלו להסכמתם של אלו, אף בדברים שאינם נוגעים לאמונה ודת, ושׂחקם ולעגם של אלו על אלו אינו עושׂה שום רושם בלבם של שניהם, לפי שכּל אחת משתי הכּתּות רואה את חברתה כאלו אינה. ואולם כשתנאי החיים מכריחים את בני הכתות השונות להמצא במשׂא ומתן תמידי זה עם זה והם מתרגלים לראות זה בזה קודם כל את האדם, – אז יתרחב ‘עולמם’ והשקפותיהם סובלות שנויים רבים על פי הסכמת ‘העולם’ במובנו החדש.\n\n\n\nלפיכך, בדורות שעברו, כשהיו אבותינו מאמינים בפשטו של ‘אתה בחרתנו’, לא היתה החרפּה שחרפום האומות פועלת כלל על טוהר נפשם פנימה. הם ידעו את ערכם ולא התפעלו עד מה מן ‘ההסכמה הכללית’ אשר מחוץ להם, בהיות כל חברת ‘המסכימים’ נחשבת בעיניהם למין מיוחד של בריות זרות להם ושונות מהם שנוי עצמי, בלי כל יחס וכל דמיון בינם ובינן. אז היה היהודי יכול לשמוע במנוחת לב כל המגרעות המוסריות והחטאים המעשׂיים שטפלה עליו הסכמת העמים, מבלי להרגיש בנפשו שום בושה או שפלוּת פנימית. כי מה לו ולמחשבות ‘הנכרים’ עליו ועל ערכּוֹ? לוּ רק יתנו לו לישב בשלוה! – אבל בדור הזה אין הדבר כן, עתה ‘עולמנו’ נתרחב הרבה, וההסכמה האירופּית פועלת עלינו בחזקה בכל ענפי החיים. ולפי שאין אנו מוציאים עוד את ‘הכל’ מן הכלל, לכן נתפעל בעל כרחנו ממה ש’הכל\' מוציאים אותנו מן הכלל, סופר אחד רוסי שאל באלו הימים בתמימוּת: אחר שכל העולם שׂונאים את היהודים, וכי אפשר לאמור, שכל העולם חייבים והיהודים זכאים? – ושאלה כזו מתגנבת עתה גם אל לב רבים מאחינו: וכי אפשר לאמור, שכל אותן התכונות הנשחתות והמעשׂים הרעים שכל העולם מיחס ליהודים אינם אלא ‘בדותא’?\n\nוהספק הזה, מכיון שנתעורר, מוצא לו מחיה בנקל באותם ההיקשים המוטעים ‘מן הפרט אל הכלל’ הרגילים מאד אצל המון בני האדם. הספור הידוע על דבר נוסע אחד, שבא לאחת הערים ונזדמן לאכסניא שהיה בה משרת כבד־פה, וכתב בפנקסו: בעיר פלונית משרתי האכסניות הם כבדי־פה, – הספור הזה מצייר בצורה של התוּל דרכי־ההגיון של ההמון ברוב משפטיו הכלליים. כל החזיונות הנראים באיזה דבר פרטי רגיל ההמון ליחס אל הכלל שהדבר ההוא מתחשב עליו לפי שמו התמידי, מבלי להתבונן, כי ‘פרט’ אחד יוכל להתחשב על ‘כללים’ רבים ביחד, כלומר, להיות שוּתף בתכוּנה אחת עם פרטיו של כלל אחד ובתכונה אחרת עם פרטיו של כלל אחר, בעוד שהשם הנקרא עליו מציין רק את התיחסותו לאחד הכללים באחד מצדדיו, לא בכולם. – על משפטים ממין זה תוכל להשען, וגם תשען באמת, ההסכמה הכללית ביחוסה אלינו: פלוני ופלוני הם יהודים לפי שמם ורמאים לפי תכוּנתם; שמע מינה, שהיהודים הם לפי תכונתם רמאים. ההגיון האמתי ישיב אמנם על זה, כי אף אם היו באמת כל היהודים בדורנו רמאים, אין מזה עוד ראיה, שהיהודים הם רמאים, כלומר, שתכוּנת הרמאוּת הנמצאת בכל יהודי נמצאת בו מצד התיחסותו אל הכלל ‘יהודים’ ולא מצד איזה כלל אחר (למשל, כלל ‘סוחרים’), שגם אליו מתיחס היהודי בתור פרט, ביחד עם אחרים אשר דבר אין להם עם הכלל ‘יהודים’. וכדי לברר הדבר, צריך לבדוֹק תחלה אותם ‘האחרים’ המשתתפים יחד עם היהודים בכללים אחרים. ורק אחר שנמצא על ידי בדיקה זו, שאין תכוּנת הרמאוּת מצויה בשום ‘כלל’ אחר המשותף ליהודים ולאחרים, – רק אז תהיה לנו צדקה לחרוץ משפט, כי היהדות היא אֵם הרמאוּת. – אבל, כאמור, אין דרכם של בני אדם להעמיק בהגיון, ואין אנו יכולים לדרוש כזאת גם מהמון בני עמנו. הם שומעים את המשפט החרוץ של ההסכמה הכללית ורואים עם זה, שרבים בקרבּנוּ כך הם באמת כמו שאומרת ההסכמה, ובזה די להם, והרי הם מתחילים להסכים גם בעצמם. וככה עוברות ‘תכוּנות היהודים’ כמטבע כשרה מיד ליד, מן ההסכמה החיצונית של העמים אל ההסכמה הפנימית בקרב עמנו, רק עם ההבדל הזה, שהעמים מונים את תכוּנותינו הרעות אחת לאחת בקול ענוֹת גבוּרה ולעג השאננים, ואנחנו עונים אחריהם מלה במלה בקול דממה דקה והצטדקות חלושה; הם ממשילים אותנו לכלי חרס, שאין לו תקנה אלא שבירה, ואנחנו ממשילים עצמנו לכלי מתכת, שאפשר לו בהגעלה ולבּוּן…\n\nהמצב הזה, אם יאריך ימים, יוכל לגרום לנו נזק מוסרי גדול. אין דבר מסוכּן לגוי ולאדם כהודאה על חטאים שאין בו. מי שחטא באמת, הרי שערי תשובה לא ננעלו, וברצונו הטוב יכול להסיר חלאתו מעליו. אבל מי שאחרים הביאוהו לחשוֹד עצמו במה שאין בו, איך יוכל להטהר בעיני עצמו? מצד אחד מאמין הוא לדברי האומרים לו: טול קורה מבין עיניך, ומצד אחר מרגיש הוא, שאינו יכול לטול את הקורה מבין עיניו, אחר שאינה באמת אלא בדמיון, והרי הוא במצב אותם המונומַנים הידועים, שמאיזו סבּה באו לידי אמונה, כי משׂא כבד תלוי להם בחוטמם מבלי שיוכלו להסירו. ולא עוד אלא שלפעמים תביא אמונה זו את האיש הפרטי להשתתף באותה המדה המגוּנה שלפי אמונתו היא קנין הכלל כולו, אעפ“י שהוא עצמו מצד פרטיותו אינו נוטה כלל לזה. אין ספק, למשל, כי בקרב העם שיצאו מתוכו אנשים כהרמב”ם נמצאים גם עתה בעלי דעה מיושבת ואוהבי סדר ושיטה בכל דבר, והם, בקחתם חלק בעבודת הצבּוּר, היו יכולים לתת בה את רוחם ולפעול גם על יתר העובדים. אבל מה נעשׂה, וכל גזרה ‘ההסכמה’, ששׂנאת הסדרים היא תכוּנה יהודית, וכבר הסכמנו גם אנחנו להסכמה זו (אעפ"י שעוד לא נתברר, אם התכוּנה הזאת, המצויה באמת בחלק גדול מעמנו, מתיחסת אל הכלל ‘יהודים’, או אולי – מה שיותר מתקבל על הלב – אל הכלל ‘חניכי־החדר’). ועל כן תרפינה ידי אוהבי הסדר, בהאמינם, כי אין עצה ואין תבונה נגד תכוּנת העם. ואם פטריוטים הם, יעקרו גם מלבם את האהבה לסדרים, המתנגדת לרוח עמם, ויעשׂו גם הם את מעשׂיהם כראוי ליהודים אמתיים…\n\n\n\nצריך איפוא לבקש איזה אמצעי, איך להוציא את עצמנו מתחת השפעת ‘ההסכמה הכללית’ בנוגע לתכוּנות ישׂראל וערכו המוסרי, כדי שלא נהיה בזויים בעיני עצמנו ולא נחשוב, שבאמת גרועים אנחנו מכל בני האדם תחת השמש, וכדי שלא נבוא עי"ז להיות ברבות הימים בפועל מה שאין אנו עתה אלא בדמיון.\n\nואת האמצעי הזה נותנת לנו ‘ההסכמה הכללית’ עצמה על ידי עלילת־הדם. העלילה הזאת היא היחידה בין כל רעותיה אשר בה לא תוכל ההסכמה להביא גם אותנו לידי ספק, אם באמת ‘כל העולם חייבים ואנחנו זכאים’, בהיותה מיוסדת כולה על שקר מוחלט ואין לה משען באיזה היקש מוטעה ‘מן הפרט על הכלל’. כל איש ישׂראל שנתחנך בתוך עמו יודע בבירור גמור, שאין בתוך כלל ישׂראל אף פרט אחד האוכל דם אדם לשם שמים. ואת הידיעה הברורה הזאת משגיאת ‘ההסכמה הכללית’, המתחדשת בלבנו מזמן לזמן על ידי התחדשות עלילת־הדם, צריכים אנו לשמור תמיד בזכרוננו, והיא תעזור לנו לעקור מלבנו את הנטיה להכּנע מפני האַבטוֹריטט של ‘כל העולם’ גם ביתר הדברים. יאמר כל העולם מה שיאמר על דבר פחיתוּת ערכּנוּ המוסרי, – אנחנו יודעים, כי ‘ההסכמה’ הזאת נשענת רק על הגיון המוני, בלי כל יסוד מדעי אמתּי. כי מי בא בסוד עמקי רוחנו וראה את ‘היהודי’ כמו שהוא מצד עצמו? מי שקל זה לעומת זה יהודים ושאינם יהודים הדומים אלו לאלו בכל יתר ‘הכללים’: סוחרים לעומת סוחרים, נרדפים לעומת נרדפים, רעבים לעומת רעבים וכו\'. – מי שקל כל אלה במאזני החכמה האמתּית ומצא את הכף מַכרעת לאחד הצדדים?\n\n‘וכי אפשר שכּל העולם חייבים והיהודים זכאים?’\n\nאפשר ואפשר, ועלילת־הדם תוכיח. פה הרי היהודים זכאים וטהורים כמלאכי השרת: יהודי ודם! היש שני הפכים גדולים מאלו? – ואף על פי כן…\n\n\n\nה\' תשרי תרנ"ג\n\n\n\n\n\n\nנדפס ב‘המליץ’ י“ד תשרי תרנ”ג. \xa0↩\n\n\n\n\n\n\n\n\n\n\nאת הטקסט לעיל הפיקו מתנדבי פרויקט בן־יהודה באינטרנט. הוא זמין תמיד בכתובת הבאה:https://benyehuda.org/read/10'
}
```
### Data Fields
- `authors`
- `genre`
- `id`
- `original_language`
- `source_edition`
- `text`
- `title`
- `translators`
- `url`
### Data Splits
| | train |
|--------|------:|
| corpus | 10078 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
Researchers.
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
MIT License
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
### Citation Information
```
@article{,
author = {},
title = {Public domain texts from Project Ben-Yehuda},
journal = {},
url = {https://github.com/projectbenyehuda/public_domain_dump},
year = {2020},
}
```
### Contributions
Thanks to [@imvladikon](https://github.com/imvladikon) for adding this dataset. |
false |
# Dataset Card for "librispeech_lm"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [http://www.openslr.org/11](http://www.openslr.org/11)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Size of downloaded dataset files:** 1.51 GB
- **Size of the generated dataset:** 4.42 GB
- **Total amount of disk used:** 5.93 GB
### Dataset Summary
Language modeling resources to be used in conjunction with the LibriSpeech ASR corpus.
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 1.51 GB
- **Size of the generated dataset:** 4.42 GB
- **Total amount of disk used:** 5.93 GB
An example of 'train' looks as follows.
```
{
"text": "This is a test file"
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `text`: a `string` feature.
### Data Splits
| name | train |
|-------|-------:|
|default|40418260|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
```
@inproceedings{panayotov2015librispeech,
title={Librispeech: an ASR corpus based on public domain audio books},
author={Panayotov, Vassil and Chen, Guoguo and Povey, Daniel and Khudanpur, Sanjeev},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on},
pages={5206--5210},
year={2015},
organization={IEEE}
}
```
### Contributions
Thanks to [@lewtun](https://github.com/lewtun), [@jplu](https://github.com/jplu), [@thomwolf](https://github.com/thomwolf) for adding this dataset. |
false |
# `deepa2` Datasets Collection
## Table of Contents
- [`deepa2` Datasets Collection](#deepa2-datasets-collection)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Sub-Datasets](#sub-datasets)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Initial Data Collection and Normalization](#initial-data-collection-and-normalization)
- [Who are the source language producers?](#who-are-the-source-language-producers)
- [Annotations](#annotations)
- [Annotation process](#annotation-process)
- [Who are the annotators?](#who-are-the-annotators)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [blog post](https://debatelab.github.io/journal/deepa2.html)
- **Repository:** [github](https://github.com/debatelab/deepa2)
- **Paper:** [arxiv](https://arxiv.org/abs/2110.01509)
- **Point of Contact:** [Gregor Betz](gregor.betz@kit.edu)
### Dataset Summary
This is a growing, curated collection of `deepa2` datasets, i.e. datasets that contain comprehensive logical analyses of argumentative texts. The collection comprises:
* datasets that are built from existing NLP datasets by means of the [`deepa2 bake`](https://github.com/debatelab/deepa2) tool.
* original `deepa2` datasets specifically created for this collection.
The tool [`deepa2 serve`](https://github.com/debatelab/deepa2#integrating-deepa2-into-your-training-pipeline) may be used to render the data in this collection as text2text examples.
### Supported Tasks and Leaderboards
For each of the tasks tagged for this dataset, give a brief description of the tag, metrics, and suggested models (with a link to their HuggingFace implementation if available). Give a similar description of tasks that were not covered by the structured tag set (repace the `task-category-tag` with an appropriate `other:other-task-name`).
- `conditional-text-generation`: The dataset can be used to train models to generate a fully reconstruction of an argument from a source text, making, e.g., its implicit assumptions explicit.
- `structure-prediction`: The dataset can be used to train models to formalize sentences.
- `text-retrieval`: The dataset can be used to train models to extract reason statements and conjectures from a given source text.
### Languages
English. Will be extended to cover other languages in the futures.
## Dataset Structure
### Sub-Datasets
This collection contains the following `deepa2` datasets:
* `esnli`: created from e-SNLI with `deepa2 bake` as [described here](https://github.com/debatelab/deepa2/blob/main/docs/esnli.md).
* `enbank` (`task_1`, `task_2`): created from Entailment Bank with `deepa2 bake` as [described here](https://github.com/debatelab/deepa2/blob/main/docs/enbank.md).
* `argq`: created from IBM-ArgQ with `deepa2 bake` as [described here](https://github.com/debatelab/deepa2/blob/main/docs/argq.md).
* `argkp`: created from IBM-KPA with `deepa2 bake` as [described here](https://github.com/debatelab/deepa2/blob/main/docs/argkp.md).
* `aifdb` (`moral-maze`, `us2016`, `vacc-itc`): created from AIFdb with `deepa2 bake` as [described here](https://github.com/debatelab/deepa2/blob/main/docs/aifdb.md).
* `aaac` (`aaac01` and `aaac02`): original, machine-generated contribution; based on an an improved and extended algorithm that backs https://huggingface.co/datasets/debatelab/aaac.
### Data Instances
see: https://github.com/debatelab/deepa2/tree/main/docs
### Data Fields
see: https://github.com/debatelab/deepa2/tree/main/docs
|feature|esnli|enbank|aifdb|aaac|argq|argkp|
|--|--|--|--|--|--|--|
| `source_text` | x | x | x | x | x | x |
| `title` | | x | | x | | |
| `gist` | x | x | | x | | x |
| `source_paraphrase` | x | x | x | x | | |
| `context` | | x | | x | | x |
| `reasons` | x | x | x | x | x | |
| `conjectures` | x | x | x | x | x | |
| `argdown_reconstruction` | x | x | | x | | x |
| `erroneous_argdown` | x | | | x | | |
| `premises` | x | x | | x | | x |
| `intermediary_conclusion` | | | | x | | |
| `conclusion` | x | x | | x | | x |
| `premises_formalized` | x | | | x | | x |
| `intermediary_conclusion_formalized` | | | | x | | |
| `conclusion_formalized` | x | | | x | | x |
| `predicate_placeholders` | | | | x | | |
| `entity_placeholders` | | | | x | | |
| `misc_placeholders` | x | | | x | | x |
| `plchd_substitutions` | x | | | x | | x |
### Data Splits
Each sub-dataset contains three splits: `train`, `validation`, and `test`.
## Dataset Creation
### Curation Rationale
Many NLP datasets focus on tasks that are relevant for logical analysis and argument reconstruction. This collection is the attempt to unify these resources in a common framework.
### Source Data
See: [Sub-Datasets](#sub-datasets)
## Additional Information
### Dataset Curators
Gregor Betz, KIT; Kyle Richardson, Allen AI
### Licensing Information
We re-distribute the the imported sub-datasets under their original license:
|Sub-dataset|License|
|--|--|
|esnli|MIT|
|aifdb|free for academic use ([TOU](https://arg-tech.org/index.php/research/argument-corpora/))|
|enbank|CC BY 4.0|
|aaac|CC BY 4.0|
|argq|CC BY SA 4.0|
|argkp|Apache|
### Citation Information
```
@article{betz2021deepa2,
title={DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models},
author={Gregor Betz and Kyle Richardson},
year={2021},
eprint={2110.01509},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--If the dataset has a [DOI](https://www.doi.org/), please provide it here.-->
|
true |
# Dataset Card for HateOffensive
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage** : https://arxiv.org/abs/1905.12516
- **Repository** : https://github.com/t-davidson/hate-speech-and-offensive-language
- **Paper** : https://arxiv.org/abs/1905.12516
- **Leaderboard** :
- **Point of Contact** : trd54 at cornell dot edu
### Dataset Summary
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English (`en`)
## Dataset Structure
### Data Instances
```
{
"count": 3,
"hate_speech_annotation": 0,
"offensive_language_annotation": 0,
"neither_annotation": 3,
"label": 2, # "neither"
"tweet": "!!! RT @mayasolovely: As a woman you shouldn't complain about cleaning up your house. & as a man you should always take the trash out...")
}
```
### Data Fields
count: (Integer) number of users who coded each tweet (min is 3, sometimes more users coded a tweet when judgments were determined to be unreliable,
hate_speech_annotation: (Integer) number of users who judged the tweet to be hate speech,
offensive_language_annotation: (Integer) number of users who judged the tweet to be offensive,
neither_annotation: (Integer) number of users who judged the tweet to be neither offensive nor non-offensive,
label: (Class Label) integer class label for majority of CF users (0: 'hate-speech', 1: 'offensive-language' or 2: 'neither'),
tweet: (string)
### Data Splits
This dataset is not splitted, only the train split is available.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
Usernames are not anonymized in the dataset.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
MIT License
### Citation Information
@inproceedings{hateoffensive,
title = {Automated Hate Speech Detection and the Problem of Offensive Language},
author = {Davidson, Thomas and Warmsley, Dana and Macy, Michael and Weber, Ingmar},
booktitle = {Proceedings of the 11th International AAAI Conference on Web and Social Media},
series = {ICWSM '17},
year = {2017},
location = {Montreal, Canada},
pages = {512-515}
}
### Contributions
Thanks to [@MisbahKhan789](https://github.com/MisbahKhan789) for adding this dataset. |
false |
# Dataset Card for PersonalDialog
## Table of Contents
- [Dataset Card for PersonalDialog](#dataset-card-for-personaldialog)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Initial Data Collection and Normalization](#initial-data-collection-and-normalization)
- [Who are the source language producers?](#who-are-the-source-language-producers)
- [Annotations](#annotations)
- [Annotation process](#annotation-process)
- [Who are the annotators?](#who-are-the-annotators)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.zhengyinhe.com/datasets/
- **Repository:** https://github.com/silverriver/PersonalDilaog
- **Paper:** https://arxiv.org/abs/1901.09672
### Dataset Summary
The PersonalDialog dataset is a large-scale multi-turn Chinese dialogue dataset containing various traits from a large number of speakers.
We are releasing about 5M sessions of carefully filtered dialogues.
Each utterance in PersonalDialog is associated with a speaker marked with traits like Gender, Location, Interest Tags.
### Supported Tasks and Leaderboards
- dialogue-generation: The dataset can be used to train a model for generating dialogue responses.
- response-retrieval: The dataset can be used to train a reranker model that can be used to implement a retrieval-based dialogue model.
### Languages
PersonalDialog is in Chinese
PersonalDialog中的对话是中文的
## Dataset Structure
### Data Instances
`train` split:
```json
{
"dialog": ["那么 晚", "加班 了 刚 到 家 呀 ！", "吃饭 了 么", "吃 过 了 ！"],
"profile": [
{
"tag": ["间歇性神经病", "爱笑的疯子", "他们说我犀利", "爱做梦", "自由", "旅游", "学生", "双子座", "好性格"],
"loc": "福建 厦门", "gender": "male"
}, {
"tag": ["设计师", "健康养生", "热爱生活", "善良", "宅", "音樂", "时尚"],
"loc": "山东 济南", "gender": "male"
}
],
"uid": [0, 1, 0, 1],
}
```
`dev` and `test` split:
```json
{
"dialog": ["没 人性 啊 ！", "可以 来 组织 啊", "来 上海 陪姐 打 ？"],
"profile": [
{"tag": [""], "loc": "上海 浦东新区", "gender": "female"},
{"tag": ["嘉庚", "keele", "leicester", "UK", "泉州五中"], "loc": "福建 泉州", "gender": "male"},
],
"uid": [0, 1, 0],
"responder_profile": {"tag": ["嘉庚", "keele", "leicester", "UK", "泉州五中"], "loc": "福建 泉州", "gender": "male"},
"golden_response": "吴经理 派车来 小 泉州 接 么 ？",
"is_biased": true,
}
```
### Data Fields
- `dialog` (list of strings): List of utterances consisting of a dialogue.
- `profile` (list of dicts): List of profiles associated with each speaker.
- `tag` (list of strings): List of tags associated with each speaker.
- `loc` (string): Location of each speaker.
- `gender` (string): Gender of each speaker.
- `uid` (list of int): Speaker id for each utterance in the dialogue.
- `responder_profile` (dict): Profile of the responder. (Only available in `dev` and `test` split)
- `golden_response` (str): Response of the responder. (Only available in `dev` and `test` split)
- `id_biased` (bool): Whether the dialogue is guranteed to be persona related or not. (Only available in `dev` and `test` split)
### Data Splits
|train|valid|test|
|---:|---:|---:|
|5,438,165 | 10,521 | 10,523 |
## Dataset Creation
### Curation Rationale
[Needs More Information]
### Source Data
#### Initial Data Collection and Normalization
[Needs More Information]
#### Who are the source language producers?
[Needs More Information]
### Annotations
#### Annotation process
[Needs More Information]
#### Who are the annotators?
[Needs More Information]
### Personal and Sensitive Information
[Needs More Information]
## Considerations for Using the Data
### Social Impact of Dataset
[Needs More Information]
### Discussion of Biases
[Needs More Information]
### Other Known Limitations
[Needs More Information]
## Additional Information
### Dataset Curators
[Needs More Information]
### Licensing Information
other-weibo
This dataset is collected from Weibo.
You can refer to the [detailed policy](https://weibo.com/signup/v5/privacy) required to use this dataset.
Please restrict the usage of this dataset to non-commerical purposes.
### Citation Information
```bibtex
@article{zheng2019personalized,
title = {Personalized dialogue generation with diversified traits},
author = {Zheng, Yinhe and Chen, Guanyi and Huang, Minlie and Liu, Song and Zhu, Xuan},
journal = {arXiv preprint arXiv:1901.09672},
year = {2019}
}
@inproceedings{zheng2020pre,
title = {A pre-training based personalized dialogue generation model with persona-sparse data},
author = {Zheng, Yinhe and Zhang, Rongsheng and Huang, Minlie and Mao, Xiaoxi},
booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
volume = {34},
number = {05},
pages = {9693--9700},
year = {2020}
}
```
### Contributions
Thanks to [Yinhe Zheng](https://github.com/silverriver) for adding this dataset.
|
true |
# Dataset Card for Bengali Hate Speech Dataset
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Bengali Hate Speech Dataset](https://github.com/rezacsedu/Bengali-Hate-Speech-Dataset)
- **Repository:** [Bengali Hate Speech Dataset](https://github.com/rezacsedu/Bengali-Hate-Speech-Dataset)
- **Paper:** [Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network](https://arxiv.org/abs/2004.07807)
- **Point of Contact:** [Md. Rezaul Karim](rezaul.karim.fit@gmail.com)
### Dataset Summary
The Bengali Hate Speech Dataset is a Bengali-language dataset of news articles collected from various Bengali media sources and categorized based on the type of hate in the text. The dataset was created to provide greater support for under-resourced languages like Bengali on NLP tasks, and serves as a benchmark for multiple types of classification tasks.
### Supported Tasks and Leaderboards
* `topic classification`: The dataset can be used to train a Multichannel Convolutional-LSTM for classifying different types of hate speech. The model performance can be measured by its F1 score.
### Languages
The text in the dataset is in Bengali and the associated BCP-47 code is `bn`.
## Dataset Structure
### Data Instances
A data instance takes the form of a news article and its associated label.
🚨 Beware that the following example contains extremely offensive content!
An example looks like this:
```
{"text": "রেন্ডিয়াকে পৃথীবির মানচিএ থেকে মুচে ফেলতে হবে",
"label": "Geopolitical"}
```
### Data Fields
* `text`: the text of the Bengali news article
* `label`: one of `Geopolitical`, `Personal`, `Political`, `Religious`, or `Gender abusive` indicating the type of hate speech
### Data Splits
The dataset has 3418 examples.
## Dataset Creation
### Curation Rationale
Under-resourced languages like Bengali lack supporting resources that languages like English have. This dataset was collected from multiple Bengali news sources to provide several classification benchmarks for hate speech detection, document classification and sentiment analysis.
### Source Data
#### Initial Data Collection and Normalization
Bengali articles were collected from a Bengali Wikipedia dump, Bengali news articles, news dumps of TV channels, books, blogs, sports portal and social media. Emphasis was placed on Facebook pages and newspaper sources because they have about 50 million followers and is a common source of opinion and hate speech. The full dataset consists of 250 million articles and is currently being prepared. This is a subset of the full dataset.
#### Who are the source language producers?
The source language producers are Bengali authors and users who interact with these various forms of Bengali media.
### Annotations
#### Annotation process
The data was annotated by manually identifying freqently occurring terms in texts containing hate speech and references to specific entities. The authors also prepared normalized frequency vectors of 175 abusive terms that are commonly used to express hate in Bengali. A hate label is assigned if at least one of these terms exists in the text. Annotator's were provided with unbiased text only contents to make the decision. Non-hate statements were removed from the list and the category of hate was further divided into political, personal, gender abusive, geopolitical and religious. To reduce possible bias, each label was assigned based on a majority voting on the annotator's opinions and Cohen's Kappa was computed to measure inter-annotator agreement.
#### Who are the annotators?
Three native Bengali speakers and two linguists annotated the dataset which was then reviewed and validated by three experts (one South Asian linguist and two native speakers).
### Personal and Sensitive Information
The dataset contains very sensitive and highly offensive comments in a religious, political and gendered context. Some of the comments are directed towards contemporary public figures like politicians, religious leaders, celebrities and athletes.
## Considerations for Using the Data
### Social Impact of Dataset
The purpose of the dataset is to improve hate speech detection in Bengali. The growth of social media has enabled people to express hate freely online and there has been a lot of focus on detecting hate speech for highly resourced languages like English. The use of hate speech is pervasive, like any other major language, which can have serious and deadly consequences. Failure to react to hate speech renders targeted minorities more vulnerable to attack and it can also create indifference towards their treatment from majority populations.
### Discussion of Biases
The dataset was collected using a bootstrapping approach. An initial search was made for specific types of texts, articles and tweets containing common harassment directed at targeting characteristics. As a result, this dataset contains **extremely** offensive content that is disturbing. In addition, Facebook pages and newspaper sources were emphasized because they are well-known for having hate and harassment issues.
### Other Known Limitations
The dataset contains racist, sexist, homophobic and offensive comments. It is collected and annotated for research related purposes only.
## Additional Information
### Dataset Curators
The dataset was curated by Md. Rezaul Karim, Sumon Kanti Dey, Bharathi Raja Chakravarthi, John McCrae and Michael Cochez.
### Licensing Information
This dataset is licensed under the MIT License.
### Citation Information
```
@inproceedings{karim2020BengaliNLP,
title={Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network},
author={Karim, Md. Rezaul and Chakravarti, Bharathi Raja and P. McCrae, John and Cochez, Michael},
booktitle={7th IEEE International Conference on Data Science and Advanced Analytics (IEEE DSAA,2020)},
publisher={IEEE},
year={2020}
}
```
### Contributions
Thanks to [@stevhliu](https://github.com/stevhliu) for adding this dataset. |
true |
# Dataset Card for Consumer Finance Complaints
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.consumerfinance.gov/data-research/consumer-complaints/
- **Repository:**
https://github.com/cfpb/consumerfinance.gov
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This database is a collection of complaints about consumer financial products and services that we sent to companies for response.
The Consumer Complaint Database is a collection of complaints about consumer financial products and services that we sent to companies for response. Complaints are published after the company responds, confirming a commercial relationship with the consumer, or after 15 days, whichever comes first. Complaints referred to other regulators, such as complaints about depository institutions with less than $10 billion in assets, are not published in the Consumer Complaint Database. The database generally updates daily.
Complaints can give us insights into problems people are experiencing in the marketplace and help us regulate consumer financial products and services under existing federal consumer financial laws, enforce those laws judiciously, and educate and empower consumers to make informed financial decisions. We also report on complaint trends annually in Consumer Response’s Annual Report to Congress.
### Supported Tasks and Leaderboards
Text Classification Tasks
| Task | Label Name | Description | SOTA |
| ----------- | ----------- |----------- | ----------- |
| Text Classification | Product| Predict the related product of a complaint | N/A |
| Task | Label Name | Description | SOTA |
| ----------- | ----------- |----------- | ----------- |
| Text Classification | Sub-Product| Predict the related sub product of a complaint | N/A |
| Task | Label Name | Description | SOTA |
| ----------- | ----------- |----------- | ----------- |
| Text Classification | Tags | Predict whether a complaint has been made by someone elderly or a service person| N/A |
### Languages
English
## Dataset Structure
### Data Instances
This dataset is a point in time extract of the database, the database increases in size every day
An example of 'train' looks as follows.
```
{
"Complaint ID": "4511031",
"Product": "Credit reporting, credit repair services, or other personal consumer reports",
"Sub Issue": "Credit inquiries on your report that you don't recognize",
"Consumer Disputed": "N/A",
"Sub Product": "Credit reporting",
"State": "TX",
"Tags": "Older American, Servicemember",
"Company Public Response": "",
"Zip Code": "75202",
"Issue": "Improper use of your report",
"Submitted via": "Web",
"Company Response To Consumer": "Closed with explanation",
"Complaint Text": "I am XXXX XXXX and I am submitting this complaint myself and there is no third party involved. Despite the multiple previous written requests, the unverified inquiries listed below still remain on my credit report in violation of Federal Law. The Equifax Credit Bureau failed to comply with Fair Credit Reporting Act, XXXX XXXX sections XXXX within the time set forth by law and continued reporting of erroneous information which now, given all my attempts to address it directly with the creditor, as willful negligence and non-compliance with federal statutes. PLEASE REMOVE THE FOLLOWING INQUIRIES COMPLETELY FROM MY CREDIT REPORT : XXXX CARD-Date of inquiry XX/XX/XXXX XXXX CARD-Date of inquiry XX/XX/XXXX",
"Date Received": "07-02-2021",
"Company": "EQUIFAX, INC.",
"Consumer Consent Provided": "Consent not provided",
"Timely Response": "Yes",
"Date Sent To Company": "2021-07-02"
}
```
### Data Fields
| Field | name | Description | Data Type |
| ----------- | ----------- |----------- | ----------- |
| Date received | The date the CFPB received the complaint | date & time | |
| Product | The type of product the consumer identified in the complaint | plain text | This field is a categorical variable. |
| Sub-product | The type of sub-product the consumer identified in the complaint | plain text | This field is a categorical variable. Not all Products have Sub-products. |
| Issue | The issue the consumer identified in the complaint | plain text | This field is a categorical variable. Possible values are dependent on Product. |
| Sub-issue | The sub-issue the consumer identified in the complaint | plain text | This field is a categorical variable. Possible values are dependent on product and issue. Not all Issues have corresponding Sub-issues. |
| Consumer complaint narrative | Consumer complaint narrative is the consumer-submitted description of "what happened" from the complaint. Consumers must opt-in to share their narrative. We will not publish the narrative unless the consumer consents, and consumers can opt-out at any time. The CFPB takes reasonable steps to scrub personal information from each complaint that could be used to identify the consumer. | plain text | Consumers' descriptions of what happened are included if consumers consent to publishing the description and after we take steps to remove personal information. |
| Company public response | The company's optional, public-facing response to a consumer's complaint. Companies can choose to select a response from a pre-set list of options that will be posted on the public database. For example, "Company believes complaint is the result of an isolated error." | plain text | Companies' public-facing responses to complaints are included if companies choose to publish one. Companies may select a public response from a set list of options as soon as they respond to the complaint, but no later than 180 days after the complaint was sent to the company for response. |
| Company | The complaint is about this company | plain text | This field is a categorical variable. |
| State | The state of the mailing address provided by the consumer | plain text | This field is a categorical variable. |
| ZIP code | The mailing ZIP code provided by the consumer | plain text | Mailing ZIP code provided by the consumer. This field may: i) include the first five digits of a ZIP code; ii) include the first three digits of a ZIP code (if the consumer consented to publication of their complaint narrative); or iii) be blank (if ZIP codes have been submitted with non-numeric values, if there are less than 20,000 people in a given ZIP code, or if the complaint has an address outside of the United States). For example, complaints where the submitter reports the age of the consumer as 62 years or older are tagged, ‘Older American.’ Complaints submitted by or on behalf of a servicemember or the spouse or dependent of a servicemember are tagged, ‘Servicemember.’ Servicemember includes anyone who is active duty, National Guard, or Reservist, as well as anyone who previously served and is a Veteran or retiree. |
| Tags | Data that supports easier searching and sorting of complaints submitted by or on behalf of consumers. | plain text | |
| Consumer consent provided? | Identifies whether the consumer opted in to publish their complaint narrative. We do not publish the narrative unless the consumer consents and consumers can opt-out at any time. | plain text | This field shows whether a consumer provided consent to publish their complaint narrative |
| Submitted via | How the complaint was submitted to the CFPB | plain text | This field is a categorical variable. |
| Date sent to company | The date the CFPB sent the complaint to the company | date & time | |
| Company response to consumer | This is how the company responded. For example, "Closed with explanation." | plain text | This field is a categorical variable. |
| Timely response? | Whether the company gave a timely response | plain text | yes/no |
| Consumer disputed? | Whether the consumer disputed the company’s response | plain text | YES/ NO/ N/A: The Bureau discontinued the consumer dispute option on April 24, 2017. |
| Complaint ID | The unique identification number for a complaint | number | |
### Data Splits
This dataset only contains a TRAIN set - this can be further split into TRAIN, TEST and VALIDATE subsets with the datasets library
## Dataset Creation
### Curation Rationale
Open sourcing customer complaints
### Source Data
https://cfpb.github.io/api/ccdb/
#### Initial Data Collection and Normalization
This database is maintained by the Consumer Financial Protection Bureau
#### Who are the source language producers?
English
### Annotations
#### Annotation process
User submitted to the CFPB
#### Who are the annotators?
N/A
### Personal and Sensitive Information
All PII data has been anonymised
## Considerations for Using the Data
### Social Impact of Dataset
N/A
### Discussion of Biases
This database is not a statistical sample of consumers’ experiences in the marketplace. Complaints are not necessarily representative of all consumers’ experiences and complaints do not constitute “information” for purposes of the Information Quality Act .
Complaint volume should be considered in the context of company size and/or market share. For example, companies with more customers may have more complaints than companies with fewer customers. We encourage you to pair complaint data with public and private data sets for additional context.
The Bureau publishes the consumer’s narrative description of his or her experience if the consumer opts to share it publicly and after the Bureau takes steps to remove personal information. We don’t verify all the allegations in complaint narratives. Unproven allegations in consumer narratives should be regarded as opinion, not fact. We do not adopt the views expressed and make no representation that consumers’ allegations are accurate, clear, complete, or unbiased in substance or presentation. Users should consider what conclusions may be fairly drawn from complaints alone.
### Other Known Limitations
N/A
## Additional Information
### Dataset Curators
https://cfpb.github.io/api/ccdb/
### Licensing Information
Creative Commons Zero v1.0 Universal
### Citation Information
N/A
### Contributions
Thanks to [@kayvane1](https://github.com/kayvane1) for adding this dataset and to the [Consumer Financial Protection Bureau](https://cfpb.github.io/) for publishing it. |
false |
# Dataset Card for ConvQuestions
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [ConvQuestions page](https://convex.mpi-inf.mpg.de)
- **Repository:** [GitHub](https://github.com/PhilippChr/CONVEX)
- **Paper:** [Look before you hop: Conversational question answering over knowledge graphs using judicious context expansion](https://arxiv.org/abs/1910.03262)
- **Leaderboard:** [ConvQuestions leaderboard](https://convex.mpi-inf.mpg.de)
- **Point of Contact:** [Philipp Christmann](mailto:pchristm@mpi-inf.mpg.de)
### Dataset Summary
ConvQuestions is the first realistic benchmark for conversational question answering over
knowledge graphs. It contains 11,200 conversations which can be evaluated over Wikidata.
They are compiled from the inputs of 70 Master crowdworkers on Amazon Mechanical Turk,
with conversations from five domains: Books, Movies, Soccer, Music, and TV Series.
The questions feature a variety of complex question phenomena like comparisons, aggregations,
compositionality, and temporal reasoning. Answers are grounded in Wikidata entities to enable
fair comparison across diverse methods. The data gathering setup was kept as natural as
possible, with the annotators selecting entities of their choice from each of the five domains,
and formulating the entire conversation in one session. All questions in a conversation are
from the same Turker, who also provided gold answers to the questions. For suitability to knowledge
graphs, questions were constrained to be objective or factoid in nature, but no other restrictive
guidelines were set. A notable property of ConvQuestions is that several questions are not
answerable by Wikidata alone (as of September 2019), but the required facts can, for example,
be found in the open Web or in Wikipedia. For details, please refer to the CIKM 2019 full paper
(https://dl.acm.org/citation.cfm?id=3358016).
### Supported Tasks and Leaderboards
[Needs More Information]
### Languages
en
## Dataset Structure
### Data Instances
An example of 'train' looks as follows.
```
{
'domain': 'music',
'seed_entity': 'https://www.wikidata.org/wiki/Q223495',
'seed_entity_text': 'The Carpenters',
'questions': [
'When did The Carpenters sign with A&M Records?',
'What song was their first hit?',
'When did Karen die?',
'Karen had what eating problem?',
'and how did she die?'
],
'answers': [
[
'1969'
],
[
'https://www.wikidata.org/wiki/Q928282'
],
[
'1983'
],
[
'https://www.wikidata.org/wiki/Q131749'
],
[
'https://www.wikidata.org/wiki/Q181754'
]
],
'answer_texts': [
'1969',
'(They Long to Be) Close to You',
'1983',
'anorexia nervosa',
'heart failure'
]
}
```
### Data Fields
- `domain`: a `string` feature. Any of: ['books', 'movies', 'music', 'soccer', 'tv_series']
- `seed_entity`: a `string` feature. Wikidata ID of the topic entity.
- `seed_entity_text`: a `string` feature. Surface form of the topic entity.
- `questions`: a `list` of `string` features. List of questions (initial question and follow-up questions).
- `answers`: a `list` of `lists` of `string` features. List of answers, given as Wikidata IDs or literals (e.g. timestamps or names).
- `answer_texts`: a `list` of `string` features. List of surface forms of the answers.
### Data Splits
|train|validation|tests|
|----:|---------:|----:|
| 6720| 2240| 2240|
## Dataset Creation
### Curation Rationale
[Needs More Information]
### Source Data
#### Initial Data Collection and Normalization
[Needs More Information]
#### Who are the source language producers?
[Needs More Information]
### Annotations
#### Annotation process
With insights from a meticulous in-house pilot study with ten students over two weeks, the authors posed the conversation generation task on Amazon Mechanical Turk (AMT) in the most natural setup: Each crowdworker was asked to build a conversation by asking five sequential questions starting from any seed entity of his/her choice, as this is an intuitive mental model that humans may have when satisfying their real information needs via their search assistants.
#### Who are the annotators?
Local students (Saarland Informatics Campus) and AMT Master Workers.
### Personal and Sensitive Information
[Needs More Information]
## Considerations for Using the Data
### Social Impact of Dataset
[Needs More Information]
### Discussion of Biases
[Needs More Information]
### Other Known Limitations
[Needs More Information]
## Additional Information
### Dataset Curators
[Needs More Information]
### Licensing Information
The ConvQuestions benchmark is licensed under a Creative Commons Attribution 4.0 International License.
### Citation Information
```
@InProceedings{christmann2019look,
title={Look before you hop: Conversational question answering over knowledge graphs using judicious context expansion},
author={Christmann, Philipp and Saha Roy, Rishiraj and Abujabal, Abdalghani and Singh, Jyotsna and Weikum, Gerhard},
booktitle={Proceedings of the 28th ACM International Conference on Information and Knowledge Management},
pages={729--738},
year={2019}
}
```
### Contributions
Thanks to [@PhilippChr](https://github.com/PhilippChr) for adding this dataset. |
true |
# Dataset Card for ReDial (Recommendation Dialogues)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [ReDial Dataset](https://redialdata.github.io/website/)
- **Repository:** [ReDialData](https://github.com/ReDialData/website/tree/data)
- **Paper:** [Towards Deep Conversational Recommendations](https://proceedings.neurips.cc/paper/2018/file/800de15c79c8d840f4e78d3af937d4d4-Paper.pdf)
- **Point of Contact:** [ReDial Google Group](https://groups.google.com/forum/embed/?place=forum/redial-dataset&showpopout=true#!forum/redial-dataset)
### Dataset Summary
ReDial (Recommendation Dialogues) is an annotated dataset of dialogues, where users
recommend movies to each other. The dataset was collected by a team of researchers working at
Polytechnique Montréal, MILA – Quebec AI Institute, Microsoft Research Montréal, HEC Montreal, and Element AI.
The dataset allows research at the intersection of goal-directed dialogue systems
(such as restaurant recommendation) and free-form (also called “chit-chat”) dialogue systems.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The text in the dataset is in English.
## Dataset Structure
### Data Instances
JSON-formatted example of a typical instance in the dataset.
```
{
"movieMentions":{
"203371":"Final Fantasy: The Spirits Within (2001)",
"84779":"The Triplets of Belleville (2003)",
"122159":"Mary and Max (2009)",
"151313":"A Scanner Darkly (2006)",
"191602":"Waking Life (2001)",
"165710":"The Boss Baby (2017)"
},
"respondentQuestions":{
"203371":{
"suggested":1,
"seen":0,
"liked":1
},
"84779":{
"suggested":0,
"seen":1,
"liked":1
},
"122159":{
"suggested":0,
"seen":1,
"liked":1
},
"151313":{
"suggested":0,
"seen":1,
"liked":1
},
"191602":{
"suggested":0,
"seen":1,
"liked":1
},
"165710":{
"suggested":1,
"seen":0,
"liked":1
}
},
"messages":[
{
"timeOffset":0,
"text":"Hi there, how are you? I'm looking for movie recommendations",
"senderWorkerId":0,
"messageId":1021
},
{
"timeOffset":15,
"text":"I am doing okay. What kind of movies do you like?",
"senderWorkerId":1,
"messageId":1022
},
{
"timeOffset":66,
"text":"I like animations like @84779 and @191602",
"senderWorkerId":0,
"messageId":1023
},
{
"timeOffset":86,
"text":"I also enjoy @122159",
"senderWorkerId":0,
"messageId":1024
},
{
"timeOffset":95,
"text":"Anything artistic",
"senderWorkerId":0,
"messageId":1025
},
{
"timeOffset":135,
"text":"You might like @165710 that was a good movie.",
"senderWorkerId":1,
"messageId":1026
},
{
"timeOffset":151,
"text":"What's it about?",
"senderWorkerId":0,
"messageId":1027
},
{
"timeOffset":207,
"text":"It has Alec Baldwin it is about a baby that works for a company and gets adopted it is very funny",
"senderWorkerId":1,
"messageId":1028
},
{
"timeOffset":238,
"text":"That seems like a nice comedy",
"senderWorkerId":0,
"messageId":1029
},
{
"timeOffset":272,
"text":"Do you have any animated recommendations that are a bit more dramatic? Like @151313 for example",
"senderWorkerId":0,
"messageId":1030
},
{
"timeOffset":327,
"text":"I like comedies but I prefer films with a little more depth",
"senderWorkerId":0,
"messageId":1031
},
{
"timeOffset":467,
"text":"That is a tough one but I will remember something",
"senderWorkerId":1,
"messageId":1032
},
{
"timeOffset":509,
"text":"@203371 was a good one",
"senderWorkerId":1,
"messageId":1033
},
{
"timeOffset":564,
"text":"Ooh that seems cool! Thanks for the input. I'm ready to submit if you are.",
"senderWorkerId":0,
"messageId":1034
},
{
"timeOffset":571,
"text":"It is animated, sci fi, and has action",
"senderWorkerId":1,
"messageId":1035
},
{
"timeOffset":579,
"text":"Glad I could help",
"senderWorkerId":1,
"messageId":1036
},
{
"timeOffset":581,
"text":"Nice",
"senderWorkerId":0,
"messageId":1037
},
{
"timeOffset":591,
"text":"Take care, cheers!",
"senderWorkerId":0,
"messageId":1038
},
{
"timeOffset":608,
"text":"bye",
"senderWorkerId":1,
"messageId":1039
}
],
"conversationId":"391",
"respondentWorkerId":1,
"initiatorWorkerId":0,
"initiatorQuestions":{
"203371":{
"suggested":1,
"seen":0,
"liked":1
},
"84779":{
"suggested":0,
"seen":1,
"liked":1
},
"122159":{
"suggested":0,
"seen":1,
"liked":1
},
"151313":{
"suggested":0,
"seen":1,
"liked":1
},
"191602":{
"suggested":0,
"seen":1,
"liked":1
},
"165710":{
"suggested":1,
"seen":0,
"liked":1
}
}
}
```
### Data Fields
The dataset is published in the “jsonl” format, i.e., as a text file where each line corresponds to a Dialogue given as a valid JSON document.
A Dialogue contains these fields:
**conversationId:** an integer
**initiatorWorkerId:** an integer identifying to the worker initiating the conversation (the recommendation seeker)
**respondentWorkerId:** an integer identifying the worker responding to the initiator (the recommender)
**messages:** a list of Message objects
**movieMentions:** a dict mapping movie IDs mentioned in this dialogue to movie names
**initiatorQuestions:** a dictionary mapping movie IDs to the labels supplied by the initiator. Each label is a bool corresponding to whether the initiator has said he saw the movie, liked it, or suggested it.
**respondentQuestions:** a dictionary mapping movie IDs to the labels supplied by the respondent. Each label is a bool corresponding to whether the initiator has said he saw the movie, liked it, or suggested it.
Each Message contains these fields:
**messageId:** a unique ID for this message
**text:** a string with the actual message. The string may contain a token starting with @ followed by an integer. This is a movie ID which can be looked up in the movieMentions field of the Dialogue object.
**timeOffset:** time since start of dialogue in seconds
**senderWorkerId:** the ID of the worker sending the message, either initiatorWorkerId or respondentWorkerId.
The labels in initiatorQuestions and respondentQuestions have the following meaning:
*suggested:* 0 if it was mentioned by the seeker, 1 if it was a suggestion from the recommender
*seen:* 0 if the seeker has not seen the movie, 1 if they have seen it, 2 if they did not say
*liked:* 0 if the seeker did not like the movie, 1 if they liked it, 2 if they did not say
### Data Splits
The dataset contains a total of 11348 dialogues, 10006 for training and model selection, and 1342 for testing.
## Dataset Creation
### Curation Rationale
The dataset allows research at the intersection of goal-directed dialogue systems (such as restaurant recommendation) and free-form (also called “chit-chat”) dialogue systems.
In the dataset, users talk about which movies they like and which ones they do not like, which ones they have seen or not etc., and labels which we ensured agree between the two participants. This allows to research how sentiment is expressed in dialogues, which differs a lot from e.g. review websites.
The dialogues and the movies they mention form a curious bi-partite graph structure, which is related to how users talk about the movie (e.g. genre information).
Ignoring label information, this dataset can also be viewed as a limited domain chit-chat dialogue dataset.
### Source Data
#### Initial Data Collection and Normalization
Describe the data collection process. Describe any criteria for data selection or filtering. List any key words or search terms used. If possible, include runtime information for the collection process.
If data was collected from other pre-existing datasets, link to source here and to their [Hugging Face version](https://huggingface.co/datasets/dataset_name).
If the data was modified or normalized after being collected (e.g. if the data is word-tokenized), describe the process and the tools used.
#### Who are the source language producers?
Here we formalize the setup of a conversation involving recommendations for the purposes of data collection. To provide some additional structure to our data (and models) we define one person in the dialogue as the recommendation seeker and the other as the recommender.
To obtain data in this form, we developed an interface and pairing mechanism mediated by Amazon Mechanical Turk (AMT).
We pair up AMT workers and give each of them a role. The movie seeker has to explain what kind of movie he/she likes, and asks for movie suggestions. The recommender tries to understand the seeker’s movie tastes, and recommends movies. All exchanges of information and recommendations are made using natural language.
We add additional instructions to improve the data quality and guide the workers to dialogue the way we expect them to. Thus we ask to use formal language and that conversations contain roughly ten messages minimum. We also require that at least four different movies are mentioned in every conversation. Finally, we also ask to converse only about movies, and notably not to mention Mechanical Turk or the task itself.
In addition, we ask that every movie mention is tagged using the ‘@’ symbol. When workers type ‘@’, the following characters are used to find matching movie names, and workers can choose a movie from that list. This allows us to detect exactly what movies are mentioned and when. We gathered entities from DBpedia that were of type http://dbpedia.org/ontology/Film to obtain a list of movies, but also allow workers to add their own movies to the list if it is not present already. We obtained the release dates from the movie titles (e.g. http://dbpedia.org/page/American_Beauty_(1999_film), or, if the movie title does not contain that information, from an additional SPARQL request. Note that the year or release date of a movie can be essential to differentiate movies with the same name, but released at different dates.
We will refer to these additional labels as movie dialogue forms. Both workers have to answer these forms even though it really concerns the seeker’s movie tastes. Ideally, the two participants would give the same answer to every form, but it is possible that their answers do not coincide (because of carelessness, or dialogue ambiguity). The movie dialogue forms therefore allow us to evaluate sub-components of an overall neural dialogue system more systematically, for example one can train and evaluate a sentiment analysis model directly using these labels. %which could produce a reward for the dialogue agent.
In each conversation, the number of movies mentioned varies, so we have different numbers of movie dialogue form answers for each conversation. The distribution of the different classes of the movie dialogue form is shown in Table 1a. The liked/disliked/did not say label is highly imbalanced. This is standard for recommendation data, since people are naturally more likely to talk about movies that they like, and the recommender’s objective is to recommend movies that the seeker is likely to like.
### Annotations
#### Annotation process
Mentioned in above sub-section.
#### Who are the annotators?
For the AMT HIT we collect data in English and chose to restrict the data collection to countries where English is the main language. The fact that we pair workers together slows down the data collection since we ask that at least two persons are online at the same time to do the task, so a good amount of workers is required to make the collection possible. Meanwhile, the task is quite demanding, and we have to select qualified workers. HIT reward and qualification requirement were decisive to get good conversation quality while still ensuring that people could get paired together. We launched preliminary HITs to find a compromise and finally set the reward to $0.50 per person for each completed conversation (so each conversation costs us $1, plus taxes), and ask that workers meet the following requirements: (1)~Approval percentage greater than 95, (2)~Number of approved HITs greater than 1000, (3)~Their location must be in United States, Canada, United Kingdom, Australia, or New Zealand.
### Personal and Sensitive Information
Workers had to confirm a consent form before every task that explains what the data is being collected for and how it is going to be used.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The dataset collection was funded by Google, IBM, and NSERC, with editorial support from Microsoft Research.
### Licensing Information
The data is published under the CC BY 4.0 License.
### Citation Information
```
@inproceedings{li2018conversational,
title={Towards Deep Conversational Recommendations},
author={Li, Raymond and Kahou, Samira Ebrahimi and Schulz, Hannes and Michalski, Vincent and Charlin, Laurent and Pal, Chris},
booktitle={Advances in Neural Information Processing Systems 31 (NIPS 2018)},
year={2018}
}
```
### Contributions
Thanks to [@bhavitvyamalik](https://github.com/bhavitvyamalik) for adding this dataset. |
false |
# Dataset Card for AMTTL
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Github](https://github.com/adapt-sjtu/AMTTL/tree/master/medical_data)
- **Repository:** [Github](https://github.com/adapt-sjtu/AMTTL/tree/master/medical_data)
- **Paper:** [Aclweb](http://aclweb.org/anthology/C18-1307)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```bibtex
@inproceedings{xing2018adaptive,
title={Adaptive multi-task transfer learning for Chinese word segmentation in medical text},
author={Xing, Junjie and Zhu, Kenny and Zhang, Shaodian},
booktitle={Proceedings of the 27th International Conference on Computational Linguistics},
pages={3619--3630},
year={2018}
}
```
### Contributions
Thanks to [@JetRunner](https://github.com/JetRunner) for adding this dataset. |
false |
# Dataset Card for An Atlas of Machine Commonsense for If-Then Reasoning - Atomic Common Sense Dataset
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:**
https://homes.cs.washington.edu/~msap/atomic/
- **Repository:**
https://homes.cs.washington.edu/~msap/atomic/
- **Paper:**
Maarten Sap, Ronan LeBras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith & Yejin Choi (2019). ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. AAAI
### Dataset Summary
This dataset provides the template sentences and
relationships defined in the ATOMIC common sense dataset. There are
three splits - train, test, and dev.
From the authors.
Disclaimer/Content warning: the events in atomic have been
automatically extracted from blogs, stories and books written at
various times. The events might depict violent or problematic actions,
which we left in the corpus for the sake of learning the (probably
negative but still important) commonsense implications associated with
the events. We removed a small set of truly out-dated events, but
might have missed some so please email us (msap@cs.washington.edu) if
you have any concerns.
For more information, see: https://homes.cs.washington.edu/~msap/atomic/
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
en
## Dataset Structure
### Data Instances
Here is one example from the atomic dataset:
``
{'event': "PersonX uses PersonX's ___ to obtain", 'oEffect': [], 'oReact': ['annoyed', 'angry', 'worried'], 'oWant': [], 'prefix': ['uses', 'obtain'], 'split': 'trn', 'xAttr': [], 'xEffect': [], 'xIntent': ['to have an advantage', 'to fulfill a desire', 'to get out of trouble'], 'xNeed': [], 'xReact': ['pleased', 'smug', 'excited'], 'xWant': []}
``
### Data Fields
Notes from the authors:
* event: just a string representation of the event.
* oEffect,oReact,oWant,xAttr,xEffect,xIntent,xNeed,xReact,xWant: annotations for each of the dimensions, stored in a json-dumped string.
Note: "none" means the worker explicitly responded with the empty response, whereas [] means the worker did not annotate this dimension.
* prefix: json-dumped string that represents the prefix of content words (used to make a better trn/dev/tst split).
* split: string rep of which split the event belongs to.
### Data Splits
The atomic dataset has three splits: test, train and dev of the form:
## Dataset Creation
### Curation Rationale
This dataset was gathered and created over to assist in common sense reasoning.
### Source Data
#### Initial Data Collection and Normalization
See the reaserch paper and website for more detail. The dataset was
created by the University of Washington using crowd sourced data
#### Who are the source language producers?
The Atomic authors and crowd source.
### Annotations
#### Annotation process
Human annotations directed by forms.
#### Who are the annotators?
Human annotations.
### Personal and Sensitive Information
Unkown, but likely none.
## Considerations for Using the Data
### Social Impact of Dataset
The goal for the work is to help machines understand common sense.
### Discussion of Biases
Since the data is human annotators, there is likely to be baised. From the authors:
Disclaimer/Content warning: the events in atomic have been automatically extracted from blogs, stories and books written at various times. The events might depict violent or problematic actions, which we left in the corpus for the sake of learning the (probably negative but still important) commonsense implications associated with the events. We removed a small set of truly out-dated events, but might have missed some so please email us (msap@cs.washington.edu) if you have any concerns.
### Other Known Limitations
While there are many relationships, the data is quite sparse. Also, each item of the dataset could be expanded into multiple sentences along the vsrious dimensions, oEffect, oRect, etc.
For example, given event: "PersonX uses PersonX's ___ to obtain" and dimension oReact: "annoyed", this could be transformed into an entry:
"PersonX uses PersonX's ___ to obtain => PersonY is annoyed"
## Additional Information
### Dataset Curators
The authors of Aotmic at The University of Washington
### Licensing Information
The Creative Commons Attribution 4.0 International License. https://creativecommons.org/licenses/by/4.0/
### Citation Information
@article{Sap2019ATOMICAA,
title={ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning},
author={Maarten Sap and Ronan Le Bras and Emily Allaway and Chandra Bhagavatula and Nicholas Lourie and Hannah Rashkin and Brendan Roof and Noah A. Smith and Yejin Choi},
journal={ArXiv},
year={2019},
volume={abs/1811.00146}
}
### Contributions
Thanks to [@ontocord](https://github.com/ontocord) for adding this dataset. |
false |
# Dataset Card for CAPES
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:**[Parallel corpus of theses and dissertation abstracts in Portuguese and English from CAPES](https://sites.google.com/view/felipe-soares/datasets#h.p_kxOR6EhHm2a6)
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
A parallel corpus of theses and dissertations abstracts in English and Portuguese were collected from the
CAPES website (Coordenação de Aperfeiçoamento de Pessoal de Nível Superior) - Brazil.
The corpus is sentence aligned for all language pairs. Approximately 240,000 documents were
collected and aligned using the Hunalign algorithm.
### Supported Tasks and Leaderboards
The underlying task is machine translation.
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```
@inproceedings{soares2018parallel,
title={A Parallel Corpus of Theses and Dissertations Abstracts},
author={Soares, Felipe and Yamashita, Gabrielli Harumi and Anzanello, Michel Jose},
booktitle={International Conference on Computational Processing of the Portuguese Language},
pages={345--352},
year={2018},
organization={Springer}
}
```
### Contributions
Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset. |
false |
# Dataset Card for "event2Mind"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [https://uwnlp.github.io/event2mind/](https://uwnlp.github.io/event2mind/)
- **Repository:** https://github.com/uwnlp/event2mind
- **Paper:** [Event2Mind: Commonsense Inference on Events, Intents, and Reactions](https://arxiv.org/abs/1805.06939)
- **Point of Contact:** [Hannah Rashkin](mailto:hrashkin@cs.washington.edu), [Maarten Sap](mailto:msap@cs.washington.edu)
- **Size of downloaded dataset files:** 1.30 MB
- **Size of the generated dataset:** 7.24 MB
- **Total amount of disk used:** 8.54 MB
### Dataset Summary
In Event2Mind, we explore the task of understanding stereotypical intents and reactions to events. Through crowdsourcing, we create a large corpus with 25,000 events and free-form descriptions of their intents and reactions, both of the event's subject and (potentially implied) other participants.
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 1.30 MB
- **Size of the generated dataset:** 7.24 MB
- **Total amount of disk used:** 8.54 MB
An example of 'validation' looks as follows.
```
{
"Event": "It shrinks in the wash",
"Osent": "1",
"Otheremotion": "[\"upset\", \"angry\"]",
"Source": "it_events",
"Xemotion": "[\"none\"]",
"Xintent": "[\"none\"]",
"Xsent": ""
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `Source`: a `string` feature.
- `Event`: a `string` feature.
- `Xintent`: a `string` feature.
- `Xemotion`: a `string` feature.
- `Otheremotion`: a `string` feature.
- `Xsent`: a `string` feature.
- `Osent`: a `string` feature.
### Data Splits
| name |train|validation|test|
|-------|----:|---------:|---:|
|default|46472| 5401|5221|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
```
@inproceedings{rashkin-etal-2018-event2mind,
title = "{E}vent2{M}ind: Commonsense Inference on Events, Intents, and Reactions",
author = "Rashkin, Hannah and
Sap, Maarten and
Allaway, Emily and
Smith, Noah A. and
Choi, Yejin",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1043",
doi = "10.18653/v1/P18-1043",
pages = "463--473",
}
```
### Contributions
Thanks to [@thomwolf](https://github.com/thomwolf), [@patrickvonplaten](https://github.com/patrickvonplaten), [@lewtun](https://github.com/lewtun) for adding this dataset. |
true |
# Dataset Card for Interpress Turkish News Category Dataset (270K)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Interpress](https://www.interpress.com/)
- **Point of Contact:** [Yavuz Komecoglu](mailto:yavuz.komecoglu@kodiks.com)
### Dataset Summary
Turkish News Category Dataset (270K) is a Turkish news data set consisting of 273601 news in 17 categories, compiled from printed media and news websites between 2010 and 2017 by the Interpress (https://www.interpress.com/) media monitoring company.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is based on Turkish.
## Dataset Structure
### Data Instances
A text classification dataset with 17 different news category.
```
{'id': 301365715,
'title': 'BİR SİHİRBAZ',
'content': 'NİANG, TAKIM ARKADAŞI FERNANDES E ÖVGÜLER YAĞDIRDI FUTBOL OYNARKEN EĞLENİYORUM YÜZDE 701E OYNUYORUM LİDERLE ARAMIZDA SADECE 5 PUAN VAR, ŞAMPİYONLUK ŞANSIMIZ YÜKSEK 4 j Fernandes le birlikte oynamayı seviyorum, adam adeta sihirbaz gibi J Frank Ribery, futbol hayatımda oynamaktan en çok zevk aldığım isim ı Abartılacak bir ] sonuç almadık ı .BAHÇE derbisinde Kartal ın ilk golünü atan, üçüncü golün de asistini yapan Mamadou Niang, TRT Spor da Futbol Keyfi programında özel açıklamalar yaptı. Senegalli forvet şampiyonluk şanslarının yüksek olduğunu dile getirirken, Portekizli yıldız Fernandes için Onunla oynamayı seviyorum, adeta bir sihirbaz gibi ifadesini kullandı. Frank Ribery nin futbol hayatında oynamaktan en çok zevk aldığım isim olduğunu ifade eden Niang, Moussa Sow ve Burak Yılmaz ın da Süper Lig deki en iyi forvetler olduğunu, ikisinin de tarzını beğendiğini söyledi. Senegalli yıldız şampiyonluk şansları için, Çok yüksek. Çünkü liderle aramızda 5 puan fark var ve bunu kapatacak güçteyiz yorumunu yaptı. NİANG şöyle devam etti: t.f En zorlandığım stoper İbrahim Toraman dır. Neyse ki şu an onunla takım arkadaşıyım. Almeida sakatlıktan döndükten sonra nasıl bir diziliş olur bilemiyorum. Onunla beraber oynayabiliriz, Holosko ile de oynayabiliriz. Türkiye, .. O NİANG, şu anda gerçek performansının yüzde 70 i ile oynadığını söyledi. İyi bir seviyede olmadığını kabul ettiğini belirten Senegalli yıldız, Sahada savaşan oyuncularla birlikte olmayı seviyorum. Bizim takımda Olcay ve Oğuzhan gibi bu yapıda isimler var. Tabii ki şansın da önemi var diye konuştu. zor bir lig. Eskiden arkadaşlarıma Türkiye Ligi nin iyi olduğunu söylediğimde inanmazlardı. Şimdi Didier Drogba, VVesley Sneijder, Sovvgibi oyuncuların burada olması ilgiyi artırdı. Futbol oynarken eğleniyorum ve şu an emekli olmayı düşünmüyorum. Açılış törenine, yönetici Metin Albayrak ile birlikte futbolcular Necip Uysal, McGregor ve Mehmet Akyüz de katıldı. BEŞİKTAŞLI Necip Uysal, +f başkan Fikret Orman gibi F.Bahçe galibiyetinin abartılmaması gerektiğini söyledi. Pazar günü İnönü Stadı nda güzel bir zafer elde ettiklerini vurgulayan genç yıldız, 10 karşılaşmaya daha çıkacağız. Her maçımız final, ayaklarımızın yere sağlam basması gerekiyor. Maçlara tek tek bakacağız ve hepsini kazanmak için oynayacağız yorumunu yaptı. Trabzon un her zaman zor deplasman olduğunu ifade eden Necip, Kolay olmayacağını biliyoruz ama şampiyonluk şansımızın sürmesi için kesinlikle üç puanla dönmeye mecburuz dedi. sflPa',
'category': 12,
'categorycode': 12,
'publishdatetime': '2013-03-07T00:00:00Z'}
```
### Data Fields
- `id`
- `title`
- `content`
- `category`
- `categorycode`
- `publishdatetime`
### Data Splits
The data is split into a training and testing. The split is organized as the following
| | train | test |
|------------|--------:|-------:|
| data split | 218,880 | 54,721 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
Downloaded over 270,000 news from the printed media and news websites between 2010 and 2017 by the Interpress (https://www.interpress.com/) media monitoring company. This data collection compiled from print media and internet news is presented in its raw form. For this reason, it is appropriate to use it with careful pre-processing steps regarding various OCR errors and typos.
#### Who are the source language producers?
Turkish printed news sources and online news sites.
### Annotations
The dataset does not contain any additional annotations.
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
https://www.interpress.com/
### Contributions
Thanks to [@basakbuluz](https://github.com/basakbuluz) for adding this dataset. |
true |
# Dataset Card for OffensEval-TR 2020
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [offensive-turkish](https://coltekin.github.io/offensive-turkish/)
- **Paper:** [A Corpus of Turkish Offensive Language on Social Media](https://coltekin.github.io/offensive-turkish/troff.pdf)
- **Point of Contact:** [Çağrı Çöltekin](ccoltekin@sfs.uni-tuebingen.de)
### Dataset Summary
The file offenseval-tr-training-v1.tsv contains 31,756 annotated tweets.
The file offenseval-annotation.txt contains a short summary of the annotation guidelines.
Twitter user mentions were substituted by @USER and URLs have been substitute by URL.
Each instance contains up to 1 labels corresponding to one of the following sub-task:
- Sub-task A: Offensive language identification;
### Supported Tasks and Leaderboards
The dataset was published on this [paper](https://coltekin.github.io/offensive-turkish/troff.pdf).
### Languages
The dataset is based on Turkish.
## Dataset Structure
### Data Instances
A binary dataset with with (NOT) Not Offensive and (OFF) Offensive tweets.
### Data Fields
Instances are included in TSV format as follows:
ID INSTANCE SUBA
The column names in the file are the following:
id tweet subtask_a
The labels used in the annotation are listed below.
#### Task and Labels
(A) Sub-task A: Offensive language identification
- (NOT) Not Offensive - This post does not contain offense or profanity.
- (OFF) Offensive - This post contains offensive language or a targeted (veiled or direct) offense
In our annotation, we label a post as offensive (OFF) if it contains any form of non-acceptable language (profanity) or a targeted offense, which can be veiled or direct.
### Data Splits
| train | test |
|------:|-----:|
| 31756 | 3528 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
From tweeter.
### Annotations
[More Information Needed]
#### Annotation process
We describe the labels above in a “flat” manner. However, the annotation process we follow is hierarchical. The following QA pairs give a more flowchart-like procedure to follow
1. Is the tweet in Turkish and understandable?
* No: mark tweet X for exclusion, and go to next tweet
* Yes: continue to step 2
2. Is the tweet include offensive/inappropriate language?
* No: mark the tweet non go to step 4
* Yes: continue to step 3
3. Is the offense in the tweet targeted?
* No: mark the tweet prof go to step 4
* Yes: chose one (or more) of grp, ind, *oth based on the definitions above. Please try to limit the number of labels unless it is clear that the tweet includes offense against multiple categories.
4. Was the labeling decision difficult (precise answer needs more context, tweets includes irony, or for another reason)?
* No: go to next tweet
* Yes: add the label X, go to next tweet
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
The annotations are distributed under the terms of [Creative Commons Attribution License (CC-BY)](https://creativecommons.org/licenses/by/2.0/). Please cite the following paper, if you use this resource.
### Citation Information
```
@inproceedings{coltekin2020lrec,
author = {\c{C}\"{o}ltekin, \c{C}a\u{g}r{\i}},
year = {2020},
title = {A Corpus of Turkish Offensive Language on Social Media},
booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference},
pages = {6174--6184},
address = {Marseille, France},
url = {https://www.aclweb.org/anthology/2020.lrec-1.758},
}
```
### Contributions
Thanks to [@yavuzKomecoglu](https://github.com/yavuzKomecoglu) for adding this dataset. |
true |
# Dataset Card for `xnli_bn`
## Table of Contents
- [Dataset Card for `xnli_bn`](#dataset-card-for-xnli_bn)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Usage](#usage)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Initial Data Collection and Normalization](#initial-data-collection-and-normalization)
- [Who are the source language producers?](#who-are-the-source-language-producers)
- [Annotations](#annotations)
- [Annotation process](#annotation-process)
- [Who are the annotators?](#who-are-the-annotators)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Repository:** [https://github.com/csebuetnlp/banglabert](https://github.com/csebuetnlp/banglabert)
- **Paper:** [**"BanglaBERT: Combating Embedding Barrier in Multilingual Models for Low-Resource Language Understanding"**](https://arxiv.org/abs/2101.00204)
- **Point of Contact:** [Tahmid Hasan](mailto:tahmidhasan@cse.buet.ac.bd)
### Dataset Summary
This is a Natural Language Inference (NLI) dataset for Bengali, curated using the subset of
MNLI data used in XNLI and state-of-the-art English to Bengali translation model introduced **[here](https://aclanthology.org/2020.emnlp-main.207/).**
### Supported Tasks and Leaderboards
[More information needed](https://github.com/csebuetnlp/banglabert)
### Languages
* `Bengali`
### Usage
```python
from datasets import load_dataset
dataset = load_dataset("csebuetnlp/xnli_bn")
```
## Dataset Structure
### Data Instances
One example from the dataset is given below in JSON format.
```
{
"sentence1": "আসলে, আমি এমনকি এই বিষয়ে চিন্তাও করিনি, কিন্তু আমি এত হতাশ হয়ে পড়েছিলাম যে, শেষ পর্যন্ত আমি আবার তার সঙ্গে কথা বলতে শুরু করেছিলাম",
"sentence2": "আমি তার সাথে আবার কথা বলিনি।",
"label": "contradiction"
}
```
### Data Fields
The data fields are as follows:
- `sentence1`: a `string` feature indicating the premise.
- `sentence2`: a `string` feature indicating the hypothesis.
- `label`: a classification label, where possible values are `contradiction` (0), `entailment` (1), `neutral` (2) .
### Data Splits
| split |count |
|----------|--------|
|`train`| 381449 |
|`validation`| 2419 |
|`test`| 4895 |
## Dataset Creation
The dataset curation procedure was the same as the [XNLI](https://aclanthology.org/D18-1269/) dataset: we translated the [MultiNLI](https://aclanthology.org/N18-1101/) training data using the English to Bangla translation model introduced [here](https://aclanthology.org/2020.emnlp-main.207/). Due to the possibility of incursions of error during automatic translation, we used the [Language-Agnostic BERT Sentence Embeddings (LaBSE)](https://arxiv.org/abs/2007.01852) of the translations and original sentences to compute their similarity. All sentences below a similarity threshold of 0.70 were discarded.
### Curation Rationale
[More information needed](https://github.com/csebuetnlp/banglabert)
### Source Data
[XNLI](https://aclanthology.org/D18-1269/)
#### Initial Data Collection and Normalization
[More information needed](https://github.com/csebuetnlp/banglabert)
#### Who are the source language producers?
[More information needed](https://github.com/csebuetnlp/banglabert)
### Annotations
[More information needed](https://github.com/csebuetnlp/banglabert)
#### Annotation process
[More information needed](https://github.com/csebuetnlp/banglabert)
#### Who are the annotators?
[More information needed](https://github.com/csebuetnlp/banglabert)
### Personal and Sensitive Information
[More information needed](https://github.com/csebuetnlp/banglabert)
## Considerations for Using the Data
### Social Impact of Dataset
[More information needed](https://github.com/csebuetnlp/banglabert)
### Discussion of Biases
[More information needed](https://github.com/csebuetnlp/banglabert)
### Other Known Limitations
[More information needed](https://github.com/csebuetnlp/banglabert)
## Additional Information
### Dataset Curators
[More information needed](https://github.com/csebuetnlp/banglabert)
### Licensing Information
Contents of this repository are restricted to only non-commercial research purposes under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/). Copyright of the dataset contents belongs to the original copyright holders.
### Citation Information
If you use the dataset, please cite the following paper:
```
@misc{bhattacharjee2021banglabert,
title={BanglaBERT: Combating Embedding Barrier in Multilingual Models for Low-Resource Language Understanding},
author={Abhik Bhattacharjee and Tahmid Hasan and Kazi Samin and Md Saiful Islam and M. Sohel Rahman and Anindya Iqbal and Rifat Shahriyar},
year={2021},
eprint={2101.00204},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@abhik1505040](https://github.com/abhik1505040) and [@Tahmid](https://github.com/Tahmid04) for adding this dataset. |
true |
# Dataset Card for K-MHaS
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Sample Code
<a href="https://colab.research.google.com/drive/171KhS1_LVBtpAFd_kaT8lcrZmhcz5ehY?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="base"/></a>
## Dataset Description
- **Homepage:** [K-MHaS](https://github.com/adlnlp/K-MHaS)
- **Repository:** [Korean Multi-label Hate Speech Dataset](https://github.com/adlnlp/K-MHaS)
- **Paper:** [K-MHaS: A Multi-label Hate Speech Detection Dataset in Korean Online News Comment](https://arxiv.org/abs/2208.10684)
- **Point of Contact:** [Caren Han](caren.han@sydney.edu.au)
- **Sample code:** [Colab](https://colab.research.google.com/drive/171KhS1_LVBtpAFd_kaT8lcrZmhcz5ehY?usp=sharing)
### Dataset Summary
The Korean Multi-label Hate Speech Dataset, **K-MHaS**, consists of 109,692 utterances from Korean online news comments, labelled with 8 fine-grained hate speech classes (labels: `Politics`, `Origin`, `Physical`, `Age`, `Gender`, `Religion`, `Race`, `Profanity`) or `Not Hate Speech` class. Each utterance provides from a single to four labels that can handles Korean language patterns effectively. For more details, please refer to our paper about [**K-MHaS**](https://aclanthology.org/2022.coling-1.311), published at COLING 2022.
### Supported Tasks and Leaderboards
Hate Speech Detection
* `binary classification` (labels: `Hate Speech`, `Not Hate Speech`)
* `multi-label classification`: (labels: `Politics`, `Origin`, `Physical`, `Age`, `Gender`, `Religion`, `Race`, `Profanity`, `Not Hate Speech`)
For the multi-label classification, a `Hate Speech` class from the binary classification, is broken down into eight classes, associated with the hate speech category. In order to reflect the social and historical context, we select the eight hate speech classes. For example, the `Politics` class is chosen, due to a significant influence on the style of Korean hate speech.
### Languages
Korean
## Dataset Structure
### Data Instances
The dataset is provided with train/validation/test set in the txt format. Each instance is a news comment with a corresponding one or more hate speech classes (labels: `Politics`, `Origin`, `Physical`, `Age`, `Gender`, `Religion`, `Race`, `Profanity`) or `Not Hate Speech` class. The label numbers matching in both English and Korean is in the data fields section.
```python
{'text':'수꼴틀딱시키들이 다 디져야 나라가 똑바로 될것같다..답이 없는 종자들ㅠ'
'label': [2, 3, 4]
}
```
### Data Fields
* `text`: utterance from Korean online news comment.
* `label`: the label numbers matching with 8 fine-grained hate speech classes and `not hate speech` class are follows.
* `0`: `Origin`(`출신차별`) hate speech based on place of origin or identity;
* `1`: `Physical`(`외모차별`) hate speech based on physical appearance (e.g. body, face) or disability;
* `2`: `Politics`(`정치성향차별`) hate speech based on political stance;
* `3`: `Profanity`(`혐오욕설`) hate speech in the form of swearing, cursing, cussing, obscene words, or expletives; or an unspecified hate speech category;
* `4`: `Age`(`연령차별`) hate speech based on age;
* `5`: `Gender`(`성차별`) hate speech based on gender or sexual orientation (e.g. woman, homosexual);
* `6`: `Race`(`인종차별`) hate speech based on ethnicity;
* `7`: `Religion`(`종교차별`) hate speech based on religion;
* `8`: `Not Hate Speech`(`해당사항없음`).
### Data Splits
In our repository, we provide splitted datasets that have 78,977(train) / 8,776 (validation) / 21,939 (test) samples, preserving the class proportion.
## Dataset Creation
### Curation Rationale
We propose K-MHaS, a large size Korean multi-label hate speech detection dataset that represents Korean language patterns effectively. Most datasets in hate speech research are annotated using a single label classification of particular aspects, even though the subjectivity of hate speech cannot be explained with a mutually exclusive annotation scheme. We propose a multi-label hate speech annotation scheme that allows overlapping labels associated with the subjectivity and the intersectionality of hate speech.
### Source Data
#### Initial Data Collection and Normalization
Our dataset is based on the Korean online news comments available on Kaggle and Github. The unlabeled raw data was collected between January 2018 and June 2020. Please see the details in our paper [K-MHaS](https://aclanthology.org/2022.coling-1.311) published at COLING2020.
#### Who are the source language producers?
The language producers are users who left the comments on the Korean online news platform between 2018 and 2020.
### Annotations
#### Annotation process
We begin with the common categories of hate speech found in literature and match the keywords for each category. After the preliminary round, we investigate the results to merge or remove labels in order to provide the most representative subtype labels of hate speech contextual to the cultural background. Our annotation instructions explain a twolayered annotation to (a) distinguish hate and not hate speech, and (b) the categories of hate speech. Annotators are requested to consider given keywords or alternatives of each category within social, cultural, and historical circumstances. For more details, please refer to the paper [K-MHaS](https://aclanthology.org/2022.coling-1.311).
#### Who are the annotators?
Five native speakers were recruited for manual annotation in both the preliminary and main rounds.
### Personal and Sensitive Information
This datasets contains examples of hateful language, however, has no personal information.
## Considerations for Using the Data
### Social Impact of Dataset
We propose K-MHaS, a new large-sized dataset for Korean hate speech detection with a multi-label annotation scheme. We provided extensive baseline experiment results, presenting the usability of a dataset to detect Korean language patterns in hate speech.
### Discussion of Biases
All annotators were recruited from a crowdsourcing platform. They were informed about hate speech before handling the data. Our instructions allowed them to feel free to leave if they were uncomfortable with the content. With respect to the potential risks, we note that the subjectivity of human annotation would impact on the quality of the dataset.
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
This dataset is curated by Taejun Lim, Heejun Lee and Bogeun Jo.
### Licensing Information
Creative Commons Attribution-ShareAlike 4.0 International (cc-by-sa-4.0).
### Citation Information
```
@inproceedings{lee-etal-2022-k,
title = "K-{MH}a{S}: A Multi-label Hate Speech Detection Dataset in {K}orean Online News Comment",
author = "Lee, Jean and
Lim, Taejun and
Lee, Heejun and
Jo, Bogeun and
Kim, Yangsok and
Yoon, Heegeun and
Han, Soyeon Caren",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.311",
pages = "3530--3538",
abstract = "Online hate speech detection has become an important issue due to the growth of online content, but resources in languages other than English are extremely limited. We introduce K-MHaS, a new multi-label dataset for hate speech detection that effectively handles Korean language patterns. The dataset consists of 109k utterances from news comments and provides a multi-label classification using 1 to 4 labels, and handles subjectivity and intersectionality. We evaluate strong baselines on K-MHaS. KR-BERT with a sub-character tokenizer outperforms others, recognizing decomposed characters in each hate speech class.",
}
```
### Contributions
The contributors of the work are:
- [Jean Lee](https://jeanlee-ai.github.io/) (The University of Sydney)
- [Taejun Lim](https://github.com/taezun) (The University of Sydney)
- [Heejun Lee](https://bigwaveai.com/) (BigWave AI)
- [Bogeun Jo](https://bigwaveai.com/) (BigWave AI)
- Yangsok Kim (Keimyung University)
- Heegeun Yoon (National Information Society Agency)
- [Soyeon Caren Han](https://drcarenhan.github.io/) (The University of Western Australia and The University of Sydney)
|
false |
# Dataset Card for `squad_bn`
## Table of Contents
- [Dataset Card for `squad_bn`](#dataset-card-for-squad_bn)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Usage](#usage)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Initial Data Collection and Normalization](#initial-data-collection-and-normalization)
- [Who are the source language producers?](#who-are-the-source-language-producers)
- [Annotations](#annotations)
- [Annotation process](#annotation-process)
- [Who are the annotators?](#who-are-the-annotators)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Repository:** [https://github.com/csebuetnlp/banglabert](https://github.com/csebuetnlp/banglabert)
- **Paper:** [**"BanglaBERT: Combating Embedding Barrier in Multilingual Models for Low-Resource Language Understanding"**](https://arxiv.org/abs/2101.00204)
- **Point of Contact:** [Tahmid Hasan](mailto:tahmidhasan@cse.buet.ac.bd)
### Dataset Summary
This is a Question Answering (QA) dataset for Bengali, curated from the [SQuAD 2.0](), [TyDI-QA]() datasets and using the state-of-the-art English to Bengali translation model introduced **[here](https://aclanthology.org/2020.emnlp-main.207/).**
### Supported Tasks and Leaderboards
[More information needed](https://github.com/csebuetnlp/banglabert)
### Languages
* `Bengali`
### Usage
```python
from datasets import load_dataset
dataset = load_dataset("csebuetnlp/squad_bn")
```
## Dataset Structure
### Data Instances
One example from the dataset is given below in JSON format.
```
{
"title": "শেখ মুজিবুর রহমান",
"paragraphs": [
{
"qas": [
{
"answers": [
{
"answer_start": 19,
"text": "১৭ মার্চ ১৯২০"
}
],
"id": "bengali--981248442377505718-0-2649",
"question": "শেখ মুজিবুর রহমান কবে জন্মগ্রহণ করেন ?"
}
],
"context": "শেখ মুজিবুর রহমান (১৭ মার্চ ১৯২০ - ১৫ আগস্ট ১৯৭৫) বাংলাদেশের প্রথম রাষ্ট্রপতি ও ভারতীয় উপমহাদেশের একজন অন্যতম প্রভাবশালী রাজনৈতিক ব্যক্তিত্ব যিনি বাঙালীর অধিকার রক্ষায় ব্রিটিশ ভারত থেকে ভারত বিভাজন আন্দোলন এবং পরবর্তীতে পূর্ব পাকিস্তান থেকে বাংলাদেশ প্রতিষ্ঠার সংগ্রামে নেতৃত্ব প্রদান করেন। প্রাচীন বাঙ্গালি সভ্যতার আধুনিক স্থপতি হিসাবে শেখ মুজিবুর রহমানকে বাংলাদেশের জাতির জনক বা জাতির পিতা বলা হয়ে থাকে। তিনি মাওলানা আব্দুল হামিদ খান ভাসানী প্রতিষ্ঠিত আওয়ামী লীগের সভাপতি, বাংলাদেশের প্রথম রাষ্ট্রপতি এবং পরবর্তীতে এদেশের প্রধানমন্ত্রীর দায়িত্ব পালন করেন। জনসাধারণের কাছে তিনি শেখ মুজিব এবং শেখ সাহেব হিসাবে বেশি পরিচিত এবং তার উপাধি বঙ্গবন্ধু। তার কন্যা শেখ হাসিনা বাংলাদেশ আওয়ামী লীগের বর্তমান সভানেত্রী এবং বাংলাদেশের বর্তমান প্রধানমন্ত্রী।"
}
]
}
```
### Data Fields
The data fields are as follows:
- `id`: a `string` feature.
- `title`: a `string` feature.
- `context`: a `string` feature.
- `question`: a `string` feature.
- `answers`: a dictionary feature containing:
- `text`: a `string` feature.
- `answer_start`: a `int32` feature.
### Data Splits
| split |count |
|----------|--------|
|`train`| 127771 |
|`validation`| 2502 |
|`test`| 2504 |
## Dataset Creation
For the training set, we translated the complete [SQuAD 2.0](https://aclanthology.org/N18-1101/) dataset using the English to Bangla translation model introduced [here](https://aclanthology.org/2020.emnlp-main.207/). Due to the possibility of incursions of error during automatic translation, we used the [Language-Agnostic BERT Sentence Embeddings (LaBSE)](https://arxiv.org/abs/2007.01852) of the translations and original sentences to compute their similarity. A datapoint was accepted if all of its constituent sentences had a similarity score over 0.7.
Since the TyDI-QA Gold Passage task guarantees that the given context contains the answer and we want to pose our QA task analogous to SQuAD 2.0, we also consider examples from the Passage selection task that don't have an answer for the given question. We distribute the resultant examples from the TyDI-QA training and validation sets (which are publicly available) evenly to our test and validation sets.
### Curation Rationale
[More information needed](https://github.com/csebuetnlp/banglabert)
### Source Data
[SQuAD 2.0](https://arxiv.org/abs/1606.05250), [TyDi-QA](https://arxiv.org/abs/2003.05002)
#### Initial Data Collection and Normalization
[More information needed](https://github.com/csebuetnlp/banglabert)
#### Who are the source language producers?
[More information needed](https://github.com/csebuetnlp/banglabert)
### Annotations
[More information needed](https://github.com/csebuetnlp/banglabert)
#### Annotation process
[More information needed](https://github.com/csebuetnlp/banglabert)
#### Who are the annotators?
[More information needed](https://github.com/csebuetnlp/banglabert)
### Personal and Sensitive Information
[More information needed](https://github.com/csebuetnlp/banglabert)
## Considerations for Using the Data
### Social Impact of Dataset
[More information needed](https://github.com/csebuetnlp/banglabert)
### Discussion of Biases
[More information needed](https://github.com/csebuetnlp/banglabert)
### Other Known Limitations
[More information needed](https://github.com/csebuetnlp/banglabert)
## Additional Information
### Dataset Curators
[More information needed](https://github.com/csebuetnlp/banglabert)
### Licensing Information
Contents of this repository are restricted to only non-commercial research purposes under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/). Copyright of the dataset contents belongs to the original copyright holders.
### Citation Information
If you use the dataset, please cite the following paper:
```
@misc{bhattacharjee2021banglabert,
title={BanglaBERT: Combating Embedding Barrier in Multilingual Models for Low-Resource Language Understanding},
author={Abhik Bhattacharjee and Tahmid Hasan and Kazi Samin and Md Saiful Islam and M. Sohel Rahman and Anindya Iqbal and Rifat Shahriyar},
year={2021},
eprint={2101.00204},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@abhik1505040](https://github.com/abhik1505040) and [@Tahmid](https://github.com/Tahmid04) for adding this dataset. |
false |
# Dataset Card for Cryptonite
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Github](https://github.com/aviaefrat/cryptonite)
- **Repository:** [Github](https://github.com/aviaefrat/cryptonite)
- **Paper:** [Arxiv](https://arxiv.org/pdf/2103.01242.pdf)
- **Leaderboard:**
- **Point of Contact:** [Twitter](https://twitter.com/AviaEfrat)
### Dataset Summary
Current NLP datasets targeting ambiguity can be solved by a native speaker with relative ease. We present Cryptonite, a large-scale dataset based on cryptic crosswords, which is both linguistically complex and naturally sourced. Each example in Cryptonite is a cryptic clue, a short phrase or sentence with a misleading surface reading, whose solving requires disambiguating semantic, syntactic, and phonetic wordplays, as well as world knowledge. Cryptic clues pose a challenge even for experienced solvers, though top-tier experts can solve them with almost 100% accuracy. Cryptonite is a challenging task for current models; fine-tuning T5-Large on 470k cryptic clues achieves only 7.6% accuracy, on par with the accuracy of a rule-based clue solver (8.6%).
### Languages
English
## Dataset Structure
### Data Instances
This is one example from the train set.
```python
{
'clue': 'make progress socially in stated region (5)',
'answer': 'climb',
'date': 971654400000,
'enumeration': '(5)',
'id': 'Times-31523-6across',
'publisher': 'Times',
'quick': False
}
```
### Data Fields
- `clue`: a string representing the clue provided for the crossword
- `answer`: a string representing the answer to the clue
- `enumeration`: a string representing the
- `publisher`: a string representing the publisher of the crossword
- `date`: a int64 representing the UNIX timestamp of the date of publication of the crossword
- `quick`: a bool representing whether the crossword is quick (a crossword aimed at beginners, easier to solve)
- `id`: a string to uniquely identify a given example in the dataset
### Data Splits
Train (470,804 examples), validation (26,156 examples), test (26,157 examples).
## Dataset Creation
### Curation Rationale
Crosswords from the Times and the Telegraph.
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Avia Efrat, Uri Shaham, Dan Kilman, Omer Levy
### Licensing Information
`cc-by-nc-4.0`
### Citation Information
```
@misc{efrat2021cryptonite,
title={Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language},
author={Avia Efrat and Uri Shaham and Dan Kilman and Omer Levy},
year={2021},
eprint={2103.01242},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@theo-m](https://github.com/theo-m) for adding this dataset. |
true |
# Dataset Card for HateOffensive
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage** : https://sites.google.com/view/qanta/projects/diplomacy
- **Repository** : https://github.com/DenisPeskov/2020_acl_diplomacy
- **Paper** : http://users.umiacs.umd.edu/~jbg/docs/2020_acl_diplomacy.pdf
- **Leaderboard** :
- **Point of Contact** :
### Dataset Summary
This dataset contains pairwise conversations annotated by the sender and the receiver for deception (and conversely truthfulness). The 17,289 messages are gathered from 12 games.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English
## Dataset Structure
### Data Instances
```
{
"messages":
["Greetings Sultan!\n\nAs your neighbor I would like to propose an alliance! What are your views on the board so far?", "I think an alliance would be great! Perhaps a dmz in the Black Sea would be a good idea to solidify this alliance?\n\nAs for my views on the board, my first moves will be Western into the Balkans and Mediterranean Sea.", "Sounds good lets call a dmz in the black sea", "What's our move this year?", "I've been away from the game for a while", "Not sure yet, what are your thoughts?", "Well I'm pretty worried about Germany attacking me (and Austria to a lesser extent) so im headed west. It looks like Italy's landing a army in Syr this fall unless you can stop it", "That sounds good to me. I'll move to defend against Italy while you move west. If it's not too much too ask, I'd like to request that you withdraw your fleet from bla.", "Oh sorry missed the msg to move out of bl sea ill do that this turn. I did bring my army down into Armenia, To help you expel the Italian. It looks like Austria and Italy are working together. If we have a chance in the region you should probably use smy to protect con. We can't afford to lose con.", "I'll defend con from both ank and smy.", "Hey sorry for stabbing you earlier, it was an especially hard choice since Turkey is usually my country of choice. It's cool we got to do this study huh?"],
"sender_labels": [false, true, false, true, true, true, true, true, true, true, true],
"receiver_labels": [true, true, true, true, true, true, true, true, true, true, "NOANNOTATION"],
"speakers": ["russia", "turkey", "russia", "russia", "russia", "turkey", "russia", "turkey", "russia", "turkey", "russia"],
"receivers": ["turkey", "russia", "turkey", "turkey", "turkey", "russia", "turkey", "russia", "turkey", "russia", "turkey"],
"absolute_message_index": [78, 107, 145, 370, 371, 374, 415, 420, 495, 497, 717],
"relative_message_index": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
"seasons": ["Spring", "Spring", "Spring", "Spring", "Spring", "Spring", "Fall", "Fall", "Spring", "Spring", "Fall"],
"years": ["1901", "1901", "1901", "1902", "1902", "1902", "1902", "1902", "1903", "1903", "1905"],
"game_score": ["4", "3", "4", "5", "5", "4", "5", "4", "5", "3", "7"],
"game_score_delta": ["1", "-1", "1", "1", "1", "-1", "1", "-1", "2", "-2", "7"],
"players": ["russia", "turkey"],
"game_id": 10
}
```
### Data Fields
- speakers: the sender of the message (string format. Seven possible values: russia, turkey, england, austria, germany, france, italy)
- receivers: the receiver of the message (string format. Seven possible values: russia, turkey, england, austria, germany, france, italy)
- messages: the raw message string (string format. ranges in length from one word to paragraphs in length)
- sender_labels: indicates if the sender of the message selected that the message is truthful, true, or deceptive, false. This is used for our ACTUAL_LIE calculation (true/false which can be bool or string format)
- receiver_labels: indicates if the receiver of the message selected that the message is perceived as truthful, true, or deceptive, false. In <10% of the cases, no annotation was received. This is used for our SUSPECTED_LIE calculation (string format. true/false/"NOANNOTATION" )
- game_score: the current game score---supply centers---of the sender (string format that ranges can range from 0 to 18)
- game_score_delta: the current game score---supply centers---of the sender minus the game score of the recipient (string format that ranges from -18 to 18)
- absolute_message_index: the index the message is in the entire game, across all dialogs (int format)
- relative_message_index: the index of the message in the current dialog (int format)
- seasons: the season in Diplomacy, associated with the year (string format. Spring, Fall, Winter)
- years: the year in Diplomacy, associated with the season (string format. 1901 through 1918)
- game_id: which of the 12 games the dialog comes from (int format ranging from 1 to 12)
### Data Splits
Train, Test and Validation splits
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
Unknown
### Citation Information
@inproceedings{Peskov:Cheng:Elgohary:Barrow:Danescu-Niculescu-Mizil:Boyd-Graber-2020,
Title = {It Takes Two to Lie: One to Lie and One to Listen},
Author = {Denis Peskov and Benny Cheng and Ahmed Elgohary and Joe Barrow and Cristian Danescu-Niculescu-Mizil and Jordan Boyd-Graber},
Booktitle = {Association for Computational Linguistics},
Year = {2020},
Location = {Seattle},
}
### Contributions
Thanks to [@MisbahKhan789](https://github.com/MisbahKhan789) for adding this dataset. |
false |
# Dataset Card for Hausa VOA NER Corpus
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.aclweb.org/anthology/2020.emnlp-main.204/
- **Repository:** [Hausa VOA NER](https://github.com/uds-lsv/transfer-distant-transformer-african/tree/master/data/hausa_ner)
- **Paper:** https://www.aclweb.org/anthology/2020.emnlp-main.204/
- **Leaderboard:**
- **Point of Contact:** [David Adelani](mailto:didelani@lsv.uni-saarland.de)
### Dataset Summary
The Hausa VOA NER is a named entity recognition (NER) dataset for Hausa language based on the [VOA Hausa news](https://www.voahausa.com/) corpus.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The language supported is Hausa.
## Dataset Structure
### Data Instances
A data point consists of sentences seperated by empty line and tab-seperated tokens and tags.
{'id': '0',
'ner_tags': [B-PER, 0, 0, B-LOC, 0],
'tokens': ['Trump', 'ya', 'ce', 'Rasha', 'ma']
}
### Data Fields
- `id`: id of the sample
- `tokens`: the tokens of the example text
- `ner_tags`: the NER tags of each token
The NER tags correspond to this list:
```
"O", "B-PER", "I-PER", "B-ORG", "I-ORG", "B-LOC", "I-LOC", "B-DATE", "I-DATE",
```
The NER tags have the same format as in the CoNLL shared task: a B denotes the first item of a phrase and an I any non-initial word. There are four types of phrases: person names (PER), organizations (ORG), locations (LOC) and dates & times (DATE). (O) is used for tokens not considered part of any named entity.
### Data Splits
Training (1,014 sentences), validation (145 sentences) and test split (291 sentences)
## Dataset Creation
### Curation Rationale
The data was created to help introduce resources to new language - Hausa.
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
The dataset is based on the news domain and was crawled from [VOA Hausa news](https://www.voahausa.com/).
[More Information Needed]
#### Who are the source language producers?
The dataset was collected from VOA Hausa news. Most of the texts used in creating the Hausa VOA NER are news stories from Nigeria, Niger Republic, United States, and other parts of the world.
[More Information Needed]
### Annotations
Named entity recognition annotation
#### Annotation process
[More Information Needed]
#### Who are the annotators?
The data was annotated by Jesujoba Alabi and David Adelani for the paper:
[Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages](https://www.aclweb.org/anthology/2020.emnlp-main.204/).
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The annotated data sets were developed by students of Saarland University, Saarbrücken, Germany .
### Licensing Information
The data is under the [Creative Commons Attribution 4.0 ](https://creativecommons.org/licenses/by/4.0/)
### Citation Information
```
@inproceedings{hedderich-etal-2020-transfer,
title = "Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on {A}frican Languages",
author = "Hedderich, Michael A. and
Adelani, David and
Zhu, Dawei and
Alabi, Jesujoba and
Markus, Udia and
Klakow, Dietrich",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.emnlp-main.204",
doi = "10.18653/v1/2020.emnlp-main.204",
pages = "2580--2591",
}
```
### Contributions
Thanks to [@dadelani](https://github.com/dadelani) for adding this dataset. |
false |
# Dataset Card for GEM/RiSAWOZ
## Dataset Description
- **Homepage:** https://terryqj0107.github.io/RiSAWOZ_webpage
- **Repository:** https://github.com/terryqj0107/RiSAWOZ
- **Paper:** https://aclanthology.org/2020.emnlp-main.67
- **Leaderboard:** N/A
- **Point of Contact:** Deyi Xiong
### Link to Main Data Card
You can find the main data card on the [GEM Website](https://gem-benchmark.com/data_cards/RiSAWOZ).
### Dataset Summary
RiSAWOZ is a Chinese dialog dataset. It can be used to study various dialogue tasks, such as Dialogue State Tracking, Dialogue Context-to-Text Generation, Coreference Resolution and Unified Generative Ellipsis and Coreference Resolution.
You can load the dataset via:
```
import datasets
data = datasets.load_dataset('GEM/RiSAWOZ')
```
The data loader can be found [here](https://huggingface.co/datasets/GEM/RiSAWOZ).
#### website
[Website](https://terryqj0107.github.io/RiSAWOZ_webpage)
#### paper
[ACL Anthology](https://aclanthology.org/2020.emnlp-main.67)
#### authors
Jun Quan (Soochow University, Suzhou, China), Shian Zhang (Soochow University, Suzhou, China), Qian Cao(Soochow University, Suzhou, China), Zizhong Li (Tianjin University, Tianjin, China), Deyi Xiong (Tianjin University, Tianjin, China)
## Dataset Overview
### Where to find the Data and its Documentation
#### Webpage
<!-- info: What is the webpage for the dataset (if it exists)? -->
<!-- scope: telescope -->
[Website](https://terryqj0107.github.io/RiSAWOZ_webpage)
#### Download
<!-- info: What is the link to where the original dataset is hosted? -->
<!-- scope: telescope -->
[Github](https://github.com/terryqj0107/RiSAWOZ)
#### Paper
<!-- info: What is the link to the paper describing the dataset (open access preferred)? -->
<!-- scope: telescope -->
[ACL Anthology](https://aclanthology.org/2020.emnlp-main.67)
#### BibTex
<!-- info: Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex. -->
<!-- scope: microscope -->
```
@inproceedings{quan-etal-2020-risawoz,
title = "{R}i{SAWOZ}: A Large-Scale Multi-Domain {W}izard-of-{O}z Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling",
author = "Quan, Jun and
Zhang, Shian and
Cao, Qian and
Li, Zizhong and
Xiong, Deyi",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.emnlp-main.67",
pages = "930--940",
}
```
#### Contact Name
<!-- quick -->
<!-- info: If known, provide the name of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
Deyi Xiong
#### Contact Email
<!-- info: If known, provide the email of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
dyxiong@tju.edu.cn
#### Has a Leaderboard?
<!-- info: Does the dataset have an active leaderboard? -->
<!-- scope: telescope -->
no
### Languages and Intended Use
#### Multilingual?
<!-- quick -->
<!-- info: Is the dataset multilingual? -->
<!-- scope: telescope -->
no
#### Covered Dialects
<!-- info: What dialects are covered? Are there multiple dialects per language? -->
<!-- scope: periscope -->
Only Mandarin Chinese is covered in this dataset.
#### Covered Languages
<!-- quick -->
<!-- info: What languages/dialects are covered in the dataset? -->
<!-- scope: telescope -->
`Mandarin Chinese`
#### License
<!-- quick -->
<!-- info: What is the license of the dataset? -->
<!-- scope: telescope -->
cc-by-4.0: Creative Commons Attribution 4.0 International
#### Intended Use
<!-- info: What is the intended use of the dataset? -->
<!-- scope: microscope -->
RiSAWOZ can be used to support the study under various dialogue tasks, such as Natural Language Understanding, Dialogue State Tracking, Dialogue Context-to-Text Generation, Coreference Resolution and Unified Generative Ellipsis and Coreference Resolution.
#### Primary Task
<!-- info: What primary task does the dataset support? -->
<!-- scope: telescope -->
Dialog Response Generation
#### Communicative Goal
<!-- quick -->
<!-- info: Provide a short description of the communicative goal of a model trained for this task on this dataset. -->
<!-- scope: periscope -->
Generate system response given dialogue context across multiple domains.
### Credit
#### Curation Organization Type(s)
<!-- info: In what kind of organization did the dataset curation happen? -->
<!-- scope: telescope -->
`academic`
#### Curation Organization(s)
<!-- info: Name the organization(s). -->
<!-- scope: periscope -->
Soochow University and Tianjin University
#### Dataset Creators
<!-- info: Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s). -->
<!-- scope: microscope -->
Jun Quan (Soochow University, Suzhou, China), Shian Zhang (Soochow University, Suzhou, China), Qian Cao(Soochow University, Suzhou, China), Zizhong Li (Tianjin University, Tianjin, China), Deyi Xiong (Tianjin University, Tianjin, China)
#### Funding
<!-- info: Who funded the data creation? -->
<!-- scope: microscope -->
the National Key Research and Development Project
#### Who added the Dataset to GEM?
<!-- info: Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM. -->
<!-- scope: microscope -->
Tianhao Shen (Tianjin University, Tianjin, China), Chaobin You (Tianjin University, Tianjin, China), Deyi Xiong (Tianjin University, Tianjin, China)
### Dataset Structure
#### Data Fields
<!-- info: List and describe the fields present in the dataset. -->
<!-- scope: telescope -->
- gem_id (string): GEM-RiSAWOZ-{split}-{id}
- dialogue_id (string): dialogue ID
- goal (string): natural language descriptions of the user goal
- domains (list of strings): domains mentioned in current dialogue session
- dialogue (list of dicts): dialog turns and corresponding annotations. Each turn includes:
- turn_id (int): turn ID
- turn_domain (list of strings): domain mentioned in current turn
- user_utterance (string): user utterance
- system_utterance (string): system utterance
- belief_state (dict): dialogue state, including:
- inform slot-values (dict): the slots and corresponding values informed until current turn
- turn_inform (dict): the slots and corresponding values informed in current turn
- turn request (dict): the slots requested in current turn
- user_actions (list of lists): user dialogue acts in current turn
- user_actions (list of lists): system dialogue acts in current turn
- db_results (list of strings): database search results
- segmented_user_utterance (string): word segmentation result of user utterance
- segmented_system_utterance (string): word segmentation result of system utterance
#### Example Instance
<!-- info: Provide a JSON formatted example of a typical instance in the dataset. -->
<!-- scope: periscope -->
```
[
{
"dialogue_id": "attraction_goal_4-63###6177",
"goal": "attraction_goal_4-63: 你是苏州人，但不怎么出去玩。你朋友来苏州找你，你准备带他逛逛“水乡古镇”，你希望客服给你推荐个消费水平“中等”的地方。然后你要问清楚这地方“是否地铁直达”、“特点”、“门票价格”这些信息。最后，你要感谢客服的帮助，然后说再见。",
"domains": [
"旅游景点"
],
"dialogue": [
{
"turn_id": 0,
"turn_domain": [
"旅游景点"
],
"user_utterance": "你好，我是苏州人，但是不怎么出去玩，我朋友来苏州找我了，我准备带他逛逛水乡古镇，你能帮我推荐一下吗？",
"system_utterance": "推荐您去周庄古镇。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "水乡 古镇"
},
"turn_inform": {
"旅游景点-景点类型": "水乡 古镇"
},
"turn request": []
},
"user_actions": [
[
"Inform",
"旅游景点",
"景点类型",
"水乡 古镇"
],
[
"Greeting",
"旅游景点",
"",
""
]
],
"system_actions": [
[
"Recommend",
"旅游景点",
"名称",
"周庄 古镇"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为8",
"{'名称': '周庄古镇', '区域': '昆山', '景点类型': '水乡古镇', '最适合人群': '朋友出游', '消费': '偏贵', '是否地铁直达': '否', '门票价格': '100元', '电话号码': '400-8282900', '地址': '苏州市昆山市周庄镇全福路43号', '评分': 4.5, '开放时间': '07:30-18:50', '特点': '小桥流水与人家，双桥水巷摇橹船，还有沈万三的足迹待你寻访'}",
"{'名称': '同里古镇', '区域': '吴江', '景点类型': '水乡古镇', '最适合人群': '朋友出游', '消费': '偏贵', '是否地铁直达': '否', '门票价格': '100元', '电话号码': '0512-63325728', '地址': '苏州市吴江区同里古镇', '评分': 4.5, '开放时间': '07:30-17:30', '特点': '五湖环抱的江南水乡古镇，走三桥，参观小巧精致的园林退思园。'}",
"{'名称': '山塘街', '区域': '姑苏区', '景点类型': '水乡古镇', '最适合人群': '情侣约会', '消费': '中等', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '0512-65314467', '地址': '苏州市姑苏区古城西北', '评分': 4.5, '开放时间': '08:30-21:00', '特点': '欣赏苏州老城风貌，参观会馆等古迹，乘游船，拍摄美丽的夜景。'}",
"{'名称': '平江路', '区域': '姑苏区', '景点类型': '水乡古镇', '最适合人群': '情侣约会', '消费': '中等', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '0512-69163907', '地址': '江苏省苏州市姑苏区白塔东路65号', '评分': 4.5, '开放时间': '全天', '特点': '漫步保存完整的古街区，看小桥流水古宅，逛文艺小店，吃美食。'}",
"{'名称': '木渎古镇', '区域': '吴中区', '景点类型': '水乡古镇', '最适合人群': '朋友出游', '消费': '便宜', '是否地铁直达': '否', '门票价格': '免费', '电话号码': '0512-66514042', '地址': '苏州市吴中区木渎镇山塘街188号', '评分': 4.4, '开放时间': '08:30-17:00', '特点': '以园林为特色的古镇，游严家花园等古典园林，坐船看小桥流水。'}",
"{'名称': '甪直古镇', '区域': '吴中区', '景点类型': '水乡古镇', '最适合人群': '朋友出游', '消费': '便宜', '是否地铁直达': '否', '门票价格': '免费', '电话号码': '0512-66191668', '地址': '苏州市吴中区甪直镇晓市路21号', '评分': 4.3, '开放时间': '07:30-17:30', '特点': '甪直古镇有2500多年历史，甪直境内水流纵横，桥梁密布，有五湖之厅、六泽之冲之称。'}",
"{'名称': '千灯古镇', '区域': '昆山', '景点类型': '水乡古镇', '最适合人群': '朋友出游', '消费': '便宜', '是否地铁直达': '否', '门票价格': '免费', '电话号码': '0512-57472155', '地址': '苏州市昆山市千灯古镇尚书路1号', '评分': 4.3, '开放时间': '08:00-17:00', '特点': '千灯古镇，距今已有2500多年的历史，古镇白墙黑瓦，昆韵盎然。'}",
"{'名称': '锦溪古镇', '区域': '昆山', '景点类型': '水乡古镇', '最适合人群': '朋友出游', '消费': '中等', '是否地铁直达': '否', '门票价格': '65元', '电话号码': '0512-57224669', '地址': '苏州市昆山市锦溪镇邵甸港路18号', '评分': 4.4, '开放时间': '08:00-17:00', '特点': '锦溪古镇位于昆山南郊的淀山湖畔，是一座有千年历史的江南水乡。'}"
],
"segmented_user_utterance": "你好 ， 我 是 苏州人 ， 但是 不怎么 出去玩 ， 我 朋友 来 苏州 找 我 了 ， 我 准备 带 他 逛逛 水乡 古镇 ， 你 能 帮 我 推荐 一下 吗 ？",
"segmented_system_utterance": "推荐 您 去 周庄 古镇 。"
},
{
"turn_id": 1,
"turn_domain": [
"旅游景点"
],
"user_utterance": "我希望这个地方消费水平适中的，这个是中等的吗？",
"system_utterance": "这个不是，我又重新帮您找了一家山塘街。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "水乡 古镇",
"旅游景点-消费": "中等"
},
"turn_inform": {
"旅游景点-消费": "中等"
},
"turn request": []
},
"user_actions": [
[
"Inform",
"旅游景点",
"消费",
"中等"
]
],
"system_actions": [
[
"Recommend",
"旅游景点",
"名称",
"山塘 街"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为3",
"{'名称': '山塘街', '区域': '姑苏区', '景点类型': '水乡古镇', '最适合人群': '情侣约会', '消费': '中等', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '0512-65314467', '地址': '苏州市姑苏区古城西北', '评分': 4.5, '开放时间': '08:30-21:00', '特点': '欣赏苏州老城风貌，参观会馆等古迹，乘游船，拍摄美丽的夜景。'}",
"{'名称': '平江路', '区域': '姑苏区', '景点类型': '水乡古镇', '最适合人群': '情侣约会', '消费': '中等', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '0512-69163907', '地址': '江苏省苏州市姑苏区白塔东路65号', '评分': 4.5, '开放时间': '全天', '特点': '漫步保存完整的古街区，看小桥流水古宅，逛文艺小店，吃美食。'}",
"{'名称': '锦溪古镇', '区域': '昆山', '景点类型': '水乡古镇', '最适合人群': '朋友出游', '消费': '中等', '是否地铁直达': '否', '门票价格': '65元', '电话号码': '0512-57224669', '地址': '苏州市昆山市锦溪镇邵甸港路18号', '评分': 4.4, '开放时间': '08:00-17:00', '特点': '锦溪古镇位于昆山南郊的淀山湖畔，是一座有千年历史的江南水乡。'}"
],
"segmented_user_utterance": "我 希望 这个 地方 消费水平 适中 的 ， 这个 是 中等 的 吗 ？",
"segmented_system_utterance": "这个 不是 ， 我 又 重新 帮 您 找 了 一家 山塘 街 。"
},
{
"turn_id": 2,
"turn_domain": [
"旅游景点"
],
"user_utterance": "听这地方应该挺好玩，他们家特点是什么？",
"system_utterance": "特点是欣赏苏州老城风貌，参观会馆等古迹，乘游船，拍摄美丽的夜景。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "水乡 古镇",
"旅游景点-消费": "中等",
"旅游景点-名称": "山塘 街"
},
"turn_inform": {
"旅游景点-名称": "山塘 街"
},
"turn request": [
"特点"
]
},
"user_actions": [
[
"Inform",
"旅游景点",
"名称",
"山塘 街"
],
[
"Request",
"旅游景点",
"特点",
""
]
],
"system_actions": [
[
"Inform",
"旅游景点",
"特点",
"欣赏 苏州 老城 风貌 ， 参观 会馆 等 古迹 ， 乘 游船 ， 拍摄 美丽 的 夜景"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '山塘街', '区域': '姑苏区', '景点类型': '水乡古镇', '最适合人群': '情侣约会', '消费': '中等', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '0512-65314467', '地址': '苏州市姑苏区古城西北', '评分': 4.5, '开放时间': '08:30-21:00', '特点': '欣赏苏州老城风貌，参观会馆等古迹，乘游船，拍摄美丽的夜景。'}"
],
"segmented_user_utterance": "听 这 地方 应该 挺好玩 ， 他们 家 特点 是 什么 ？",
"segmented_system_utterance": "特点 是 欣赏 苏州 老城 风貌 ， 参观 会馆 等 古迹 ， 乘 游船 ， 拍摄 美丽 的 夜景 。"
},
{
"turn_id": 3,
"turn_domain": [
"旅游景点"
],
"user_utterance": "听起来很不错，他们家门票是多少？",
"system_utterance": "门票免费。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "水乡 古镇",
"旅游景点-消费": "中等",
"旅游景点-名称": "山塘 街"
},
"turn_inform": {},
"turn request": [
"门票价格"
]
},
"user_actions": [
[
"Request",
"旅游景点",
"门票价格",
""
]
],
"system_actions": [
[
"Inform",
"旅游景点",
"门票价格",
"免费"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '山塘街', '区域': '姑苏区', '景点类型': '水乡古镇', '最适合人群': '情侣约会', '消费': '中等', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '0512-65314467', '地址': '苏州市姑苏区古城西北', '评分': 4.5, '开放时间': '08:30-21:00', '特点': '欣赏苏州老城风貌，参观会馆等古迹，乘游船，拍摄美丽的夜景。'}"
],
"segmented_user_utterance": "听 起来 很 不错 ， 他们 家 门票 是 多少 ？",
"segmented_system_utterance": "门票 免费 。"
},
{
"turn_id": 4,
"turn_domain": [
"旅游景点"
],
"user_utterance": "还行，那他们家是否有地铁直达呢？",
"system_utterance": "嗯嗯，可以地铁直达。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "水乡 古镇",
"旅游景点-消费": "中等",
"旅游景点-名称": "山塘 街"
},
"turn_inform": {},
"turn request": [
"是否地铁直达"
]
},
"user_actions": [
[
"Request",
"旅游景点",
"是否地铁直达",
""
]
],
"system_actions": [
[
"Inform",
"旅游景点",
"是否地铁直达",
"是"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '山塘街', '区域': '姑苏区', '景点类型': '水乡古镇', '最适合人群': '情侣约会', '消费': '中等', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '0512-65314467', '地址': '苏州市姑苏区古城西北', '评分': 4.5, '开放时间': '08:30-21:00', '特点': '欣赏苏州老城风貌，参观会馆等古迹，乘游船，拍摄美丽的夜景。'}"
],
"segmented_user_utterance": "还 行 ， 那 他们 家 是否 有 地铁 直达 呢 ？",
"segmented_system_utterance": "嗯 嗯 ， 可以 地铁 直达 。"
},
{
"turn_id": 5,
"turn_domain": [
"通用"
],
"user_utterance": "谢谢你的帮助，再见！",
"system_utterance": "再见。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "水乡 古镇",
"旅游景点-消费": "中等",
"旅游景点-名称": "山塘 街"
},
"turn_inform": {},
"turn request": []
},
"user_actions": [
[
"Bye",
"通用",
"",
""
]
],
"system_actions": [
[
"Bye",
"通用",
"",
""
]
],
"db_results": [],
"segmented_user_utterance": "谢谢 你 的 帮助 ， 再见 ！",
"segmented_system_utterance": "再见 。"
}
]
},
{
"dialogue_id": "attraction_goal_3-33_v2###7307",
"goal": "attraction_goal_3-33: 你和朋友一起来苏州出差，顺便想去“苏州乐园森林水世界”逛一逛。因此，你要询问客服这个地方“是否地铁直达”、“评分”、“特点”这些信息。最后，你向客服表示感谢，结束对话。",
"domains": [
"旅游景点"
],
"dialogue": [
{
"turn_id": 0,
"turn_domain": [
"旅游景点"
],
"user_utterance": "你好，我和朋友一起来苏州出差，顺便想去苏州乐园森林水世界玩玩，能否帮我看看这个地方是否有地铁直达呢？",
"system_utterance": "稍等，很抱歉，没有地铁能直接到这个景点呢。",
"belief_state": {
"inform slot-values": {
"旅游景点-名称": "苏州 乐园 森林 水 世界"
},
"turn_inform": {
"旅游景点-名称": "苏州 乐园 森林 水 世界"
},
"turn request": [
"是否地铁直达"
]
},
"user_actions": [
[
"Inform",
"旅游景点",
"名称",
"苏州 乐园 森林 水 世界"
],
[
"Request",
"旅游景点",
"是否地铁直达",
""
],
[
"Greeting",
"旅游景点",
"",
""
]
],
"system_actions": [
[
"Inform",
"旅游景点",
"是否地铁直达",
"否"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '苏州乐园森林水世界', '区域': '高新区', '景点类型': '游乐场', '最适合人群': '情侣约会', '消费': '偏贵', '是否地铁直达': '否', '门票价格': '198元', '电话号码': '0512-68717107', '地址': '苏州市高新区阳山东路以西，山神湾路以东', '评分': 4.4, '开放时间': '09:00-17:00', '特点': '各项水上娱乐项目皆具森林特色，被赋予森林主题，让人身处浩瀚森林又能享受到海洋般的舒爽水游乐。'}"
],
"segmented_user_utterance": "你好 ， 我 和 朋友 一 起来 苏州 出差 ， 顺便 想 去 苏州 乐园 森林 水 世界 玩玩 ， 能否 帮 我 看看 这个 地方 是否 有 地铁 直达 呢 ？",
"segmented_system_utterance": "稍 等 ， 很 抱歉 ， 没有 地铁 能 直接 到 这个 景点 呢 。"
},
{
"turn_id": 1,
"turn_domain": [
"旅游景点"
],
"user_utterance": "你再帮我看看景点的评分好吗？",
"system_utterance": "这个景点的评分是4.4分。",
"belief_state": {
"inform slot-values": {
"旅游景点-名称": "苏州 乐园 森林 水 世界"
},
"turn_inform": {},
"turn request": [
"评分"
]
},
"user_actions": [
[
"Request",
"旅游景点",
"评分",
""
]
],
"system_actions": [
[
"Inform",
"旅游景点",
"评分",
"4.4"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '苏州乐园森林水世界', '区域': '高新区', '景点类型': '游乐场', '最适合人群': '情侣约会', '消费': '偏贵', '是否地铁直达': '否', '门票价格': '198元', '电话号码': '0512-68717107', '地址': '苏州市高新区阳山东路以西，山神湾路以东', '评分': 4.4, '开放时间': '09:00-17:00', '特点': '各项水上娱乐项目皆具森林特色，被赋予森林主题，让人身处浩瀚森林又能享受到海洋般的舒爽水游乐。'}"
],
"segmented_user_utterance": "你 再 帮 我 看看 景点 的 评分 好 吗 ？",
"segmented_system_utterance": "这个 景点 的 评分 是 4.4 分 。"
},
{
"turn_id": 2,
"turn_domain": [
"旅游景点"
],
"user_utterance": "这个景点有啥特点呢？",
"system_utterance": "这个景点的特点是各项水上娱乐项目皆具森林特色，被赋予森林主题，让人身处浩瀚森林又能享受到海洋般的舒爽水游乐。",
"belief_state": {
"inform slot-values": {
"旅游景点-名称": "苏州 乐园 森林 水 世界"
},
"turn_inform": {},
"turn request": [
"特点"
]
},
"user_actions": [
[
"Request",
"旅游景点",
"特点",
""
]
],
"system_actions": [
[
"Inform",
"旅游景点",
"特点",
"各项 水上 娱乐 项目 皆 具 森林 特色 ， 被 赋予 森林 主题 ， 让 人 身处 浩瀚 森林 又 能 享受 到 海洋 般的 舒爽 水 游乐 。"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '苏州乐园森林水世界', '区域': '高新区', '景点类型': '游乐场', '最适合人群': '情侣约会', '消费': '偏贵', '是否地铁直达': '否', '门票价格': '198元', '电话号码': '0512-68717107', '地址': '苏州市高新区阳山东路以西，山神湾路以东', '评分': 4.4, '开放时间': '09:00-17:00', '特点': '各项水上娱乐项目皆具森林特色，被赋予森林主题，让人身处浩瀚森林又能享受到海洋般的舒爽水游乐。'}"
],
"segmented_user_utterance": "这个 景点 有 啥 特点 呢 ？",
"segmented_system_utterance": "这个 景点 的 特点 是 各项 水上 娱乐 项目 皆 具 森林 特色 ， 被 赋予 森林 主题 ， 让 人 身处 浩瀚 森林 又 能 享受 到 海洋 般的 舒爽 水 游乐 。"
},
{
"turn_id": 3,
"turn_domain": [
"通用"
],
"user_utterance": "太好了，我觉得我会很喜欢这个地方，哈哈。",
"system_utterance": "这个景点挺不错的，就是没有地铁需要您乘坐其它交通工具了。",
"belief_state": {
"inform slot-values": {
"旅游景点-名称": "苏州 乐园 森林 水 世界"
},
"turn_inform": {},
"turn request": []
},
"user_actions": [
[
"General",
"通用",
"",
""
]
],
"system_actions": [
[
"General",
"通用",
"",
""
]
],
"db_results": [],
"segmented_user_utterance": "太好了 ， 我 觉得 我会 很 喜欢 这个 地方 ， 哈哈 。",
"segmented_system_utterance": "这个 景点 挺不错 的 ， 就是 没有 地铁 需要 您 乘坐 其它 交通工具 了 。"
},
{
"turn_id": 4,
"turn_domain": [
"通用"
],
"user_utterance": "我打出租车去吧，就是多花点车费，没事。",
"system_utterance": "请问您还有其他问题吗？",
"belief_state": {
"inform slot-values": {
"旅游景点-名称": "苏州 乐园 森林 水 世界"
},
"turn_inform": {},
"turn request": []
},
"user_actions": [
[
"General",
"通用",
"",
""
]
],
"system_actions": [
[
"General",
"通用",
"",
""
]
],
"db_results": [],
"segmented_user_utterance": "我 打 出租车 去 吧 ， 就是 多花点 车费 ， 没事 。",
"segmented_system_utterance": "请问 您 还有 其他 问题 吗 ？"
},
{
"turn_id": 5,
"turn_domain": [
"通用"
],
"user_utterance": "没有了。谢谢你，再见。",
"system_utterance": "再见。",
"belief_state": {
"inform slot-values": {
"旅游景点-名称": "苏州 乐园 森林 水 世界"
},
"turn_inform": {},
"turn request": []
},
"user_actions": [
[
"Bye",
"通用",
"",
""
]
],
"system_actions": [
[
"Bye",
"通用",
"",
""
]
],
"db_results": [],
"segmented_user_utterance": "没有 了 。 谢谢 你 ， 再见 。",
"segmented_system_utterance": "再见 。"
}
]
}
]
```
#### Data Splits
<!-- info: Describe and name the splits in the dataset if there are more than one. -->
<!-- scope: periscope -->
- Train:
- dialogues: 10000
- turns: 134580
- Avg. turns: 13.5
- Valid:
- dialogues: 600
- turns: 8116
- Avg. turns: 13.5
- Test:
- dialogues: 600
- turn: 9286
- Avg. turns: 15.5
####
<!-- info: What does an outlier of the dataset in terms of length/perplexity/embedding look like? -->
<!-- scope: microscope -->
the most complex example (i.e. with the most domains):
```
{
"dialogue_id": "attraction_restaurant_hotel_goal_2-69_v2###8355",
"goal": "attraction_restaurant_hotel_goal_2-69: 公司派你去苏州出差，你准备抽空旅游一下。第一，你想去一个“山水景区”，消费水平最好是“偏贵”的，你需要问清楚这地方“开放时间”、“门票价格”这些信息。第二，你要找个地方住，让客服给你推荐一家价位“中等”的“商务出行”酒店，并且询问这家酒店的“停车场”、“电话号码”这些信息。第三，你还想拔草美食，问客服有没有价位“中等”的“江浙菜”餐厅推荐，然后了解这家餐厅的“是否地铁直达”、“人均消费”这些信息。最后你要感谢客服的帮助，并说再见。",
"domains": [
"旅游景点",
"餐厅",
"酒店"
],
"dialogue": [
{
"turn_id": 0,
"turn_domain": [
"旅游景点"
],
"user_utterance": "你好，来苏州出差，准备抽空旅游一下。我想去山水景区，消费水平偏贵点，帮忙推荐一个。",
"system_utterance": "你好，向您推荐金鸡湖景区，感受一下苏州现代化的一面。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵"
},
"turn_inform": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵"
},
"turn request": []
},
"user_actions": [
[
"Inform",
"旅游景点",
"景点类型",
"山水 景区"
],
[
"Inform",
"旅游景点",
"消费",
"偏贵"
],
[
"Greeting",
"旅游景点",
"",
""
],
[
"General",
"旅游景点",
"",
""
]
],
"system_actions": [
[
"Greeting",
"通用",
"",
""
],
[
"General",
"通用",
"",
""
],
[
"Recommend",
"旅游景点",
"名称",
"金鸡湖 景区"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为2",
"{'名称': '金鸡湖景区', '区域': '工业园区', '景点类型': '山水景区', '最适合人群': '情侣约会', '消费': '偏贵', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '400-7558558', '地址': '苏州市工业园区星港街158号', '评分': 4.5, '开放时间': '全天', '特点': '看东方之门等高楼，坐摩天轮，乘船夜游，感受苏州现代化的一面。'}",
"{'名称': '沙家浜风景区', '区域': '常熟', '景点类型': '山水景区', '最适合人群': '家庭亲子', '消费': '偏贵', '是否地铁直达': '否', '门票价格': '110元', '电话号码': '0512-52500000', '地址': '苏州市常熟市沙家浜镇', '评分': 4.5, '开放时间': '08:00-16:30', '特点': '京剧样板戏《沙家浜》的发源地，访剧中场景，坐船深入芦苇荡。'}"
],
"segmented_user_utterance": "你好 ， 来 苏州 出差 ， 准备 抽空 旅游 一下 。 我 想 去 山水 景区 ， 消费水平 偏 贵点 ， 帮忙 推荐 一个 。",
"segmented_system_utterance": "你好 ， 向 您 推荐 金鸡湖 景区 ， 感受一下 苏州 现代化 的 一面 。"
},
{
"turn_id": 1,
"turn_domain": [
"旅游景点"
],
"user_utterance": "这里开放时间？需要安排一下。",
"system_utterance": "景区是全天开放的，可以尽情游览！",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区"
},
"turn_inform": {
"旅游景点-名称": "金鸡湖 景区"
},
"turn request": [
"开放时间"
]
},
"user_actions": [
[
"Inform",
"旅游景点",
"名称",
"金鸡湖 景区"
],
[
"Request",
"旅游景点",
"开放时间",
""
],
[
"General",
"旅游景点",
"",
""
]
],
"system_actions": [
[
"Inform",
"旅游景点",
"开放时间",
"全天"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '金鸡湖景区', '区域': '工业园区', '景点类型': '山水景区', '最适合人群': '情侣约会', '消费': '偏贵', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '400-7558558', '地址': '苏州市工业园区星港街158号', '评分': 4.5, '开放时间': '全天', '特点': '看东方之门等高楼，坐摩天轮，乘船夜游，感受苏州现代化的一面。'}"
],
"segmented_user_utterance": "这里 开放 时间 ？ 需要 安排 一下 。",
"segmented_system_utterance": "景区 是 全天 开放 的 ， 可以 尽情 游览 ！"
},
{
"turn_id": 2,
"turn_domain": [
"旅游景点"
],
"user_utterance": "门票多少钱？",
"system_utterance": "这里是免费景区。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区"
},
"turn_inform": {},
"turn request": [
"门票价格"
]
},
"user_actions": [
[
"Request",
"旅游景点",
"门票价格",
""
]
],
"system_actions": [
[
"Inform",
"旅游景点",
"门票价格",
"免费"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '金鸡湖景区', '区域': '工业园区', '景点类型': '山水景区', '最适合人群': '情侣约会', '消费': '偏贵', '是否地铁直达': '是', '门票价格': '免费', '电话号码': '400-7558558', '地址': '苏州市工业园区星港街158号', '评分': 4.5, '开放时间': '全天', '特点': '看东方之门等高楼，坐摩天轮，乘船夜游，感受苏州现代化的一面。'}"
],
"segmented_user_utterance": "门票 多少 钱 ？",
"segmented_system_utterance": "这里 是 免费 景区 。"
},
{
"turn_id": 3,
"turn_domain": [
"酒店"
],
"user_utterance": "哦，好的。还有酒店，帮我推荐个价位中等的商务酒店！",
"system_utterance": "推荐苏州金鸡湖李公堤瑞贝庭公寓酒店，在金鸡湖景区附近。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区",
"酒店-价位": "中等",
"酒店-酒店类型": "商务 出行"
},
"turn_inform": {
"酒店-价位": "中等",
"酒店-酒店类型": "商务 出行"
},
"turn request": []
},
"user_actions": [
[
"Inform",
"酒店",
"价位",
"中等"
],
[
"Inform",
"酒店",
"酒店类型",
"商务 出行"
],
[
"General",
"酒店",
"",
""
]
],
"system_actions": [
[
"Recommend",
"酒店",
"名称",
"苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
],
[
"General",
"通用",
"",
""
]
],
"db_results": [
"数据库检索结果：成功匹配个数为16",
"{'名称': '苏州慢享主题酒店', '区域': '姑苏区', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '收费', '房费': '266元', '地址': '苏州姑苏区景德路26-64号', '电话号码': '0512-67570999', '评分': 4.7}",
"{'名称': '苏州慢享主题酒店', '区域': '姑苏区', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '收费', '房费': '278元', '地址': '苏州姑苏区景德路26-64号', '电话号码': '0512-67570999', '评分': 4.7}",
"{'名称': '美锦酒店', '区域': '高新区', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '免费', '房费': '308元', '地址': '苏州高新区滨河路999号花样年喜年生活广场5栋1层', '电话号码': '0512-66053331', '评分': 4.8}",
"{'名称': '美锦酒店', '区域': '高新区', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '免费', '房费': '349元', '地址': '苏州高新区滨河路999号花样年喜年生活广场5栋1层', '电话号码': '0512-66053331', '评分': 4.8}",
"{'名称': '苏州金鸡湖李公堤瑞贝庭公寓酒店', '区域': '工业园区', '星级': '4', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '免费', '房费': '438元', '地址': '苏州工业园区李公堤三期E区商业街9幢', '电话号码': '0512-69995666', '评分': 4.6}",
"{'名称': '苏州金鸡湖李公堤瑞贝庭公寓酒店', '区域': '工业园区', '星级': '4', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '免费', '房费': '438元', '地址': '苏州工业园区李公堤三期E区商业街9幢', '电话号码': '0512-69995666', '评分': 4.6}",
"{'名称': '苏州途乐酒店公寓', '区域': '工业园区', '星级': '2', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '收费', '房费': '486元', '地址': '苏州工业园区苏州丰隆城市中心T1楼', '电话号码': '151-5149-7911', '评分': 4.6}",
"{'名称': '苏州途乐酒店公寓', '区域': '工业园区', '星级': '2', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '收费', '房费': '486元', '地址': '苏州工业园区苏州丰隆城市中心T1楼', '电话号码': '151-5149-7911', '评分': 4.6}",
"{'名称': '万悦酒店', '区域': '吴中区', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '免费', '房费': '346元', '地址': '苏州吴中区金山路47-2号', '电话号码': '0512-83808380', '评分': 4.5}",
"{'名称': '万悦酒店', '区域': '吴中区', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '免费', '房费': '338元', '地址': '苏州吴中区金山路47-2号', '电话号码': '0512-83808380', '评分': 4.5}",
"{'名称': '周庄多瓦台临河客栈', '区域': '昆山', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '收费', '房费': '279元', '地址': '昆山周庄镇东浜村75号', '电话号码': '181-3619-1632', '评分': 4.8}",
"{'名称': '周庄多瓦台临河客栈', '区域': '昆山', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '收费', '房费': '279元', '地址': '昆山周庄镇东浜村75号', '电话号码': '181-3619-1632', '评分': 4.8}",
"{'名称': '常熟长江路亚朵酒店', '区域': '常熟', '星级': '4', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '免费', '房费': '312元', '地址': '常熟长江路268号', '电话号码': '0512-51661666', '评分': 4.8}",
"{'名称': '常熟长江路亚朵酒店', '区域': '常熟', '星级': '4', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '免费', '房费': '312元', '地址': '常熟长江路268号', '电话号码': '0512-51661666', '评分': 4.8}",
"{'名称': '维也纳酒店', '区域': '常熟', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '免费', '房费': '322元', '地址': '常熟碧溪镇金港路8号', '电话号码': '0512-52018188', '评分': 4.8}",
"{'名称': '维也纳酒店', '区域': '常熟', '星级': '3', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '免费', '房费': '340元', '地址': '常熟碧溪镇金港路8号', '电话号码': '0512-52018188', '评分': 4.8}"
],
"segmented_user_utterance": "哦 ， 好 的 。 还有 酒店 ， 帮 我 推荐 个 价位 中等 的 商务酒店 ！",
"segmented_system_utterance": "推荐 苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店 ， 在 金鸡湖 景区 附近 。"
},
{
"turn_id": 4,
"turn_domain": [
"酒店"
],
"user_utterance": "你想得真周到!这家酒店有停车场吗？",
"system_utterance": "酒店配备有一个免费的停车场。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区",
"酒店-价位": "中等",
"酒店-酒店类型": "商务 出行",
"酒店-名称": "苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
},
"turn_inform": {
"酒店-名称": "苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
},
"turn request": [
"停车场"
]
},
"user_actions": [
[
"Inform",
"酒店",
"名称",
"苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
],
[
"Request",
"酒店",
"停车场",
""
]
],
"system_actions": [
[
"Inform",
"酒店",
"停车场",
"免费"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为2",
"{'名称': '苏州金鸡湖李公堤瑞贝庭公寓酒店', '区域': '工业园区', '星级': '4', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '免费', '房费': '438元', '地址': '苏州工业园区李公堤三期E区商业街9幢', '电话号码': '0512-69995666', '评分': 4.6}",
"{'名称': '苏州金鸡湖李公堤瑞贝庭公寓酒店', '区域': '工业园区', '星级': '4', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '免费', '房费': '438元', '地址': '苏州工业园区李公堤三期E区商业街9幢', '电话号码': '0512-69995666', '评分': 4.6}"
],
"segmented_user_utterance": "你 想 得 真 周到 ! 这家 酒店 有 停车场 吗 ？",
"segmented_system_utterance": "酒店 配备 有 一个 免费 的 停车场 。"
},
{
"turn_id": 5,
"turn_domain": [
"酒店"
],
"user_utterance": "酒店的电话告诉我一下。",
"system_utterance": "电话号码：0512-69995666。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区",
"酒店-价位": "中等",
"酒店-酒店类型": "商务 出行",
"酒店-名称": "苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
},
"turn_inform": {},
"turn request": [
"电话号码"
]
},
"user_actions": [
[
"Request",
"酒店",
"电话号码",
""
]
],
"system_actions": [
[
"Inform",
"酒店",
"电话号码",
"0512 - 69995666"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为2",
"{'名称': '苏州金鸡湖李公堤瑞贝庭公寓酒店', '区域': '工业园区', '星级': '4', '价位': '中等', '酒店类型': '商务出行', '房型': '大床房', '停车场': '免费', '房费': '438元', '地址': '苏州工业园区李公堤三期E区商业街9幢', '电话号码': '0512-69995666', '评分': 4.6}",
"{'名称': '苏州金鸡湖李公堤瑞贝庭公寓酒店', '区域': '工业园区', '星级': '4', '价位': '中等', '酒店类型': '商务出行', '房型': '标准间', '停车场': '免费', '房费': '438元', '地址': '苏州工业园区李公堤三期E区商业街9幢', '电话号码': '0512-69995666', '评分': 4.6}"
],
"segmented_user_utterance": "酒店 的 电话 告诉 我 一下 。",
"segmented_system_utterance": "电话号码 ： 0512 - 69995666 。"
},
{
"turn_id": 6,
"turn_domain": [
"餐厅"
],
"user_utterance": "嗯，我还想拔草美食。有没有价位中等的江浙菜餐厅推荐一个。",
"system_utterance": "推荐老枫庭。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区",
"餐厅-菜系": "江浙 菜",
"餐厅-价位": "中等",
"酒店-价位": "中等",
"酒店-酒店类型": "商务 出行",
"酒店-名称": "苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
},
"turn_inform": {
"餐厅-菜系": "江浙 菜",
"餐厅-价位": "中等"
},
"turn request": []
},
"user_actions": [
[
"Inform",
"餐厅",
"菜系",
"江浙 菜"
],
[
"Inform",
"餐厅",
"价位",
"中等"
],
[
"General",
"餐厅",
"",
""
]
],
"system_actions": [
[
"Recommend",
"餐厅",
"名称",
"老枫庭"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为3",
"{'名称': '老枫庭', '区域': '吴中区', '菜系': '江浙菜', '价位': '中等', '是否地铁直达': '否', '人均消费': '94元', '地址': '木渎灵天路55号芭提雅休闲娱乐广场5号楼', '电话号码': '0512-66277557', '评分': 4.6, '营业时间': '周一至周日 11:00-13:30 17:00-20:30', '推荐菜': '松鼠桂鱼'}",
"{'名称': '同里老家', '区域': '吴江', '菜系': '江浙菜', '价位': '中等', '是否地铁直达': '否', '人均消费': '87元', '地址': '同里镇环湖西路318号', '电话号码': '0512-63339777', '评分': 4.5, '营业时间': '周一至周日 10:00-22:00', '推荐菜': '太湖三白'}",
"{'名称': '周庄花间堂桔梗餐厅', '区域': '昆山', '菜系': '江浙菜', '价位': '中等', '是否地铁直达': '否', '人均消费': '98元', '地址': '周庄镇中市街110号景点迷楼北10米', '电话号码': '138-1289-9961', '评分': 4.5, '营业时间': '周一至周日 07:00-20:30', '推荐菜': '银鱼炒蛋'}"
],
"segmented_user_utterance": "嗯 ， 我 还 想 拔草 美食 。 有没有 价位 中等 的 江浙 菜 餐厅 推荐 一个 。",
"segmented_system_utterance": "推荐 老枫庭 。"
},
{
"turn_id": 7,
"turn_domain": [
"餐厅"
],
"user_utterance": "这家餐厅地铁直达吗？",
"system_utterance": "抱歉，餐厅没有地铁直达!",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区",
"餐厅-菜系": "江浙 菜",
"餐厅-价位": "中等",
"餐厅-名称": "老枫庭",
"酒店-价位": "中等",
"酒店-酒店类型": "商务 出行",
"酒店-名称": "苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
},
"turn_inform": {
"餐厅-名称": "老枫庭"
},
"turn request": [
"是否地铁直达"
]
},
"user_actions": [
[
"Inform",
"餐厅",
"名称",
"老枫庭"
],
[
"Request",
"餐厅",
"是否地铁直达",
""
]
],
"system_actions": [
[
"Inform",
"餐厅",
"是否地铁直达",
"否"
],
[
"General",
"通用",
"",
""
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '老枫庭', '区域': '吴中区', '菜系': '江浙菜', '价位': '中等', '是否地铁直达': '否', '人均消费': '94元', '地址': '木渎灵天路55号芭提雅休闲娱乐广场5号楼', '电话号码': '0512-66277557', '评分': 4.6, '营业时间': '周一至周日 11:00-13:30 17:00-20:30', '推荐菜': '松鼠桂鱼'}"
],
"segmented_user_utterance": "这家 餐厅 地铁 直达 吗 ？",
"segmented_system_utterance": "抱歉 ， 餐厅 没有 地铁 直达 !"
},
{
"turn_id": 8,
"turn_domain": [
"餐厅"
],
"user_utterance": "人均消费呢？",
"system_utterance": "老枫庭人均消费在94元左右。",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区",
"餐厅-菜系": "江浙 菜",
"餐厅-价位": "中等",
"餐厅-名称": "老枫庭",
"酒店-价位": "中等",
"酒店-酒店类型": "商务 出行",
"酒店-名称": "苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
},
"turn_inform": {},
"turn request": [
"人均消费"
]
},
"user_actions": [
[
"Request",
"餐厅",
"人均消费",
""
]
],
"system_actions": [
[
"Inform",
"餐厅",
"人均消费",
"老枫庭"
]
],
"db_results": [
"数据库检索结果：成功匹配个数为1",
"{'名称': '老枫庭', '区域': '吴中区', '菜系': '江浙菜', '价位': '中等', '是否地铁直达': '否', '人均消费': '94元', '地址': '木渎灵天路55号芭提雅休闲娱乐广场5号楼', '电话号码': '0512-66277557', '评分': 4.6, '营业时间': '周一至周日 11:00-13:30 17:00-20:30', '推荐菜': '松鼠桂鱼'}"
],
"segmented_user_utterance": "人均 消费 呢 ？",
"segmented_system_utterance": "老枫庭 人均 消费 在 94 元 左右 。"
},
{
"turn_id": 9,
"turn_domain": [
"通用"
],
"user_utterance": "好，所有问题都解决了，谢谢你的帮助！再见！",
"system_utterance": "不客气！这是我应该做的！再见！",
"belief_state": {
"inform slot-values": {
"旅游景点-景点类型": "山水 景区",
"旅游景点-消费": "偏贵",
"旅游景点-名称": "金鸡湖 景区",
"餐厅-菜系": "江浙 菜",
"餐厅-价位": "中等",
"餐厅-名称": "老枫庭",
"酒店-价位": "中等",
"酒店-酒店类型": "商务 出行",
"酒店-名称": "苏州 金鸡湖 李公堤 瑞贝庭 公寓 酒店"
},
"turn_inform": {},
"turn request": []
},
"user_actions": [
[
"Bye",
"通用",
"",
""
],
[
"General",
"通用",
"",
""
]
],
"system_actions": [
[
"Bye",
"通用",
"",
""
],
[
"General",
"通用",
"",
""
]
],
"db_results": [],
"segmented_user_utterance": "好 ， 所有 问题 都 解决 了 ， 谢谢 你 的 帮助 ！ 再见 ！",
"segmented_system_utterance": "不 客气 ！ 这 是 我 应该 做 的 ！ 再见 ！"
}
]
}
```
## Dataset in GEM
### Rationale for Inclusion in GEM
#### Why is the Dataset in GEM?
<!-- info: What does this dataset contribute toward better generation evaluation and why is it part of GEM? -->
<!-- scope: microscope -->
RiSAWOZ is the first large-scale multi-domain Chinese Wizard-of-Oz dataset with rich semantic annotations.
#### Similar Datasets
<!-- info: Do other datasets for the high level task exist? -->
<!-- scope: telescope -->
yes
#### Unique Language Coverage
<!-- info: Does this dataset cover other languages than other datasets for the same task? -->
<!-- scope: periscope -->
no
#### Difference from other GEM datasets
<!-- info: What else sets this dataset apart from other similar datasets in GEM? -->
<!-- scope: microscope -->
The corpus contains rich semantic annotations, such as ellipsis and coreference, in addition to traditional dialogue annotations (dialogue states, dialogue acts, etc.), which can be used in various tasks in dialogue system.
#### Ability that the Dataset measures
<!-- info: What aspect of model ability can be measured with this dataset? -->
<!-- scope: periscope -->
Natural Language Understanding, Dialogue State Tracking, Dialogue Context-to-Text Generation, Coreference Resolution, Unified Generative Ellipsis and Coreference Resolution
### GEM-Specific Curation
#### Modificatied for GEM?
<!-- info: Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data? -->
<!-- scope: telescope -->
no
#### Additional Splits?
<!-- info: Does GEM provide additional splits to the dataset? -->
<!-- scope: telescope -->
no
### Getting Started with the Task
#### Pointers to Resources
<!-- info: Getting started with in-depth research on the task. Add relevant pointers to resources that researchers can consult when they want to get started digging deeper into the task. -->
<!-- scope: microscope -->
[Website](https://terryqj0107.github.io/RiSAWOZ_webpage)
#### Technical Terms
<!-- info: Technical terms used in this card and the dataset and their definitions -->
<!-- scope: microscope -->
- In task-oriented dialogue system, the Natural Language Understanding (NLU) module aims to convert the user utterance into the representation that computer can understand, which includes intent and dialogue act (slot & value) detection.
- Dialogue State Tracking (DST) is a core component in task-oriented dialogue systems, which extracts dialogue states (user goals) embedded in dialogue context. It has progressed toward open-vocabulary or generation-based DST where state-of-the-art models can generate dialogue states from dialogue context directly.
- Context-to-Text Generation: encoding dialogue context to decode system response.
- Coreference Resolution: predict coreference clusters where all mentions are referring to the same entity for each dialogue.
- Unified Generative Ellipsis and Coreference Resolution: generating omitted or referred expressions from the dialogue context.
## Previous Results
### Previous Results
#### Measured Model Abilities
<!-- info: What aspect of model ability can be measured with this dataset? -->
<!-- scope: telescope -->
Natural Language Understanding, Dialogue State Tracking, Dialogue Context-to-Text Generation, Coreference Resolution, Unified Generative Ellipsis and Coreference Resolution
#### Metrics
<!-- info: What metrics are typically used for this task? -->
<!-- scope: periscope -->
`Other: Other Metrics`
#### Other Metrics
<!-- info: Definitions of other metrics -->
<!-- scope: periscope -->
- Natural Language Understanding:
- F1 score: F1 score of user intent.
- Dialogue State Tracking:
- Joint Accuracy: accuracy of turn-level dialogue states.
- Dialogue Context-to-Text Generation:
- inform rate: measures the percentage that the output contains the appropriate entity the user asks for.
- success rate: estimates the proportion that all the requested attributes have been answered.
- BLEU: the BLEU score of generated system response.
- Combined Score: (inform + success) ∗ 0.5 + BLEU as an overall
quality.
- Coreference Resolution:
- MUC F1 Score: a link-based metric. Mentions in the same entity/cluster are considered “linked”. MUC penalizes the missing links and incorrect links, each with the same weight.
- B3 F1 Score: a mention-based metric.The evaluation score depends on the fraction of the correct mentions included in the response entities (i.e. entities created by the system).
- CEAFφ4 F1 Score: a metric which assumes each key entity should only be mapped to one response entity, and vice versa. It aligns the key entities (clusters) with the response entities in the best way, and compute scores from that alignment.
- Average F1 Score: an average F1 score of the above three metrics.
- Unified Generative Ellipsis and Coreference Resolution:
- Exact Match Rate: measures whether the generated utterances exactly match the ground-truth utterances.
- BLEU: the BLEU score of generated utterances
- Resolution F1: comparing machine-generated words with ground-truth words only from the ellipsis/coreference part of user utterances.
#### Proposed Evaluation
<!-- info: List and describe the purpose of the metrics and evaluation methodology (including human evaluation) that the dataset creators used when introducing this task. -->
<!-- scope: microscope -->
see "Definitions of other metrics"
#### Previous results available?
<!-- info: Are previous results available? -->
<!-- scope: telescope -->
yes
#### Other Evaluation Approaches
<!-- info: What evaluation approaches have others used? -->
<!-- scope: periscope -->
same as our dataset
#### Relevant Previous Results
<!-- info: What are the most relevant previous results for this task/dataset? -->
<!-- scope: microscope -->
Joint Accuracy, Inform Rate, Success Rate, BLEU Score and Combined Score on MultiWOZ and CrossWOZ dataset.
## Dataset Curation
### Original Curation
#### Original Curation Rationale
<!-- info: Original curation rationale -->
<!-- scope: telescope -->
Gather human-to-human dialog in Chinese.
#### Communicative Goal
<!-- info: What was the communicative goal? -->
<!-- scope: periscope -->
Generate system response given dialogue context across multiple domains.
#### Sourced from Different Sources
<!-- info: Is the dataset aggregated from different data sources? -->
<!-- scope: telescope -->
no
### Language Data
#### How was Language Data Obtained?
<!-- info: How was the language data obtained? -->
<!-- scope: telescope -->
`Crowdsourced`
#### Where was it crowdsourced?
<!-- info: If crowdsourced, where from? -->
<!-- scope: periscope -->
`Other crowdworker platform`
#### Topics Covered
<!-- info: Does the language in the dataset focus on specific topics? How would you describe them? -->
<!-- scope: periscope -->
domains: Attraction, Restaurant, Hotel, Flight, Train, Weather, Movie, TV, Computer, Car, Hospital, Courses
#### Data Validation
<!-- info: Was the text validated by a different worker or a data curator? -->
<!-- scope: telescope -->
validated by data curator
#### Was Data Filtered?
<!-- info: Were text instances selected or filtered? -->
<!-- scope: telescope -->
hybrid
#### Filter Criteria
<!-- info: What were the selection criteria? -->
<!-- scope: microscope -->
Rule-based and manual selection criteria
### Structured Annotations
#### Additional Annotations?
<!-- quick -->
<!-- info: Does the dataset have additional annotations for each instance? -->
<!-- scope: telescope -->
crowd-sourced
#### Number of Raters
<!-- info: What is the number of raters -->
<!-- scope: telescope -->
51<n<100
#### Rater Qualifications
<!-- info: Describe the qualifications required of an annotator. -->
<!-- scope: periscope -->
Chinese native speaker
#### Raters per Training Example
<!-- info: How many annotators saw each training example? -->
<!-- scope: periscope -->
3
#### Raters per Test Example
<!-- info: How many annotators saw each test example? -->
<!-- scope: periscope -->
3
#### Annotation Service?
<!-- info: Was an annotation service used? -->
<!-- scope: telescope -->
no
#### Annotation Values
<!-- info: Purpose and values for each annotation -->
<!-- scope: microscope -->
- dialogue_id (string): dialogue ID
- goal (string): natural language descriptions of the user goal
- domains (list of strings): domains mentioned in current dialogue session
- turn_id (int): turn ID
- turn_domain (list of strings): domain mentioned in current turn
- belief_state (dict): dialogue state, including:
- inform slot-values (dict): the slots and corresponding values informed until current turn
- turn_inform (dict): the slots and corresponding values informed in current turn
- turn request (dict): the slots requested in current turn
- user_actions (list of lists): user dialogue acts in current turn
- user_actions (list of lists): system dialogue acts in current turn
- db_results (list of strings): database search results
- segmented_user_utterance (string): word segmentation result of user utterance
- segmented_system_utterance (string): word segmentation result of system utterance
#### Any Quality Control?
<!-- info: Quality control measures? -->
<!-- scope: telescope -->
unknown
### Consent
#### Any Consent Policy?
<!-- info: Was there a consent policy involved when gathering the data? -->
<!-- scope: telescope -->
yes
#### Consent Policy Details
<!-- info: What was the consent policy? -->
<!-- scope: microscope -->
Annotators agree using the dataset for research purpose.
#### Other Consented Downstream Use
<!-- info: What other downstream uses of the data did the original data creators and the data curators consent to? -->
<!-- scope: microscope -->
Any
### Private Identifying Information (PII)
#### Contains PII?
<!-- quick -->
<!-- info: Does the source language data likely contain Personal Identifying Information about the data creators or subjects? -->
<!-- scope: telescope -->
no PII
#### Justification for no PII
<!-- info: Provide a justification for selecting `no PII` above. -->
<!-- scope: periscope -->
The slots and values as well as utterances do not contain any personal information.
### Maintenance
#### Any Maintenance Plan?
<!-- info: Does the original dataset have a maintenance plan? -->
<!-- scope: telescope -->
yes
#### Maintenance Plan Details
<!-- info: Describe the original dataset's maintenance plan. -->
<!-- scope: microscope -->
Building a leaderboard webpage to trace and display the latest results on the [dataset](https://terryqj0107.github.io/RiSAWOZ_webpage/)
#### Maintainer Contact Information
<!-- info: Provide contact information of a person responsible for the dataset maintenance -->
<!-- scope: periscope -->
Deyi Xiong (dyxiong@tju.edu.cn)
#### Any Contestation Mechanism?
<!-- info: Does the maintenance plan include a contestation mechanism allowing individuals to request removal fo content? -->
<!-- scope: periscope -->
contact maintainer
#### Contestation Form Link
<!-- info: Provide the form link or contact information -->
<!-- scope: periscope -->
Deyi Xiong (dyxiong@tju.edu.cn)
## Broader Social Context
### Previous Work on the Social Impact of the Dataset
#### Usage of Models based on the Data
<!-- info: Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems? -->
<!-- scope: telescope -->
no
### Impact on Under-Served Communities
#### Addresses needs of underserved Communities?
<!-- info: Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models). -->
<!-- scope: telescope -->
yes
#### Details on how Dataset Addresses the Needs
<!-- info: Describe how this dataset addresses the needs of underserved communities. -->
<!-- scope: microscope -->
RiSAWOZ is the first large-scale multi-domain Chinese Wizard-of-Oz dataset with rich semantic annotations.
### Discussion of Biases
#### Any Documented Social Biases?
<!-- info: Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group. -->
<!-- scope: telescope -->
no
#### Are the Language Producers Representative of the Language?
<!-- info: Does the distribution of language producers in the dataset accurately represent the full distribution of speakers of the language world-wide? If not, how does it differ? -->
<!-- scope: periscope -->
yes
## Considerations for Using the Data
### PII Risks and Liability
#### Potential PII Risk
<!-- info: Considering your answers to the PII part of the Data Curation Section, describe any potential privacy to the data subjects and creators risks when using the dataset. -->
<!-- scope: microscope -->
None
### Licenses
#### Copyright Restrictions on the Dataset
<!-- info: Based on your answers in the Intended Use part of the Data Overview Section, which of the following best describe the copyright and licensing status of the dataset? -->
<!-- scope: periscope -->
`open license - commercial use allowed`
#### Copyright Restrictions on the Language Data
<!-- info: Based on your answers in the Language part of the Data Curation Section, which of the following best describe the copyright and licensing status of the underlying language data? -->
<!-- scope: periscope -->
`open license - commercial use allowed`
### Known Technical Limitations
#### Technical Limitations
<!-- info: Describe any known technical limitations, such as spurrious correlations, train/test overlap, annotation biases, or mis-annotations, and cite the works that first identified these limitations when possible. -->
<!-- scope: microscope -->
None
#### Unsuited Applications
<!-- info: When using a model trained on this dataset in a setting where users or the public may interact with its predictions, what are some pitfalls to look out for? In particular, describe some applications of the general task featured in this dataset that its curation or properties make it less suitable for. -->
<!-- scope: microscope -->
Using the trained model on domains that are not included in the 12 domains selected for this dataset.
#### Discouraged Use Cases
<!-- info: What are some discouraged use cases of a model trained to maximize the proposed metrics on this dataset? In particular, think about settings where decisions made by a model that performs reasonably well on the metric my still have strong negative consequences for user or members of the public. -->
<!-- scope: microscope -->
Designing models that leverage unknown bias in the dataset to optimize specific metrics.
|
true |
# klej-psc
## Description
The Polish Summaries Corpus (PSC) is a dataset of summaries for 569 news articles. The human annotators created five extractive summaries for each article by choosing approximately 5% of the original text. A different annotator created each summary. The subset of 154 articles was also supplemented with additional five abstractive summaries each, i.e., not created from the fragments of the original article. In huggingface version of this dataset, summaries of the same article are used as positive pairs, and the most similar summaries of different articles are sampled as negatives.
## Tasks (input, output, and metrics)
The task is to predict whether the extract text and summary are similar.
Based on PSC, we formulate a text-similarity task. We generate the positive pairs (i.e., referring
to the same article) using only those news articles with both extractive and abstractive summaries. We match each extractive summary with two least similar abstractive ones of the same article. To create negative pairs, we follow a similar procedure. We find two most similar abstractive summaries for each extractive summary, but from different articles.
**Input** (*'extract_text'*, *'summary_text'* columns): extract text and summary text sentences
**Output** (*'label'* column): label: 1 indicates summary is similar, 0 means that it is not similar
**Domain**: News articles
**Measurements**: F1-Score
**Example**:
Input: `Mit o potopie jest prastary, sięga czasów, gdy topniał lodowiec. Na skutek tego wydarzenia w dziejach planety, poziom mórz i oceanów podniósł się o kilkadziesiąt metrów. Potop polodowcowy z całą, naukową pewnością, miał miejsce, ale najprawdopodobniej został przez ludzkość przegapiony. I oto pojawiła się w tej sprawie kolejna glosa. Jej autorami są amerykańscy geofizycy.` ; `Dwójka amerykańskich geofizyków przedstawiła swój scenariusz pochodzenia mitu o potopie. Przed 7500 laty do będącego jeszcze jeziorem Morza Czarnego wlały się wezbrane wskutek topnienia lodowców wody Morza Śródziemnego. Geofizycy twierdzą, że dzięki temu rozkwitło rolnictwo, bo ludzie musieli migrować i szerzyć rolniczy tryb życia. Środowiska naukowe twierdzą jednak, że potop był tylko jednym z czynników ekspansji rolnictwa.`
Input (translated by DeepL): `The myth of the Flood is ancient, dating back to the time when the glacier melted. As a result of this event in the history of the planet, the level of the seas and oceans rose by several tens of meters. The post-glacial flood with all, scientific certainty, took place, but was most likely missed by mankind. And here is another gloss on the matter. Its authors are American geophysicists.` ; `Two American geophysicists presented their scenario of the origin of the Flood myth. 7500 years ago, the waters of the Mediterranean Sea flooded into the Black Sea, which was still a lake, due to the melting of glaciers. Geophysicists claim that this made agriculture flourish because people had to migrate and spread their agricultural lifestyle. However, the scientific community argues that the Flood was only one factor in the expansion of agriculture.`
Output: `1` (summary is similar)
## Data splits
| Subset | Cardinality |
| ----------- | ----------: |
| train | 4302 |
| val | 0 |
| test | 1078 |
## Class distribution
| Class | train | validation | test |
|:------------|--------:|-------------:|-------:|
| not similar | 0.705 | - | 0.696 |
| similar | 0.295 | - | 0.304 |
## Citation
```
@inproceedings{ogro:kop:14:lrec,
title={The {P}olish {S}ummaries {C}orpus},
author={Ogrodniczuk, Maciej and Kope{'c}, Mateusz},
booktitle = "Proceedings of the Ninth International {C}onference on {L}anguage {R}esources and {E}valuation, {LREC}~2014",
year = "2014",
}
```
## License
```
Creative Commons Attribution ShareAlike 3.0 licence (CC-BY-SA 3.0)
```
## Links
[HuggingFace](https://huggingface.co/datasets/allegro/klej-psc)
[Source](http://zil.ipipan.waw.pl/PolishSummariesCorpus)
[Paper](https://aclanthology.org/L14-1145/)
## Examples
### Loading
```python
from pprint import pprint
from datasets import load_dataset
dataset = load_dataset("allegro/klej-psc")
pprint(dataset['train'][100])
#{'extract_text': 'Nowe prawo energetyczne jest zagrożeniem dla małych '
# 'producentów energii ze źródeł odnawialnych. Sytuacja się '
# 'pogarsza wdobie urynkowienia energii. zniosło preferencje '
# 'wprowadzone dla energetyki wodnej. UE zamierza podwoić '
# 'udział takich źródeł energetyki jak woda, wiatr, słońce do '
# '2010 r.W Polsce 1-1,5 proc. zużycia energii wytwarza się ze '
# 'źródeł odnawialnych. W krajach Unii udział ten wynosi '
# 'średnio 5,6 proc.',
# 'label': 1,
# 'summary_text': 'W Polsce w niewielkim stopniu wykorzystuje się elektrownie '
# 'wodne oraz inne sposoby tworzenia energii ze źródeł '
# 'odnawialnych. Podczas gdy w innych krajach europejskich jest '
# 'to średnio 5,6 % w Polsce jest to 1-1,5 %. Powodem jest '
# 'niska opłacalność posiadania tego typu elektrowni-zakład '
# 'energetyczny płaci ok. 17 gr. za 1kWh, podczas gdy '
# 'wybudowanie takiej elektrowni kosztuje ok. 100 tyś. zł.'}
```
### Evaluation
```python
import random
from pprint import pprint
from datasets import load_dataset, load_metric
dataset = load_dataset("allegro/klej-psc")
dataset = dataset.class_encode_column("label")
references = dataset["test"]["label"]
# generate random predictions
predictions = [random.randrange(max(references) + 1) for _ in range(len(references))]
acc = load_metric("accuracy")
f1 = load_metric("f1")
acc_score = acc.compute(predictions=predictions, references=references)
f1_score = f1.compute(predictions=predictions, references=references, average="macro")
pprint(acc_score)
pprint(f1_score)
# {'accuracy': 0.18588469184890655}
# {'f1': 0.17511412402843068}
``` |
false |
# Dataset Card for Shadertoys
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Source Data](#source-data)
- [Licensing Information](#licensing-information)
## Dataset Description
- **Repository:** https://github.com/Vipitis/project (private placeholder)
### Dataset Summary
The Shadertoys dataset contains over 44k renderpasses collected from the Shadertoy.com API. Some shader programm contain multiple render passes.
To browse a subset of this dataset, look at the [ShaderEval](https://huggingface.co/spaces/Vipitis/ShaderCoder) space. A finer variant of this dataset is [Shadertoys-fine](https://huggingface.co/datasets/Vipitis/Shadertoys-fine).
### Supported Tasks and Leaderboards
`text-generation` the dataset can be used to train generative language models, for code completion tasks.
`ShaderEval` [task1](https://huggingface.co/spaces/Vipitis/ShaderEval) from ShaderEval uses a dataset derived from Shadertoys to test return completion of autoregressive language models.
### Languages
- English (title, description, tags, comments)
- Shadercode **programming** language, a subset of GLSL specifically for Shadertoy.com
## Dataset Structure
### Data Instances
A data point consists of the whole shadercode, some information from the API as well as additional metadata.
```
{
'num_passes': 1,
'has_inputs': False,
'name': 'Image',
'type': 'image',
'code': '<full code>',
'title': '<title of the shader>',
'description': '<description of the shader>',
'tags': ['tag1','tag2','tag3', ... ],
'license': 'unknown',
'author': '<username>',
'source': 'https://shadertoy.com/view/<shaderID>'
}
```
### Data Fields
- 'num_passes' number of passes the parent shader program has
- 'has_inputs' if any inputs were used like textures, audio streams,
- 'name' Name of the renderpass, usually Image, Buffer A, Common, etc
- 'type' type of the renderpass; one of `{'buffer', 'common', 'cubemap', 'image', 'sound'}`
- 'code' the raw code (including comments) the whole renderpass.
- 'title' Name of the Shader
- 'description' description given for the Shader
- 'tags' List of tags assigned to the Shader (by it's creator); there are more than 10000 unique tags.
- 'license' currently in development
- 'author' username of the shader author
- 'source' URL to the shader. Not to the specific renderpass.
### Data Splits
Currently available (shuffled):
- train (85.0%)
- test (15.0%)
## Dataset Creation
Data retrieved starting 2022-07-20
### Source Data
#### Initial Data Collection and Normalization
All data was collected via the [Shadertoy.com API](https://www.shadertoy.com/howto#q2) and then iterated over the items in 'renderpass' while adding some of the fields from 'info'.
The code to generate these datasets should be published on the GitHub repository in the near future.
#### Who are the source language producers?
Shadertoy.com contributers which publish shaders as 'public+API'
## Licensing Information
The Default [license for each Shader](https://www.shadertoy.com/terms) is CC BY-NC-SA 3.0. However, some Shaders might have a different license attached.
The Dataset is currently not filtering for any licenses but gives a license tag, if easily recognizeable by naive means.
Please check the first comment of each shader program yourself as to not violate any copyrights for downstream use. The main license requires share alike and by attribution.
Attribution of every data field can be found in the 'author' column, but might not include further attribution within the code itself or parents from forked shaders. |
false |
# Dataset Card for [EDGAR-CORPUS]
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Licensing Information](#licensing-information)
- [References](#references)
- [Contributions](#contributions)
## Dataset Description
- **Point of Contact: Lefteris Loukas**
### Dataset Summary
This dataset card is based on the paper **EDGAR-CORPUS: Billions of Tokens Make The World Go Round** authored by _Lefteris Loukas et.al_, as published in the _ECONLP 2021_ workshop.
This dataset contains the annual reports of public companies from 1993-2020 from SEC EDGAR filings.
There is supported functionality to load a specific year.
Care: since this is a corpus dataset, different `train/val/test` splits do not have any special meaning. It's the default HF card format to have train/val/test splits.
If you wish to load specific year(s) of specific companies, you probably want to use the open-source software which generated this dataset, EDGAR-CRAWLER: https://github.com/nlpaueb/edgar-crawler.
## Citation
If this work helps or inspires you in any way, please consider citing the relevant paper published at the [3rd Economics and Natural Language Processing (ECONLP) workshop](https://lt3.ugent.be/econlp/) at EMNLP 2021 (Punta Cana, Dominican Republic):
```
@inproceedings{loukas-etal-2021-edgar,
title = "{EDGAR}-{CORPUS}: Billions of Tokens Make The World Go Round",
author = "Loukas, Lefteris and
Fergadiotis, Manos and
Androutsopoulos, Ion and
Malakasiotis, Prodromos",
booktitle = "Proceedings of the Third Workshop on Economics and Natural Language Processing",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.econlp-1.2",
pages = "13--18",
}
```
### Supported Tasks
This is a raw dataset/corpus for financial NLP.
As such, there are no annotations or labels.
### Languages
The EDGAR Filings are in English.
## Dataset Structure
### Data Instances
Refer to the dataset preview.
### Data Fields
**filename**: Name of file on EDGAR from which the report was extracted.<br>
**cik**: EDGAR identifier for a firm.<br>
**year**: Year of report.<br>
**section_1**: Corressponding section of the Annual Report.<br>
**section_1A**: Corressponding section of the Annual Report.<br>
**section_1B**: Corressponding section of the Annual Report.<br>
**section_2**: Corressponding section of the Annual Report.<br>
**section_3**: Corressponding section of the Annual Report.<br>
**section_4**: Corressponding section of the Annual Report.<br>
**section_5**: Corressponding section of the Annual Report.<br>
**section_6**: Corressponding section of the Annual Report.<br>
**section_7**: Corressponding section of the Annual Report.<br>
**section_7A**: Corressponding section of the Annual Report.<br>
**section_8**: Corressponding section of the Annual Report.<br>
**section_9**: Corressponding section of the Annual Report.<br>
**section_9A**: Corressponding section of the Annual Report.<br>
**section_9B**: Corressponding section of the Annual Report.<br>
**section_10**: Corressponding section of the Annual Report.<br>
**section_11**: Corressponding section of the Annual Report.<br>
**section_12**: Corressponding section of the Annual Report.<br>
**section_13**: Corressponding section of the Annual Report.<br>
**section_14**: Corressponding section of the Annual Report.<br>
**section_15**: Corressponding section of the Annual Report.<br>
```python
import datasets
# Load the entire dataset
raw_dataset = datasets.load_dataset("eloukas/edgar-corpus", "full")
# Load a specific year and split
year_1993_training_dataset = datasets.load_dataset("eloukas/edgar-corpus", "year_1993", split="train")
```
### Data Splits
| Config | Training | Validation | Test |
| --------- | -------- | ---------- | ------ |
| full | 176,289 | 22,050 | 22,036 |
| year_1993 | 1,060 | 133 | 133 |
| year_1994 | 2,083 | 261 | 260 |
| year_1995 | 4,110 | 514 | 514 |
| year_1996 | 7,589 | 949 | 949 |
| year_1997 | 8,084 | 1,011 | 1,011 |
| year_1998 | 8,040 | 1,006 | 1,005 |
| year_1999 | 7,864 | 984 | 983 |
| year_2000 | 7,589 | 949 | 949 |
| year_2001 | 7,181 | 898 | 898 |
| year_2002 | 6,636 | 830 | 829 |
| year_2003 | 6,672 | 834 | 834 |
| year_2004 | 7,111 | 889 | 889 |
| year_2005 | 7,113 | 890 | 889 |
| year_2006 | 7,064 | 883 | 883 |
| year_2007 | 6,683 | 836 | 835 |
| year_2008 | 7,408 | 927 | 926 |
| year_2009 | 7,336 | 917 | 917 |
| year_2010 | 7,013 | 877 | 877 |
| year_2011 | 6,724 | 841 | 840 |
| year_2012 | 6,479 | 810 | 810 |
| year_2013 | 6,372 | 797 | 796 |
| year_2014 | 6,261 | 783 | 783 |
| year_2015 | 6,028 | 754 | 753 |
| year_2016 | 5,812 | 727 | 727 |
| year_2017 | 5,635 | 705 | 704 |
| year_2018 | 5,508 | 689 | 688 |
| year_2019 | 5,354 | 670 | 669 |
| year_2020 | 5,480 | 686 | 685 |
## Dataset Creation
### Source Data
#### Initial Data Collection and Normalization
Initial data was collected and processed by the authors of the research paper **EDGAR-CORPUS: Billions of Tokens Make The World Go Round**.
#### Who are the source language producers?
Public firms filing with the SEC.
### Annotations
#### Annotation process
NA
#### Who are the annotators?
NA
### Personal and Sensitive Information
The dataset contains public filings data from SEC.
## Considerations for Using the Data
### Social Impact of Dataset
Low to none.
### Discussion of Biases
The dataset is about financial information of public companies and as such the tone and style of text is in line with financial literature.
### Other Known Limitations
The dataset needs further cleaning for improved performance.
## Additional Information
### Licensing Information
EDGAR data is publicly available.
### Shoutout
Huge shoutout to [@JanosAudran](https://huggingface.co/JanosAudran) for the HF Card setup!
### References
- [Research Paper] Lefteris Loukas, Manos Fergadiotis, Ion Androutsopoulos, and, Prodromos Malakasiotis. EDGAR-CORPUS: Billions of Tokens Make The World Go Round. Third Workshop on Economics and Natural Language Processing (ECONLP). https://arxiv.org/abs/2109.14394 - Punta Cana, Dominican Republic, November 2021.
- [Software] Lefteris Loukas, Manos Fergadiotis, Ion Androutsopoulos, and, Prodromos Malakasiotis. EDGAR-CRAWLER. https://github.com/nlpaueb/edgar-crawler (2021)
- [EDGAR CORPUS, but in zip files] EDGAR CORPUS: A corpus for financial NLP research, built from SEC's EDGAR. https://zenodo.org/record/5528490 (2021)
- [Word Embeddings] EDGAR-W2V: Word2vec Embeddings trained on EDGAR-CORPUS. https://zenodo.org/record/5524358 (2021)
- [Applied Research paper where EDGAR-CORPUS is used] Lefteris Loukas, Manos Fergadiotis, Ilias Chalkidis, Eirini Spyropoulou, Prodromos Malakasiotis, Ion Androutsopoulos, and, George Paliouras. FiNER: Financial Numeric Entity Recognition for XBRL Tagging. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/2022.acl-long.303 (2022)
|
false | # Dataset Card for "LaMini-Instruction"
<p align="center" width="100%">
<a><img src="https://raw.githubusercontent.com/mbzuai-nlp/lamini-lm/main/images/lamini.png" alt="Title" style="width: 100%; min-width: 300px; display: block; margin: auto;"></a>
</p>
<p align="center"> <a href="https://twitter.com/WuMinghao_nlp" target="_blank">Minghao Wu</a>, <a href="https://twitter.com/MacAbdul9" target="_blank">Abdul Waheed</a>, <a href="https://chiyuzhang94.github.io/" target="_blank">Chiyu Zhang</a>, <a href="https://mageed.arts.ubc.ca/" target="_blank">Muhammad Abdul-Mageed</a>, <a href="https://afaji.github.io/" target="_blank">Alham Fikri Aji</a>,</p>
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Structure](#dataset-structure)
- [Data Fields](#data-fields)
- [Data Instances](#data-instances)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Additional Information](#additional-information)
## Dataset Description
We distill the knowledge from large language models by performing sentence/offline distillation (Kim and Rush, 2016). We generate a total of **2.58M** pairs of instructions and responses using [`gpt-3.5-turbo`](https://openai.com/api/) based on several existing resources of prompts, including [self-instruct](https://github.com/yizhongw/self-instruct) (Wang et al., 2022), [P3](https://huggingface.co/datasets/bigscience/P3) (Sanh et al., 2022), [FLAN](https://github.com/google-research/FLAN) (Longpre et al., 2023) and [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) (Taori et al., 2023). More information about the process for generating our instruction dataset, please refer to [our paper](https://arxiv.org/abs/2304.14402).
We use LaMini-Instruction to fine-tune various small-sized language models, resulting in [LaMini-LM model series](https://github.com/mbzuai-nlp/laMini-LM#models).
Each sample contain the following two fields:
* `instruction`: `string`, describes the task that the model is expected to perform.
* `response`: `string`, the response to the instruction as generated by `gpt-3.5-turbo`.
* `instruction_source`: `string`, the source of a instruction. The possible values are `{'alpaca', 'generated_flan', 'generated_p3', 'original_flan', 'original_p3', 'self_instruct_with_topic', 'self_instruct_without_topic'}`.
Two examples in our LaMini-instruction data:
```json
{
"instruction": "What is the capital of Australia?\n\nIs Canberra the only city chosen to serve as a capital due to a compromise between Sydney and Melbourne?",
"response": "The capital of Australia is Canberra. Yes, Canberra was chosen as the capital of Australia in 1908 due to a compromise between Sydney and Melbourne, as neither city wanted the other to become the capital.",
"instruction_source": "generated_flan"
}
```
```json
{
"instruction": "Create a poem that has the word \"ocean\" in every other line.",
"response": "The ocean's depth is a mystery,\nIts waves crashing with energy.\nSalt air fills the coastal scene,\nThe ocean's blue hues pure and clean.\n\nSeagulls cry out a melancholy song,\nThe ocean's rhythm steady and strong.\nSunsets paint the water gold,\nThe ocean's secrets forever untold.",
"instruction_source": "self_instruct_without_topic"
}
```
## Considerations for Using the Data
As the output is distilled from ChatGPT, this data contains errors and biases produced by ChatGPT. Models trained with this dataset will inherit the errors and biases. We encourage users to use this data with caution and propose new methods to filter or improve the imperfections.
### Licensing Information
The dataset is available under the [Creative Commons NonCommercial (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/legalcode).
### Citation Information
Please cite us if you use our data or models.
```bibtex
@article{lamini-lm,
author = {Minghao Wu and
Abdul Waheed and
Chiyu Zhang and
Muhammad Abdul-Mageed and
Alham Fikri Aji
},
title = {LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions},
journal = {CoRR},
volume = {abs/2304.14402},
year = {2023},
url = {https://arxiv.org/abs/2304.14402},
eprinttype = {arXiv},
eprint = {2304.14402}
}
``` |
true | |
false |
# Dataset Card for `thainer`
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://github.com/wannaphong/thai-ner
- **Repository:** https://github.com/wannaphong/thai-ner
- **Paper:**
- **Leaderboard:**
- **Point of Contact:** https://github.com/wannaphong/
### Dataset Summary
ThaiNER (v1.3) is a 6,456-sentence named entity recognition dataset created from expanding the 2,258-sentence [unnamed dataset](http://pioneer.chula.ac.th/~awirote/Data-Nutcha.zip) by [Tirasaroj and Aroonmanakun (2012)](http://pioneer.chula.ac.th/~awirote/publications/). It is used to train NER taggers in [PyThaiNLP](https://github.com/PyThaiNLP/pythainlp). The NER tags are annotated by [Tirasaroj and Aroonmanakun (2012)]((http://pioneer.chula.ac.th/~awirote/publications/)) for 2,258 sentences and the rest by [@wannaphong](https://github.com/wannaphong/). The POS tags are done by [PyThaiNLP](https://github.com/PyThaiNLP/pythainlp)'s `perceptron` engine trained on `orchid_ud`. [@wannaphong](https://github.com/wannaphong/) is now the only maintainer of this dataset.
### Supported Tasks and Leaderboards
- named entity recognition
- pos tagging
### Languages
Thai
## Dataset Structure
### Data Instances
```
{'id': 100, 'ner_tags': [27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27], 'pos_tags': [6, 12, 13, 1, 6, 5, 11, 7, 11, 6, 5, 13, 6, 6, 6, 11, 6, 6, 11, 6, 6, 11, 6, 6, 13, 6, 11, 11, 6, 11, 6, 11, 6, 11, 6, 11, 11, 6, 6, 11, 12, 6, 13, 5, 11, 7, 11, 6, 3, 11, 12, 3, 13, 6, 1, 6, 12, 13, 1, 6, 6, 5, 11, 3, 11, 5, 4, 6, 13, 6, 13, 6, 10, 3, 13, 13, 12, 13, 12, 0, 1, 10, 11, 6, 6, 11, 6, 11, 6, 12, 13, 5, 12, 3, 13, 13, 1, 6, 1, 6, 13], 'tokens': ['เชื้อโรค', 'ที่', 'ปรากฏ', 'ใน', 'สัตว์', 'ทั้ง', ' ', '4', ' ', 'ชนิด', 'นี้', 'เป็น', 'เชื้อ', 'โรคไข้หวัด', 'นก', ' ', 'เอช', 'พี', ' ', 'เอ', 'เวียน', ' ', 'อิน', 'ฟลู', 'เอน', 'ซา', ' ', '(', 'Hight', ' ', 'Polygenic', ' ', 'Avain', ' ', 'Influenza', ')', ' ', 'ชนิด', 'รุนแรง', ' ', 'ซึ่ง', 'การ', 'ตั้งชื่อ', 'ทั้ง', ' ', '4', ' ', 'ขึ้น', 'มา', ' ', 'เพื่อที่จะ', 'สามารถ', 'ระบุ', 'เชื้อ', 'ของ', 'ไวรัส', 'ที่', 'ทำอันตราย', 'ตาม', 'สิ่งมีชีวิต', 'ประเภท', 'ต่างๆ', ' ', 'ได้', ' ', 'อีก', 'ทั้ง', 'การ', 'ระบุ', 'สถานที่', 'คือ', 'ประเทศ', 'ไทย', 'จะ', 'ทำให้', 'รู้', 'ว่า', 'พบ', 'ที่', 'แรก', 'ใน', 'ไทย', ' ', 'ส่วน', 'วัน', ' ', 'เดือน', ' ', 'ปี', 'ที่', 'พบ', 'นั้น', 'ก็', 'จะ', 'ทำให้', 'ทราบ', 'ถึง', 'ครั้งแรก', 'ของ', 'การ', 'ค้นพบ']}
{'id': 107, 'ner_tags': [27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27], 'pos_tags': [0, 1, 6, 5, 11, 12, 3, 3, 13, 6, 13, 12, 0, 2, 12, 11, 6, 5, 13, 6, 5, 1, 6, 6, 1, 10, 11, 4, 13, 6, 11, 12, 6, 6, 10, 11, 13, 6, 1, 6, 4, 6, 1, 6, 6, 11, 4, 6, 1, 5, 6, 12, 2, 13, 6, 6, 5, 1, 11, 12, 13, 1, 6, 6, 11, 13, 11, 6, 6, 6, 11, 11, 6, 11, 11, 4, 10, 11, 11, 6, 11], 'tokens': ['ล่าสุด', 'ใน', 'เรื่อง', 'นี้', ' ', 'ทั้งนี้', 'คง', 'ต้อง', 'มี', 'การ', 'ตรวจสอบ', 'ให้', 'ชัดเจน', 'อีกครั้ง', 'ว่า', ' ', 'ไวรัส', 'นี้', 'เป็น', 'ชนิด', 'เดียว', 'กับ', 'ไข้หวัด', 'นก', 'ใน', 'ไทย', ' ', 'หรือ', 'เป็น', 'การกลายพันธุ์', ' ', 'โดยที่', 'คณะ', 'สัตวแพทย์', 'มหาวิทยาลัยเกษตรศาสตร์', ' ', 'จัด', 'ระดมสมอง', 'จาก', 'คณบดี', 'และ', 'ผู้เชี่ยวชาญ', 'จาก', 'คณะ', 'สัตวแพทย์', ' ', 'และ', 'ปศุสัตว์', 'ของ', 'หลาย', 'มหาวิทยาลัย', 'เพื่อ', 'ร่วมกัน', 'หา', 'ข้อมูล', 'เรื่อง', 'นี้', 'ด้วย', ' ', 'โดย', 'ประสาน', 'กับ', 'เจ้าหน้าที่', 'ระหว่างประเทศ', ' ', 'คือ', ' ', 'องค์การ', 'สุขภาพ', 'สัตว์โลก', ' ', '(', 'OIE', ')', ' ', 'และ', 'องค์การอนามัยโลก', ' ', '(', 'WHO', ')']}
```
### Data Fields
- `id`: sentence id
- `tokens`: word tokens by [PyThaiNLP](https://github.com/PyThaiNLP/pythainlp)'s dictionary-based tokenizer `newmm`
- `pos_tags`: POS tags tagged by [PyThaiNLP](https://github.com/PyThaiNLP/pythainlp)'s `perceptron` engine trained on `orchid_ud`
- `ner_tags`: NER tags tagged by humans
### Data Splits
No explicit split is given
## Dataset Creation
### Curation Rationale
ThaiNER (v1.3) is a 6,456-sentence named entity recognition dataset created from expanding the 2,258-sentence [unnamed dataset](http://pioneer.chula.ac.th/~awirote/Data-Nutcha.zip) by [Tirasaroj and Aroonmanakun (2012)](http://pioneer.chula.ac.th/~awirote/publications/). It is used to train NER taggers in [PyThaiNLP](https://github.com/PyThaiNLP/pythainlp).
### Source Data
#### Initial Data Collection and Normalization
The earlier part of the dataset is all news articles, whereas the part added by [@wannaphong](https://github.com/wannaphong/) includes news articles, public announcements and [@wannaphong](https://github.com/wannaphong/)'s own chat messages with personal and sensitive information removed.
#### Who are the source language producers?
News articles and public announcements are created by their respective authors. Chat messages are created by [@wannaphong](https://github.com/wannaphong/).
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[Tirasaroj and Aroonmanakun (2012)](http://pioneer.chula.ac.th/~awirote/publications/) for the earlier 2,258 sentences and [@wannaphong](https://github.com/wannaphong/) for the rest
### Personal and Sensitive Information
News articles and public announcements are not expected to include personal and sensitive information. [@wannaphong](https://github.com/wannaphong/) has removed such information from his own chat messages.
## Considerations for Using the Data
### Social Impact of Dataset
- named entity recognition in Thai
### Discussion of Biases
Since almost all of collection and annotation is done by [@wannaphong](https://github.com/wannaphong/), his biases are expected to be reflected in the dataset.
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[Tirasaroj and Aroonmanakun (2012)](http://pioneer.chula.ac.th/~awirote/publications/) for the earlier 2,258 sentences and [@wannaphong](https://github.com/wannaphong/) for the rest
### Licensing Information
CC-BY 3.0
### Citation Information
```
@misc{Wannaphong Phatthiyaphaibun_2019,
title={wannaphongcom/thai-ner: ThaiNER 1.3},
url={https://zenodo.org/record/3550546},
DOI={10.5281/ZENODO.3550546},
abstractNote={Thai Named Entity Recognition},
publisher={Zenodo},
author={Wannaphong Phatthiyaphaibun},
year={2019},
month={Nov}
}
```
Work extended from:
[Tirasaroj, N. and Aroonmanakun, W. 2012. Thai NER using CRF model based on surface features. In Proceedings of SNLP-AOS 2011, 9-10 February, 2012, Bangkok, pages 176-180.](http://pioneer.chula.ac.th/~awirote/publications/)
### Contributions
Thanks to [@cstorm125](https://github.com/cstorm125) for adding this dataset. |
false | This dataset is a custom dataset created by the author by crawling Naver News (https://news.naver.com) for the Korean NLP model hands-on.
- Period: July 1, 2022 - July 10, 2022
- Subject: IT, economics
```
DatasetDict({
train: Dataset({
features: ['date', 'category', 'press', 'title', 'document', 'link', 'summary'],
num_rows: 22194
})
test: Dataset({
features: ['date', 'category', 'press', 'title', 'document', 'link', 'summary'],
num_rows: 2740
})
validation: Dataset({
features: ['date', 'category', 'press', 'title', 'document', 'link', 'summary'],
num_rows: 2466
})
})
```
---
license: apache-2.0
--- |
false |
# Dataset Card for ArCOV19
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:**
- **Repository:** https://gitlab.com/bigirqu/ArCOV-19
- **Paper:** [ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks](https://arxiv.org/abs/2004.05861)
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [Fatima Haouari](mailto:200159617@qu.edu.qa)
### Dataset Summary
ArCOV-19 is an Arabic COVID-19 Twitter dataset that covers the period from 27th of January till 30th of April 2020. ArCOV-19 is the first publicly-available Arabic Twitter dataset covering COVID-19 pandemic that includes over 1M tweets alongside the propagation networks of the most-popular subset of them (i.e., most-retweeted and-liked). The propagation networks include both retweets and conversational threads (i.e., threads of replies). ArCOV-19 is designed to enable research under several domains including natural language processing, information retrieval, and social computing, among others. Preliminary analysis shows that ArCOV-19 captures rising discussions associated with the first reported cases of the disease as they appeared in the Arab world. In addition to the source tweets and the propagation networks, we also release the search queries and the language-independent crawler used to collect the tweets to encourage the curation of similar datasets.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Arabic
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
tweet_id: the Twitter assigned ID for the tweet object.
### Data Splits
[More Information Needed]
## Dataset Creation
The dataset collection approach is presented in the following paper: [ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks](https://arxiv.org/abs/2004.05861)
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
No annotation was provided with the dataset.
#### Annotation process
No annotation was provided with the dataset.
#### Who are the annotators?
No annotation was provided with the dataset.
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
**Team:** [bigIR](https://sites.google.com/view/bigir) from Qatar University ([@bigIR_group](https://twitter.com/bigIR_group))
- [Fatima Haouari](mailto:200159617@qu.edu.qa)
- [Maram Hasanain](mailto:maram.hasanain@qu.edu.qa)
- [Reem Suwaileh](mailto:rs081123@qu.edu.qa)
- [Dr. Tamer Elsayed](mailto:telsayed@qu.edu.qa)
### Licensing Information
[More Information Needed]
### Citation Information
@article{haouari2020arcov19,
title={ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks},
author={Fatima Haouari and Maram Hasanain and Reem Suwaileh and Tamer Elsayed},
journal={arXiv preprint arXiv:2004.05861},
year={2020}
}
### Contributions
Thanks to [@Fatima-Haouari](https://github.com/Fatima-Haouari) for adding this dataset. |
false |
# Dataset Card for The Hong Kong Cantonese Corpus (HKCanCor)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://compling.hss.ntu.edu.sg/hkcancor/
- **Repository:** https://github.com/fcbond/hkcancor
- **Paper:** [Luke and Wang, 2015](https://github.com/fcbond/hkcancor/blob/master/data/LukeWong_Hong-Kong-Cantonese-Corpus.pdf)
- **Leaderboard:** N/A
- **Point of Contact:** Luke Kang Kwong
### Dataset Summary
The Hong Kong Cantonese Corpus (HKCanCor) comprise transcribed conversations recorded
between March 1997 and August 1998. It contains recordings of spontaneous speech (51 texts)
and radio programmes (42 texts), which involve 2 to 4 speakers, with 1 text of monologue.
In total, the corpus contains around 230,000 Chinese words. The text is word-segmented (i.e., tokenization is at word-level, and each token can span multiple Chinese characters). Tokens are annotated with part-of-speech (POS) tags and romanised Cantonese pronunciation.
* Romanisation
* Follows conventions set by the Linguistic Society of Hong Kong (LSHK).
* POS
* The tagset used by this corpus extends the one in the Peita-Fujitsu-Renmin Ribao (PRF) corpus (Duan et al., 2000). Extensions were made to further capture Cantonese-specific phenomena.
* To facilitate everyday usage and for better comparability across languages and/or corpora, this dataset also includes the tags mapped to the [Universal Dependencies 2.0](https://universaldependencies.org/u/pos/index.html) format. This mapping references the [PyCantonese](https://github.com/jacksonllee/pycantonese) library.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Yue Chinese / Cantonese (Hong Kong).
## Dataset Structure
This corpus has 10801 utterances and approximately 230000 Chinese words.
There is no predefined split.
### Data Instances
Each instance contains a conversation id, speaker id within that conversation,
turn number, part-of-speech tag for each Chinese word in the PRF format and UD2.0 format,
and the utterance written in Chinese characters as well as its LSHK format romanisation.
For example:
```python
{
'conversation_id': 'TNR016-DR070398-HAI6V'
'pos_tags_prf': ['v', 'w'],
'pos_tags_ud': ['VERB', 'PUNCT'],
'speaker': 'B',
'transcriptions': ['hai6', 'VQ1'],
'turn_number': 112,
'tokens': ['係', '。']
}
```
### Data Fields
- conversation_id: unique dialogue-level id
- pos_tags_prf: POS tag using the PRF format at token-level
- pos_tag_ud: POS tag using the UD2.0 format at token-level
- speaker: unique speaker id within dialogue
- transcriptions: token-level romanisation in the LSHK format
- turn_number: turn number in dialogue
- tokens: Chinese word or punctuation at token-level
### Data Splits
There are no specified splits in this dataset.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
This work is licensed under a [Creative Commons Attribution 4.0 International License](https://creativecommons.org/licenses/by/4.0/deed.ast).
### Citation Information
This corpus was developed by [Luke and Wong, 2015](http://compling.hss.ntu.edu.sg/hkcancor/data/LukeWong_Hong-Kong-Cantonese-Corpus.pdf).
```
@article{luke2015hong,
author={Luke, Kang-Kwong and Wong, May LY},
title={The Hong Kong Cantonese corpus: design and uses},
journal={Journal of Chinese Linguistics},
year={2015},
pages={309-330},
month={12}
}
```
The POS tagset to Universal Dependency tagset mapping is provided by Jackson Lee, as a part of the [PyCantonese](https://github.com/jacksonllee/pycantonese) library.
```
@misc{lee2020,
author = {Lee, Jackson},
title = {PyCantonese: Cantonese Linguistics and NLP in Python},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/jacksonllee/pycantonese}},
commit = {1d58f44e1cb097faa69de6b617e1d28903b84b98}
}
```
### Contributions
Thanks to [@j-chim](https://github.com/j-chim) for adding this dataset. |
false |
# Dataset Card for [Dataset Name]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [PANL BPPT](http://digilib.bppt.go.id/sampul/p92-budiono.pdf)
- **Repository:** [PANL BPPT Repository](https://github.com/cahya-wirawan/indonesian-language-models/raw/master/data/BPPTIndToEngCorpusHalfM.zip)
- **Paper:** [Resource Report: Building Parallel Text Corpora for Multi-Domain Translation System](http://digilib.bppt.go.id/sampul/p92-budiono.pdf)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
Parallel Text Corpora for Multi-Domain Translation System created by BPPT (Indonesian Agency for the Assessment and
Application of Technology) for PAN Localization Project (A Regional Initiative to Develop Local Language Computing
Capacity in Asia). The dataset contains around 24K sentences divided in 4 difference topics (Economic, international,
Science and Technology and Sport).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Indonesian
## Dataset Structure
[More Information Needed]
### Data Instances
An example of the dataset:
```
{
'id': '0',
'topic': 0,
'translation':
{
'en': 'Minister of Finance Sri Mulyani Indrawati said that a sharp correction of the composite
inde x by up to 4 pct in Wedenesday?s trading was a mere temporary effect of regional factors like
decline in plantation commodity prices and the financial crisis in Thailand.',
'id': 'Menteri Keuangan Sri Mulyani mengatakan koreksi tajam pada Indeks Harga Saham Gabungan
IHSG hingga sekitar 4 persen dalam perdagangan Rabu 10/1 hanya efek sesaat dari faktor-faktor regional
seperti penurunan harga komoditi perkebunan dan krisis finansial di Thailand.'
}
}
```
### Data Fields
- `id`: id of the sample
- `translation`: the parallel sentence english-indonesian
- `topic`: the topic of the sentence. It could be one of the following:
- Economic
- International
- Science and Technology
- Sport
### Data Splits
The dataset is splitted in to train, validation and test sets.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```
@inproceedings{id_panl_bppt,
author = {PAN Localization - BPPT},
title = {Parallel Text Corpora, English Indonesian},
year = {2009},
url = {http://digilib.bppt.go.id/sampul/p92-budiono.pdf},
}
```
### Contributions
Thanks to [@cahya-wirawan](https://github.com/cahya-wirawan) for adding this dataset. |
false |
# Dataset Card for WikiQAar
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [WikiQaAr](https://github.com/qcri/WikiQAar)
- **Repository:** [WikiQaAr](https://github.com/qcri/WikiQAar)
- **Paper:**
- **Point of Contact:** [Ines Abbes
](abbes.ines@yahoo.com)
### Dataset Summary
Arabic Version of WikiQA by automatic automatic machine translators
and crowdsourced the selection of the best one to be incorporated into the corpus
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is based on Arabic.
## Dataset Structure
### Data Instances
Each data point contains the question and whether the answer is a valid or not.
### Data Fields
- `question_id`: the question id.
- `question`: the question text.
- `document_id`: the wikipedia document id.
- `answer_id` : the answer id.
- `answer` : a candidate answer to the question.
- `label` : 1 if the `answer` is correct or 0 otherwise.
### Data Splits
The dataset is not split.
| | train | validation | test |
|------------|-------:|-----------:|-------:|
| Data split | 70,264 | 20,632 | 10,387 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
Translation of WikiQA.
#### Who are the source language producers?
Translation of WikiQA.
### Annotations
The dataset does not contain any additional annotations.
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```
@InProceedings{YangYihMeek:EMNLP2015:WikiQA,
author = {{Yi}, Yang and {Wen-tau}, Yih and {Christopher} Meek},
title = "{WikiQA: A Challenge Dataset for Open-Domain Question Answering}",
journal = {Association for Computational Linguistics},
year = 2015,
doi = {10.18653/v1/D15-1237},
pages = {2013–2018},
}
```
### Contributions
Thanks to [@zaidalyafeai](https://github.com/zaidalyafeai) for adding this dataset. |
true |
# Dataset Card for 3i4K
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [3i4K](https://github.com/warnikchow/3i4k)
- **Repository:** [3i4K](https://github.com/warnikchow/3i4k)
- **Paper:** [Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency](https://arxiv.org/abs/1811.04231)
- **Point of Contact:** [Won Ik Cho](wicho@hi.snu.ac.kr)
### Dataset Summary
The 3i4K dataset is a set of frequently used Korean words (corpus provided by the Seoul National University Speech Language Processing Lab) and manually created questions/commands containing short utterances. The goal is to identify the speaker intention of a spoken utterance based on its transcript, and whether in some cases, requires using auxiliary acoustic features. The classification system decides whether the utterance is a fragment, statement, question, command, rhetorical question, rhetorical command, or an intonation-dependent utterance. This is important because in head-final languages like Korean, the level of the intonation plays a significant role in identifying the speaker's intention.
### Supported Tasks and Leaderboards
* `intent-classification`: The dataset can be trained with a CNN or BiLISTM-Att to identify the intent of a spoken utterance in Korean and the performance can be measured by its F1 score.
### Languages
The text in the dataset is in Korean and the associated is BCP-47 code is `ko-KR`.
## Dataset Structure
### Data Instances
An example data instance contains a short utterance and it's label:
```
{
"label": 3,
"text": "선수잖아 이 케이스 저 케이스 많을 거 아냐 선배라고 뭐 하나 인생에 도움도 안주는데 내가 이렇게 진지하게 나올 때 제대로 한번 조언 좀 해줘보지"
}
```
### Data Fields
* `label`: determines the intention of the utterance and can be one of `fragment` (0), `statement` (1), `question` (2), `command` (3), `rhetorical question` (4), `rhetorical command` (5) and `intonation-depedent utterance` (6).
* `text`: the text in Korean about common topics like housework, weather, transportation, etc.
### Data Splits
The data is split into a training set comrpised of 55134 examples and a test set of 6121 examples.
## Dataset Creation
### Curation Rationale
For head-final languages like Korean, intonation can be a determining factor in identifying the speaker's intention. The purpose of this dataset is to to determine whether an utterance is a fragment, statement, question, command, or a rhetorical question/command using the intonation-depedency from the head-finality. This is expected to improve language understanding of spoken Korean utterances and can be beneficial for speech-to-text applications.
### Source Data
#### Initial Data Collection and Normalization
The corpus was provided by Seoul National University Speech Language Processing Lab, a set of frequently used words from the National Institute of Korean Language and manually created commands and questions. The utterances cover topics like weather, transportation and stocks. 20k lines were randomly selected.
#### Who are the source language producers?
Korean speakers produced the commands and questions.
### Annotations
#### Annotation process
Utterances were classified into seven categories. They were provided clear instructions on the annotation guidelines (see [here](https://docs.google.com/document/d/1-dPL5MfsxLbWs7vfwczTKgBq_1DX9u1wxOgOPn1tOss/edit#) for the guidelines) and the resulting inter-annotator agreement was 0.85 and the final decision was done by majority voting.
#### Who are the annotators?
The annotation was completed by three Seoul Korean L1 speakers.
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The dataset is curated by Won Ik Cho, Hyeon Seung Lee, Ji Won Yoon, Seok Min Kim and Nam Soo Kim.
### Licensing Information
The dataset is licensed under the CC BY-SA-4.0.
### Citation Information
```
@article{cho2018speech,
title={Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency},
author={Cho, Won Ik and Lee, Hyeon Seung and Yoon, Ji Won and Kim, Seok Min and Kim, Nam Soo},
journal={arXiv preprint arXiv:1811.04231},
year={2018}
}
```
### Contributions
Thanks to [@stevhliu](https://github.com/stevhliu) for adding this dataset. |
true |
# Dataset Card for REFreSD Dataset
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Github](https://github.com/Elbria/xling-SemDiv/tree/master/REFreSD)
- **Repository:** [Github](https://github.com/Elbria/xling-SemDiv/)
- **Paper:** [Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank](https://www.aclweb.org/anthology/2020.emnlp-main.121)
- **Leaderboard:**
- **Point of Contact:** [Eleftheria Briakou](mailto:ebriakou@cs.umd.edu)
- **Additional Documentation:** [Annotation workflow, data statement, DataSheet, and IRB documentation](https://elbria.github.io/post/refresd/)
### Dataset Summary
The Rationalized English-French Semantic Divergences (REFreSD) dataset consists of 1,039 English-French sentence-pairs annotated with sentence-level divergence judgments and token-level rationales. The project under which REFreSD was collected aims to advance our fundamental understanding of computational representations and methods for comparing and contrasting text meaning across languages.
### Supported Tasks and Leaderboards
`semantic-similarity-classification` and `semantic-similarity-scoring`: This dataset can by used to assess the ability of computational methods to detect meaning mismatches between languages. The model performance is measured in terms of accuracy by comparing the model predictions with the human judgments in REFreSD. Details about the results of a BERT-based model, Divergent mBERT, over this dataset can be found in the [paper](https://www.aclweb.org/anthology/2020.emnlp-main.121).
### Languages
The text is in English and French as found on Wikipedia. The associated BCP-47 codes are `en` and `fr`.
## Dataset Structure
### Data Instances
Each data point looks like this:
```python
{
'sentence_pair': {'en': 'The invention of farming some 10,000 years ago led to the development of agrarian societies , whether nomadic or peasant , the latter in particular almost always dominated by a strong sense of traditionalism .',
'fr': "En quelques décennies , l' activité économique de la vallée est passée d' une mono-activité agricole essentiellement vivrière , à une quasi mono-activité touristique , si l' on excepte un artisanat du bâtiment traditionnel important , en partie saisonnier ."}
'label': 0,
'all_labels': 0,
'rationale_en': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
'rationale_fr': [2, 3, 3, 3, 3, 3, 3, 3, 3, 3, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3],
}
```
### Data Fields
- `sentence_pair`: Dictionary of sentences containing the following field.
- `en`: The English sentence.
- `fr`: The corresponding (or not) French sentence.
- `label`: Binary. Whether both sentences correspond. `{0:divergent, 1:equivalent}`
- `all_labels`: 3-class label `{0: "unrelated", 1: "some_meaning_difference", 2:"no_meaning_difference"}`. The first two are sub-classes of the `divergent` label.
- `rationale_en`: A list of integers from 0-3 indicating the number of annotators who highlighted the token of the text in the English sentence during annotation. Word-aligned rationale for the divergent/equivalent label, from English.
- `rationale_fr`: A list of integers from 0-3 indicating the number of annotators who highlighted the token of the text in the French sentence during annotation. Word-aligned rationale for the divergent/equivalent label, from French.
### Data Splits
The dataset contains 1039 sentence pairs in a single `"train"` split. Of these pairs, 64% are annotated as divergent, and 40% contain fine-grained meaning divergences.
| Label | Number of Instances |
| ----------------------- | ------------------- |
| Unrelated | 252 |
| Some meaning difference | 418 |
| No meaning different | 369 |
## Dataset Creation
### Curation Rationale
The curators chose the English-French section of the WikiMatrix corpus because (1) it is likely to contain diverse, interesting divergence types since it consists of mined parallel sentences of diverse topics which are not necessarily generated by (human) translations, and (2) Wikipedia and WikiMatrix are widely used resources to train semantic representations and perform cross-lingual transfer in NLP.
### Source Data
#### Initial Data Collection and Normalization
The source for this corpus is the English and French portion of the [WikiMatrix corpus](https://arxiv.org/abs/1907.05791), which itself was extracted from Wikipedia articles. The curators excluded noisy samples by filtering out sentence pairs that a) were too short or too long, b) consisted mostly of numbers, or c) had a small token-level edit difference.
#### Who are the source language producers?
Some content of Wikipedia articles has been (human) translated from existing articles in another language while others have been written or edited independently in each language. Therefore, information on how the original text is created is not available.
### Annotations
#### Annotation process
The annotations were collected over the span of three weeks in April 2020. Annotators were presented with an English sentence and a French sentence. First, they highlighted spans and labeled them as 'added', 'changed', or 'other', where added spans contain information not contained in the other sentence, changed spans contain some information that is in the other sentence but whose meaning is not the same, and other spans have some different meaning not covered in the previous two cases, such as idioms. They then assessed the relation between the two sentences as either 'unrelated', 'some meaning differences', or 'no meaning difference'. See the [annotation guidelines](https://elbria.github.io/post/refresd/files/REFreSD_Annotation_Guidelines.pdf) for more information about the task and the annotation interface, and see the [DataSheet](https://elbria.github.io/post/refresd/files/REFreSD_Datasheet.pdf) for information about the annotator compensation.
The following table contains Inter-Annotator Agreement metrics for the dataset:
| Granularity | Method | IAA |
| ----------- | --------------- | ------------ |
| Sentence | Krippendorf's α | 0.60 |
| Span | macro F1 | 45.56 ± 7.60 |
| Token | macro F1 | 33.94 ± 8.24 |
#### Who are the annotators?
This dataset includes annotations from 6 participants recruited from the University of Maryland, College Park (UMD) educational institution. Participants ranged in age from 20–25 years, including one man and five women. For each participant, the curators ensured they were proficient in both languages of interest: three of them self-reported as English native speakers, one as a French native speaker, and two as bilingual English-French speakers.
### Personal and Sensitive Information
The dataset contains discussions of people as they appear in Wikipedia articles. It does not contain confidential information, nor does it contain identifying information about the source language producers or the annotators.
## Considerations for Using the Data
### Social Impact of Dataset
Models that are successful in the supported task require sophisticated semantic representations at the sentence level beyond the combined representations of the individual tokens in isolation. Such models could be used to curate parallel corpora for tasks like machine translation, cross-lingual transfer learning, or semantic modeling.
The statements in the dataset, however, are not necessarily representative of the world and may overrepresent one worldview if one language is primarily translated to, rather than an equal distribution of translations between the languages.
### Discussion of Biases
The English Wikipedia is known to have significantly more [contributors](https://en.wikipedia.org/wiki/Wikipedia:Who_writes_Wikipedia%3F) who identify as male than any other gender and who reside in either North America or Europe. This leads to an overrepresentation of male perspectives from these locations in the corpus in terms of both the topics covered and the language used to talk about those topics. It's not clear to what degree this holds true for the French Wikipedia. The REFreSD dataset itself has not yet been examined for the degree to which it contains the gender and other biases seen in the larger Wikipedia datasets.
### Other Known Limitations
It is unknown how many of the sentences in the dataset were written independently, and how many were written as [translations](https://en.wikipedia.org/wiki/Wikipedia:Translation) by either humans or machines from some other language to the languages of interest in this dataset.
## Additional Information
### Dataset Curators
The dataset curators are Eleftheria Briakou and Marine Carpuat, who are both affiliated with the University of Maryland, College Park's Department of Computer Science.
### Licensing Information
The project is licensed under the [MIT License](https://github.com/Elbria/xling-SemDiv/blob/master/LICENSE).
### Citation Information
```BibTeX
@inproceedings{briakou-carpuat-2020-detecting,
title = "Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank",
author = "Briakou, Eleftheria and Carpuat, Marine",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.emnlp-main.121",
pages = "1563--1580",
}
```
### Contributions
Thanks to [@mpariente](https://github.com/mpariente) and [@mcmillanmajora](https://github.com/mcmillanmajora) for adding this dataset. |
false |
# Dataset Card for YouTube Caption Corrections
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://github.com/2dot71mily/youtube_captions_corrections
- **Repository:** https://github.com/2dot71mily/youtube_captions_corrections
- **Paper:** [N/A]
- **Leaderboard:** [N/A]
- **Point of Contact:** Emily McMilin
### Dataset Summary
This dataset is built from pairs of YouTube captions where both an auto-generated and a manually-corrected caption are available for a single specified language. It currently only in English, but scripts at repo support other languages. The motivation for creating it was from viewing errors in auto-generated captions at a recent virtual conference, with the hope that there could be some way to help correct those errors.
The dataset in the repo at https://github.com/2dot71mily/youtube_captions_corrections records in a non-destructive manner all the differences between an auto-generated and a manually-corrected caption for thousands of videos. The dataset here focuses on the subset of those differences which are mutual and have the same size in token length difference, which means it excludes token insertion or deletion differences between the two captions. Therefore dataset here remains a non-destructive representation of the original auto-generated captions, but excludes some of the differences that are found in the manually-corrected captions.
### Supported Tasks and Leaderboards
- `token-classification`: The tokens in `default_seq` are from the auto-generated YouTube captions. If `diff_type` is labeled greater than `0` at a given index, then the associated token in same index in the `default_seq` was found to be different to the token in the manually-corrected YouTube caption, and therefore we assume it is an error. A model can be trained to learn when there are errors in the auto-generated captions.
- `slot-filling`: The `correction_seq` is sparsely populated with tokens from the manually-corrected YouTube captions in the locations where there was found to be a difference to the token in the auto-generated YouTube captions. These 'incorrect' tokens in the `default_seq` can be masked in the locations where `diff_type` is labeled greater than `0`, so that a model can be trained to hopefully find a better word to fill in, rather than the 'incorrect' one.
End to end, the models could maybe first identify and then replace (with suitable alternatives) errors in YouTube and other auto-generated captions that are lacking manual corrections
### Languages
English
## Dataset Structure
### Data Instances
If `diff_type` is labeled greater than `0` at a given index, then the associated token in same index in the `default_seq` was found to have a difference to the token in the manually-corrected YouTube caption. The `correction_seq` is sparsely populated with tokens from the manually-corrected YouTube captions at those locations of differences.
`diff_type` labels for tokens are as follows:
0: No difference
1: Case based difference, e.g. `hello` vs `Hello`
2: Punctuation difference, e.g. `hello` vs `hello`
3: Case and punctuation difference, e.g. `hello` vs `Hello,`
4: Word difference with same stem, e.g. `thank` vs `thanked`
5: Digit difference, e.g. `2` vs `two`
6: Intra-word punctuation difference, e.g. `autogenerated` vs `auto-generated`
7: Unknown type of difference, e.g. `laughter` vs `draft`
8: Reserved for unspecified difference
{
'video_titles': '_QUEXsHfsA0',
'default_seq': ['you', 'see', "it's", 'a', 'laughter', 'but', 'by', 'the', 'time', 'you', 'see', 'this', 'it', "won't", 'be', 'so', 'we', 'have', 'a', 'big']
'correction_seq': ['', 'see,', '', '', 'draft,', '', '', '', '', '', 'read', 'this,', '', '', 'be.', 'So', '', '', '', '']
'diff_type': [0, 2, 0, 0, 7, 0, 0, 0, 0, 0, 7, 2, 0, 0, 2, 1, 0, 0, 0, 0]
}
### Data Fields
- 'video_ids': Unique ID used by YouTube for each video. Can paste into `https://www.youtube.com/watch?v=<{video_ids}` to see video
- 'default_seq': Tokenized auto-generated YouTube captions for the video
- 'correction_seq': Tokenized manually-corrected YouTube captions only at those locations, where there is a difference between the auto-generated and manually-corrected captions
- 'diff_type': A value greater than `0` at every token where there is a difference between the auto-generated and manually-corrected captions
### Data Splits
No data splits
## Dataset Creation
### Curation Rationale
It was created after viewing errors in auto-generated captions at a recent virtual conference, with the hope that there could be some way to help correct those errors.
### Source Data
#### Initial Data Collection and Normalization
All captions are requested via `googleapiclient` and `youtube_transcript_api` at the `channel_id` and language granularity, using scripts written at https://github.com/2dot71mily/youtube_captions_corrections.
The captions are tokenized on spaces and the manually-corrected sequence has here been reduced to only include differences between it and the auto-generated sequence.
#### Who are the source language producers?
Auto-generated scripts are from YouTube and the manually-corrected scripts are from creators, and any support they may have (e.g. community or software support)
### Annotations
#### Annotation process
Scripts at repo, https://github.com/2dot71mily/youtube_captions_corrections take a diff of the two captions and use this to create annotations.
#### Who are the annotators?
YouTube creators, and any support they may have (e.g. community or software support)
### Personal and Sensitive Information
All content publicly available on YouTube
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Emily McMilin
### Licensing Information
MIT License
### Citation Information
https://github.com/2dot71mily/youtube_captions_corrections
### Contributions
Thanks to [@2dot71mily](https://github.com/2dot71mily) for adding this dataset. |
false | # Dataset Card for NBAiLab/NPSC
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Data Fields](#data-fiels)
- [Dataset Creation](#dataset-creation)
- [Statistics](#statistics)
- [Document Types](#document-types)
- [Languages](#languages)
- [Publish Periode](#publish-periode)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** https://www.nb.no/sprakbanken/
- **Repository:** https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-58/
- **Paper:** https://www.nb.no/sprakbanken/
- **Point of Contact:** [Per Erik Solberg](mailto:per.solberg@nb.no)
The Norwegian Parliament Speech Corpus (NPSC) is a corpus for training a Norwegian ASR (Automatic Speech Recognition) models. The corpus is created by Språkbanken at the National Library in Norway.
NPSC is based on sound recording from meeting in the Norwegian Parliament. These talks are orthographically transcribed to either Norwegian Bokmål or Norwegian Nynorsk. In addition to the data actually included in this dataset, there is a significant amount of metadata that is included in the original corpus. Through the speaker id there is additional information about the speaker, like gender, age, and place of birth (ie dialect). Through the proceedings id the corpus can be linked to the official proceedings from the meetings.
The corpus is in total sound recordings from 40 entire days of meetings. This amounts to 140 hours of speech, 65,000 sentences or 1.2 million words.
This corpus is an adaption of the original corpus made for efficiant ASR training. For simplicity and portability, a few of the original datasets features, like the token transcription, is ommitted. You can find the complete dataset at [the Resource Catalogue at Språkbanken](https://www.nb.no/sprakbanken/ressurskatalog/oai-nb-no-sbr-58/).
## How to Use (This needs to be edited of course)
```python
from datasets import load_dataset
data = load_dataset("nb/NPSC", streaming=True)
```
## Data Fields
Currently there are two versions included in this repo.
### Version A
This verison has a short list of the metadata and includes the audio (48k mp3) encoded as a float32 array in the dataset itself.
The current dataloader script is associated with this version.
One line in train.json looks like this:
```json
{
"sentence_id": 7309,
"sentence_order": 0,
"speaker_id": 1,
"speaker_name": "Marit Nybakk",
"sentence_text": "Stortingets møte er lovlig satt",
"sentence_language_code": "nb-NO",
"text": "Stortingets møte er lovlig satt",
"start_time": 302650,
"end_time": 306000,
"normsentence_text": "Stortingets møte er lovlig satt",
"transsentence_text": "Stortingets møte er lovleg sett",
"translated": 1,
"audio": {
"path": "audio/20170207-095506_302650_306000.wav",
"array": [
24,
25,
50,
(...)
],
"sampling_rate": 48000
}
}
```
### Version B
This verison does not contain the audio encoded in the dataset. Instead it has the audio files placed in sub-directories. There are currently both samples in clips_48k_wav and clips_16k_mp3. Only the base filename is referred in the dataset. Please not that there are both sentence-based audio clips as well at meeting-based audio clips. The dataset contains referrals to both, the latter referral has start and stop time as well.
One line in the train/metadata.json looks like this:
```json
{
"meeting_date": "20170207",
"full_audio_file": "20170207-095506",
"proceedings_file": "20170207-095506.ref",
"duration": 4442474,
"transcriber_id": 1,
"reviewer_id": 2,
"data_split": "test",
"speaker_name": "Marit Nybakk",
"speaker_id": 1,
"sentence_id": 7309,
"sentence_language_code": "nb-NO",
"sentence_text": "Stortingets møte er lovlig satt",
"sentence_order": 0,
"audio_file": "20170207-095506_302650_306000",
"start_time": 302650,
"end_time": 306000,
"normsentence_text": "Stortingets møte er lovlig satt",
"transsentence_text": "Stortingets møte er lovleg sett",
"translated": 1
}
```
### Dataset Creation
We are providing a **train**, **dev** and **test** split. These are the same as in the orginal corpus.
Build date: 20012022
#### Initial Data Collection and Curation
The procedure for the dataset creation is described in detail in the paper.
## Statistics
| Feature | Value |
|:---------|-----------:|
| Duration, pauses included | 140,3 hours|
| Duration, pauses not included | 125,7 hours |
| Word count | 1,2 million |
| Sentence count | 64.531 |
| Language distribution | Nynorsk: 12,8%|
| | Bokmål: 87,2%%|
| Gender distribution | Female: 38,3% |
| | Male: 61.7% |
## Considerations for Using the Data
This corpus contains speech data and is allowed to be used outside the National Library of Norway for speech recognition technology purposes.
### Discussion of Biases
Please refer to our paper.
### Dataset Curators
[Per Erik Solberg](mailto:per.solberg@nb.no)
[Freddy Wetjen](mailto:Freddy.wetjen@nb.no), [Andre Kaasen](mailto:andre.kasen@nb.no) and [Per Egil Kummervold](mailto:per.kummervold@nb.no) has contributed to porting it to the Hugging Face Dataset format.
### Licensing Information
Licensed for use outside the National Library of Norway.
## License
CC-ZERO(https://creativecommons.org/publicdomain/zero/1.0/)
### Citation Information
We are preparing an article with detailed information about this corpus. Until it is published, please cite out paper discussing the first version of this corpus:
```
ANDRE: TO BE DONE
```
|
true |
# Dataset Card for ArSenTD-LEV
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [ArSenTD-LEV homepage](http://oma-project.com/)
- **Paper:** [ArSentD-LEV: A Multi-Topic Corpus for Target-based Sentiment Analysis in Arabic Levantine Tweets](https://arxiv.org/abs/1906.01830)
### Dataset Summary
The Arabic Sentiment Twitter Dataset for Levantine dialect (ArSenTD-LEV) contains 4,000 tweets written in Arabic and equally retrieved from Jordan, Lebanon, Palestine and Syria.
### Supported Tasks and Leaderboards
Sentriment analysis
### Languages
Arabic Levantine Dualect
## Dataset Structure
### Data Instances
{'Country': 0,
'Sentiment': 3,
'Sentiment_Expression': 0,
'Sentiment_Target': 'هاي سوالف عصابات ارهابية',
'Topic': 'politics',
'Tweet': 'ثلاث تفجيرات في #كركوك الحصيلة قتيل و 16 جريح بدأت اكلاوات كركوك كانت امان قبل دخول القوات العراقية ، هاي سوالف عصابات ارهابية'}
### Data Fields
`Tweet`: the text content of the tweet \
`Country`: the country from which the tweet was collected ('jordan', 'lebanon', 'syria', 'palestine')\
`Topic`: the topic being discussed in the tweet (personal, politics, religion, sports, entertainment and others) \
`Sentiment`: the overall sentiment expressed in the tweet (very_negative, negative, neutral, positive and very_positive) \
`Sentiment_Expression`: the way how the sentiment was expressed: explicit, implicit, or none (the latter when sentiment is neutral) \
`Sentiment_Target`: the segment from the tweet to which sentiment is expressed. If sentiment is neutral, this field takes the 'none' value.
### Data Splits
No standard splits are provided
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
Make sure to read and agree to the [license](http://oma-project.com/ArSenL/ArSenTD_Lev_Intro)
### Citation Information
```
@article{baly2019arsentd,
title={Arsentd-lev: A multi-topic corpus for target-based sentiment analysis in arabic levantine tweets},
author={Baly, Ramy and Khaddaj, Alaa and Hajj, Hazem and El-Hajj, Wassim and Shaban, Khaled Bashir},
journal={arXiv preprint arXiv:1906.01830},
year={2019}
}
```
### Contributions
Thanks to [@moussaKam](https://github.com/moussaKam) for adding this dataset. |
false |
# Dataset Card for BsWac
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://nlp.ffzg.hr/resources/corpora/bswac/
- **Repository:** https://www.clarin.si/repository/xmlui/handle/11356/1062
- **Paper:** http://nlp.ffzg.hr/data/publications/nljubesi/ljubesic14-bs.pdf
- **Leaderboard:**
- **Point of Contact:** [Nikola Ljubešič](mailto:nikola.ljubesic@ffzg.hr)
### Dataset Summary
The Bosnian web corpus bsWaC was built by crawling the .ba top-level domain in 2014. The corpus was near-deduplicated on paragraph level, normalised via diacritic restoration, morphosyntactically annotated and lemmatised. The corpus is shuffled by paragraphs. Each paragraph contains metadata on the URL, domain and language identification (Bosnian vs. Croatian vs. Serbian).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Dataset is monolingual in Bosnian language.
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
Dataset is under the [CC-BY-SA 3.0](http://creativecommons.org/licenses/by-sa/3.0/) license.
### Citation Information
```
@misc{11356/1062,
title = {Bosnian web corpus {bsWaC} 1.1},
author = {Ljube{\v s}i{\'c}, Nikola and Klubi{\v c}ka, Filip},
url = {http://hdl.handle.net/11356/1062},
note = {Slovenian language resource repository {CLARIN}.{SI}},
copyright = {Creative Commons - Attribution-{ShareAlike} 4.0 International ({CC} {BY}-{SA} 4.0)},
year = {2016} }
```
### Contributions
Thanks to [@IvanZidov](https://github.com/IvanZidov) for adding this dataset. |
false | # Dataset Card for "code_x_glue_tc_nl_code_search_adv"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits-sample-size)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://github.com/microsoft/CodeXGLUE/tree/main/Text-Code/NL-code-search-Adv
### Dataset Summary
CodeXGLUE NL-code-search-Adv dataset, available at https://github.com/microsoft/CodeXGLUE/tree/main/Text-Code/NL-code-search-Adv
The dataset we use comes from CodeSearchNet and we filter the dataset as the following:
- Remove examples that codes cannot be parsed into an abstract syntax tree.
- Remove examples that #tokens of documents is < 3 or >256
- Remove examples that documents contain special tokens (e.g. <img ...> or https:...)
- Remove examples that documents are not English.
### Supported Tasks and Leaderboards
- `document-retrieval`: The dataset can be used to train a model for retrieving top-k codes from a given **English** natural language query.
### Languages
- Python **programming** language
- English **natural** language
## Dataset Structure
### Data Instances
An example of 'validation' looks as follows.
```
{
"argument_list": "",
"code": "def Func(arg_0, arg_1='.', arg_2=True, arg_3=False, **arg_4):\n \"\"\"Downloads Dailymotion videos by URL.\n \"\"\"\n\n arg_5 = get_content(rebuilt_url(arg_0))\n arg_6 = json.loads(match1(arg_5, r'qualities\":({.+?}),\"'))\n arg_7 = match1(arg_5, r'\"video_title\"\\s*:\\s*\"([^\"]+)\"') or \\\n match1(arg_5, r'\"title\"\\s*:\\s*\"([^\"]+)\"')\n arg_7 = unicodize(arg_7)\n\n for arg_8 in ['1080','720','480','380','240','144','auto']:\n try:\n arg_9 = arg_6[arg_8][1][\"url\"]\n if arg_9:\n break\n except KeyError:\n pass\n\n arg_10, arg_11, arg_12 = url_info(arg_9)\n\n print_info(site_info, arg_7, arg_10, arg_12)\n if not arg_3:\n download_urls([arg_9], arg_7, arg_11, arg_12, arg_1=arg_1, arg_2=arg_2)",
"code_tokens": ["def", "Func", "(", "arg_0", ",", "arg_1", "=", "'.'", ",", "arg_2", "=", "True", ",", "arg_3", "=", "False", ",", "**", "arg_4", ")", ":", "arg_5", "=", "get_content", "(", "rebuilt_url", "(", "arg_0", ")", ")", "arg_6", "=", "json", ".", "loads", "(", "match1", "(", "arg_5", ",", "r'qualities\":({.+?}),\"'", ")", ")", "arg_7", "=", "match1", "(", "arg_5", ",", "r'\"video_title\"\\s*:\\s*\"([^\"]+)\"'", ")", "or", "match1", "(", "arg_5", ",", "r'\"title\"\\s*:\\s*\"([^\"]+)\"'", ")", "arg_7", "=", "unicodize", "(", "arg_7", ")", "for", "arg_8", "in", "[", "'1080'", ",", "'720'", ",", "'480'", ",", "'380'", ",", "'240'", ",", "'144'", ",", "'auto'", "]", ":", "try", ":", "arg_9", "=", "arg_6", "[", "arg_8", "]", "[", "1", "]", "[", "\"url\"", "]", "if", "arg_9", ":", "break", "except", "KeyError", ":", "pass", "arg_10", ",", "arg_11", ",", "arg_12", "=", "url_info", "(", "arg_9", ")", "print_info", "(", "site_info", ",", "arg_7", ",", "arg_10", ",", "arg_12", ")", "if", "not", "arg_3", ":", "download_urls", "(", "[", "arg_9", "]", ",", "arg_7", ",", "arg_11", ",", "arg_12", ",", "arg_1", "=", "arg_1", ",", "arg_2", "=", "arg_2", ")"],
"docstring": "Downloads Dailymotion videos by URL.",
"docstring_summary": "Downloads Dailymotion videos by URL.",
"docstring_tokens": ["Downloads", "Dailymotion", "videos", "by", "URL", "."],
"func_name": "",
"id": 0,
"identifier": "dailymotion_download",
"language": "python",
"nwo": "soimort/you-get",
"original_string": "",
"parameters": "(url, output_dir='.', merge=True, info_only=False, **kwargs)",
"path": "src/you_get/extractors/dailymotion.py",
"repo": "",
"return_statement": "",
"score": 0.9997601509094238,
"sha": "b746ac01c9f39de94cac2d56f665285b0523b974",
"url": "https://github.com/soimort/you-get/blob/b746ac01c9f39de94cac2d56f665285b0523b974/src/you_get/extractors/dailymotion.py#L13-L35"
}
```
### Data Fields
In the following each data field in go is explained for each config. The data fields are the same among all splits.
#### default
| field name | type | description |
|-----------------|-----------------------|-----------------------------------------------------------------------------------|
|id |int32 | Index of the sample |
|repo |string | repo: the owner/repo |
|path |string | path: the full path to the original file |
|func_name |string | func_name: the function or method name |
|original_string |string | original_string: the raw string before tokenization or parsing |
|language |string | language: the programming language |
|code |string | code/function: the part of the original_string that is code |
|code_tokens |Sequence[string] | code_tokens/function_tokens: tokenized version of code |
|docstring |string | docstring: the top-level comment or docstring, if it exists in the original string|
|docstring_tokens |Sequence[string] | docstring_tokens: tokenized version of docstring |
|sha |string | sha of the file |
|url |string | url of the file |
|docstring_summary|string | Summary of the docstring |
|parameters |string | parameters of the function |
|return_statement |string | return statement |
|argument_list |string | list of arguments of the function |
|identifier |string | identifier |
|nwo |string | nwo |
|score |datasets.Value("float"]| score for this search |
### Data Splits
| name |train |validation|test |
|-------|-----:|---------:|----:|
|default|251820| 9604|19210|
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
Data from CodeSearchNet Challenge dataset.
[More Information Needed]
#### Who are the source language producers?
Software Engineering developers.
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
https://github.com/microsoft, https://github.com/madlag
### Licensing Information
Computational Use of Data Agreement (C-UDA) License.
### Citation Information
```
@article{husain2019codesearchnet,
title={Codesearchnet challenge: Evaluating the state of semantic code search},
author={Husain, Hamel and Wu, Ho-Hsiang and Gazit, Tiferet and Allamanis, Miltiadis and Brockschmidt, Marc},
journal={arXiv preprint arXiv:1909.09436},
year={2019}
}
```
### Contributions
Thanks to @madlag (and partly also @ncoop57) for adding this dataset. |
true |
# Dataset Card for Fake News Filipino
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Fake News Filipino homepage](https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks)
- **Repository:** [Fake News Filipino repository](https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks)
- **Paper:** [LREC 2020 paper](http://www.lrec-conf.org/proceedings/lrec2020/index.html)
- **Leaderboard:**
- **Point of Contact:** [Jan Christian Cruz](mailto:jan_christian_cruz@dlsu.edu.ph)
### Dataset Summary
Low-Resource Fake News Detection Corpora in Filipino. The first of its kind. Contains 3,206 expertly-labeled news samples, half of which are real and half of which are fake.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is primarily in Filipino, with the addition of some English words commonly used in Filipino vernacular.
## Dataset Structure
### Data Instances
Sample data:
```
{
"label": "0",
"article": "Sa 8-pahinang desisyon, pinaboran ng Sandiganbayan First Division ang petition for Writ of Preliminary Attachment/Garnishment na inihain ng prosekusyon laban sa mambabatas."
}
```
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
Fake news articles were sourced from online sites that were tagged as fake news sites by the non-profit independent media fact-checking organization Verafiles and the National Union of Journalists in the Philippines (NUJP). Real news articles were sourced from mainstream news websites in the Philippines, including Pilipino Star Ngayon, Abante, and Bandera.
### Curation Rationale
We remedy the lack of a proper, curated benchmark dataset for fake news detection in Filipino by constructing and producing what we call “Fake News Filipino.”
### Source Data
#### Initial Data Collection and Normalization
We construct the dataset by scraping our source websites, encoding all characters into UTF-8. Preprocessing was light to keep information intact: we retain capitalization and punctuation, and do not correct any misspelled words.
#### Who are the source language producers?
Jan Christian Blaise Cruz, Julianne Agatha Tan, and Charibeth Cheng
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[Jan Christian Cruz](mailto:jan_christian_cruz@dlsu.edu.ph), Julianne Agatha Tan, and Charibeth Cheng
### Licensing Information
[More Information Needed]
### Citation Information
@inproceedings{cruz2020localization,
title={Localization of Fake News Detection via Multitask Transfer Learning},
author={Cruz, Jan Christian Blaise and Tan, Julianne Agatha and Cheng, Charibeth},
booktitle={Proceedings of The 12th Language Resources and Evaluation Conference},
pages={2596--2604},
year={2020}
}
### Contributions
Thanks to [@anaerobeth](https://github.com/anaerobeth) for adding this dataset. |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.