text-classification bool 2 classes | text stringlengths 0 664k |
|---|---|
false | # ShareGPT-Processed
The [RyokoAI/ShareGPT52K](https://huggingface.co/datasets/RyokoAI/ShareGPT52K) dataset, converted to Markdown and labeled with the language used.
## Acknowledgements
* [vinta/pangu.js](https://github.com/vinta/pangu.js) — To insert whitespace between CJK (Chinese, Japanese, Korean) and half-width characters (alphabetical letters, numerical digits and symbols).
* [matthewwithanm/python-markdownify](https://github.com/matthewwithanm/python-markdownify) — Provides a starting point to convert HTML to Markdown.
* [BYVoid/OpenCC](https://github.com/BYVoid/OpenCC) — Conversions between Traditional Chinese and Simplified Chinese.
* [aboSamoor/polyglot](https://github.com/aboSamoor/polyglot) — For language detection.
* [RyokoAI/ShareGPT52K](https://huggingface.co/datasets/RyokoAI/ShareGPT52K) — The data source.
## Data Structure
Every row in this dataset is a conversation session, consisting of:
* `id` — An ID.
* `lang` — The language code of the conversation, detected with `polyglot`.
* `conversations` — A list of messages, with each message consisting of:
* `from` — `human` or `gpt`.
* `value` — The original message content. HTML.
* `markdown` — The message converted into Markdown format.
* `opencc_converted_markdown` — The Markdown-format message converted into Traditional Chinese using `opencc`. Will be `null` for non-Chinese conversations.
Example:
```json
{
"id": "AZirHBD",
"conversations": [
{
"from": "human",
"markdown": "請問英文過去完成式的用法？",
"opencc_converted_markdown": "請問英文過去完成式的用法？",
"value": "請問英文過去完成式的用法？"
},
{
"from": "gpt",
"markdown": "英文的過去完成式是用來表示一個已經發生的動作或事件，發生在過去的某個時間，並且在這個時間之前，也發生了另一個動作或事件。在語法上，過去完成式是由助動詞 \"had\" 和過去分詞形式的動詞組成。下面是一些常見的用法：\n\n1. 表示一個已經完成的動作在另一個過去的時間點之前發生。\n\n * e.g. By the time I arrived, she had already left.\n2. 表示在過去某個時間之前就已經完成的動作。\n\n * e.g. I had studied English for five years before I moved to the United States.\n3. 表示兩個已經完成的動作中，其中一個發生在另一個之前。\n\n * e.g. After I had finished my homework, I watched TV.\n4. 用來描述一個條件或假設在過去的時間點之前已經發生。\n\n * e.g. If she had known about the party, she would have come.\n5. 用來描述過去已經完成的行動對現在的影響。\n\n * e.g. He had worked as a lawyer for many years, so he knew a lot about the law.\n\n在使用過去完成式時，需要注意時態的一致性和上下文的清晰性，以確保表達的意思清晰明確。",
"opencc_converted_markdown": "英文的過去完成式是用來表示一個已經發生的動作或事件，發生在過去的某個時間，並且在這個時間之前，也發生了另一個動作或事件。在語法上，過去完成式是由助動詞 \"had\" 和過去分詞形式的動片語成。下面是一些常見的用法：\n\n1. 表示一個已經完成的動作在另一個過去的時間點之前發生。\n\n * e.g. By the time I arrived, she had already left.\n2. 表示在過去某個時間之前就已經完成的動作。\n\n * e.g. I had studied English for five years before I moved to the United States.\n3. 表示兩個已經完成的動作中，其中一個發生在另一個之前。\n\n * e.g. After I had finished my homework, I watched TV.\n4. 用來描述一個條件或假設在過去的時間點之前已經發生。\n\n * e.g. If she had known about the party, she would have come.\n5. 用來描述過去已經完成的行動對現在的影響。\n\n * e.g. He had worked as a lawyer for many years, so he knew a lot about the law.\n\n在使用過去完成式時，需要注意時態的一致性和上下文的清晰性，以確保表達的意思清晰明確。",
"value": "<div class=\"markdown prose w-full break-words dark:prose-invert light\"><p>英文的過去完成式是用來表示一個已經發生的動作或事件，發生在過去的某個時間，並且在這個時間之前，也發生了另一個動作或事件。在語法上，過去完成式是由助動詞 \"had\" 和過去分詞形式的動詞組成。下面是一些常見的用法：</p><ol><li><p>表示一個已經完成的動作在另一個過去的時間點之前發生。</p><ul><li>e.g. By the time I arrived, she had already left.</li></ul></li><li><p>表示在過去某個時間之前就已經完成的動作。</p><ul><li>e.g. I had studied English for five years before I moved to the United States.</li></ul></li><li><p>表示兩個已經完成的動作中，其中一個發生在另一個之前。</p><ul><li>e.g. After I had finished my homework, I watched TV.</li></ul></li><li><p>用來描述一個條件或假設在過去的時間點之前已經發生。</p><ul><li>e.g. If she had known about the party, she would have come.</li></ul></li><li><p>用來描述過去已經完成的行動對現在的影響。</p><ul><li>e.g. He had worked as a lawyer for many years, so he knew a lot about the law.</li></ul></li></ol><p>在使用過去完成式時，需要注意時態的一致性和上下文的清晰性，以確保表達的意思清晰明確。</p></div>"
},
{
"from": "human",
"markdown": "英文現在式的用法",
"opencc_converted_markdown": "英文現在式的用法",
"value": "英文現在式的用法"
},
{
"from": "gpt",
"markdown": "英文的現在式表示的是現在正在進行或習慣性發生的動作，也可以表示客觀事實或普遍真理。下面是一些常見的用法：\n\n1. 表示現在正在進行的動作。\n\n * e.g. I am typing on my computer right now.\n2. 表示習慣性的行為或狀態。\n\n * e.g. I usually drink coffee in the morning.\n3. 表示事實、真相或存在的狀態。\n\n * e.g. The earth orbits around the sun.\n4. 用於引述、註解或解釋現在發生的事情。\n\n * e.g. He says he is feeling better today.\n5. 表示未來已經計劃好的事件或行動。\n\n * e.g. I am leaving for Paris tomorrow.\n\n在使用現在式時，需要注意動詞的時態和主語的人稱和數，以確保表達的意思清晰明確。",
"opencc_converted_markdown": "英文的現在式表示的是現在正在進行或習慣性發生的動作，也可以表示客觀事實或普遍真理。下面是一些常見的用法：\n\n1. 表示現在正在進行的動作。\n\n * e.g. I am typing on my computer right now.\n2. 表示習慣性的行為或狀態。\n\n * e.g. I usually drink coffee in the morning.\n3. 表示事實、真相或存在的狀態。\n\n * e.g. The earth orbits around the sun.\n4. 用於引述、註解或解釋現在發生的事情。\n\n * e.g. He says he is feeling better today.\n5. 表示未來已經計劃好的事件或行動。\n\n * e.g. I am leaving for Paris tomorrow.\n\n在使用現在式時，需要注意動詞的時態和主語的人稱和數，以確保表達的意思清晰明確。",
"value": "<div class=\"markdown prose w-full break-words dark:prose-invert light\"><p>英文的現在式表示的是現在正在進行或習慣性發生的動作，也可以表示客觀事實或普遍真理。下面是一些常見的用法：</p><ol><li><p>表示現在正在進行的動作。</p><ul><li>e.g. I am typing on my computer right now.</li></ul></li><li><p>表示習慣性的行為或狀態。</p><ul><li>e.g. I usually drink coffee in the morning.</li></ul></li><li><p>表示事實、真相或存在的狀態。</p><ul><li>e.g. The earth orbits around the sun.</li></ul></li><li><p>用於引述、註解或解釋現在發生的事情。</p><ul><li>e.g. He says he is feeling better today.</li></ul></li><li><p>表示未來已經計劃好的事件或行動。</p><ul><li>e.g. I am leaving for Paris tomorrow.</li></ul></li></ol><p>在使用現在式時，需要注意動詞的時態和主語的人稱和數，以確保表達的意思清晰明確。</p></div>"
}
],
"lang": "zh_Hant"
}
```
## Languages
```json
{
"en": 63940,
"zh_Hant": 3201,
"zh": 6394,
"es": 2080,
"ja": 1525,
"unknown": 4212,
"pt": 778,
"it": 512,
"ko": 2529,
"nl": 195,
"ro": 63,
"fr": 1835,
"vi": 245,
"de": 800,
"cs": 172,
"iw": 123,
"ru": 448,
"id": 369,
"pl": 194,
"no": 65,
"ar": 78,
"tr": 150,
"da": 68,
"sa": 10,
"sv": 87,
"ia": 2,
"fo": 7,
"sq": 4,
"el": 14,
"fa": 22,
"bs": 13,
"rm": 2,
"ms": 45,
"ca": 14,
"hr": 26,
"sk": 23,
"uk": 106,
"th": 33,
"fi": 32,
"tlh": 1,
"hu": 46,
"gl": 21,
"bg": 4,
"sr": 18,
"is": 2,
"ts": 9,
"la": 27,
"sl": 6,
"uz": 5,
"qu": 3,
"ay": 7,
"mi": 3,
"ceb": 1,
"gu": 1,
"oc": 8,
"aa": 2,
"haw": 6,
"xh": 4,
"ny": 4,
"hmn": 2,
"tk": 2,
"sco": 6,
"zzp": 4,
"so": 2,
"mg": 1,
"to": 1,
"mk": 1,
"ha": 2,
"ur": 2,
"nn": 4,
"lv": 2,
"mt": 2,
"gn": 2,
"et": 2,
"ie": 3,
"tl": 3,
"lb": 4,
"bn": 1,
"rw": 4,
"bi": 1,
"ga": 1,
"war": 1,
"sw": 2,
"eo": 2,
"eu": 2,
"lt": 1,
"af": 2,
"ht": 3,
"fj": 1,
"st": 1,
"na": 1,
"sd": 1,
"fy": 1,
"jw": 1
}
```
Detected with `polyglot`. |
true | ERROR: type should be string, got "\nhttps://github.com/heyunh2015/PARADE_dataset\n\n```\n@inproceedings{he-etal-2020-parade,\n title = \"{PARADE}: {A} {N}ew {D}ataset for {P}araphrase {I}dentification {R}equiring {C}omputer {S}cience {D}omain {K}nowledge\",\n author = \"He, Yun and\n Wang, Zhuoer and\n Zhang, Yin and\n Huang, Ruihong and\n Caverlee, James\",\n booktitle = \"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)\",\n month = nov,\n year = \"2020\",\n address = \"Online\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://aclanthology.org/2020.emnlp-main.611\",\n doi = \"10.18653/v1/2020.emnlp-main.611\",\n pages = \"7572--7582\",\n abstract = \"We present a new benchmark dataset called PARADE for paraphrase identification that requires specialized domain knowledge. PARADE contains paraphrases that overlap very little at the lexical and syntactic level but are semantically equivalent based on computer science domain knowledge, as well as non-paraphrases that overlap greatly at the lexical and syntactic level but are not semantically equivalent based on this domain knowledge. Experiments show that both state-of-the-art neural models and non-expert human annotators have poor performance on PARADE. For example, BERT after fine-tuning achieves an F1 score of 0.709, which is much lower than its performance on other paraphrase identification datasets. PARADE can serve as a resource for researchers interested in testing models that incorporate domain knowledge. We make our data and code freely available.\",\n}\n```" |
true | |
true |
Read this [BLOG](https://neuralmagic.com/blog/classifying-finance-tweets-in-real-time-with-sparse-transformers/) to see how I fine-tuned a sparse transformer on this dataset.
### Dataset Description
The Twitter Financial News dataset is an English-language dataset containing an annotated corpus of finance-related tweets. This dataset is used to classify finance-related tweets for their topic.
1. The dataset holds 21,107 documents annotated with 20 labels:
```python
topics = {
"LABEL_0": "Analyst Update",
"LABEL_1": "Fed | Central Banks",
"LABEL_2": "Company | Product News",
"LABEL_3": "Treasuries | Corporate Debt",
"LABEL_4": "Dividend",
"LABEL_5": "Earnings",
"LABEL_6": "Energy | Oil",
"LABEL_7": "Financials",
"LABEL_8": "Currencies",
"LABEL_9": "General News | Opinion",
"LABEL_10": "Gold | Metals | Materials",
"LABEL_11": "IPO",
"LABEL_12": "Legal | Regulation",
"LABEL_13": "M&A | Investments",
"LABEL_14": "Macro",
"LABEL_15": "Markets",
"LABEL_16": "Politics",
"LABEL_17": "Personnel Change",
"LABEL_18": "Stock Commentary",
"LABEL_19": "Stock Movement",
}
```
The data was collected using the Twitter API. The current dataset supports the multi-class classification task.
### Task: Topic Classification
# Data Splits
There are 2 splits: train and validation. Below are the statistics:
| Dataset Split | Number of Instances in Split |
| ------------- | ------------------------------------------- |
| Train | 16,990 |
| Validation | 4,118 |
# Licensing Information
The Twitter Financial Dataset (topic) version 1.0.0 is released under the MIT License. |
true |
# Dataset Card for [Dataset Name]
## 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:** [homepage](https://github.com/masakhane-io/masakhane-news)
- **Repository:** [github](https://github.com/masakhane-io/masakhane-news)
- **Paper:** [paper]()
- **Point of Contact:** [Masakhane](https://www.masakhane.io/) or didelani@lsv.uni-saarland.de
### Dataset Summary
MasakhaNEWS is the largest publicly available dataset for news topic classification in 16 languages widely spoken in Africa.
The train/validation/test sets are available for all the 16 languages.
### Supported Tasks and Leaderboards
[More Information Needed]
- `news topic classification`: categorize news articles into new topics e.g business, sport sor politics.
### Languages
There are 16 languages available :
- Amharic (amh)
- English (eng)
- French (fra)
- Hausa (hau)
- Igbo (ibo)
- Lingala (lin)
- Luganda (lug)
- Oromo (orm)
- Nigerian Pidgin (pcm)
- Rundi (run)
- chShona (sna)
- Somali (som)
- Kiswahili (swą)
- Tigrinya (tir)
- isiXhosa (xho)
- Yorùbá (yor)
## Dataset Structure
### Data Instances
The examples look like this for Yorùbá:
```
from datasets import load_dataset
data = load_dataset('masakhane/masakhanews', 'yor')
# Please, specify the language code
# A data point example is below:
{
'label': 0,
'headline': "'The barriers to entry have gone - go for it now'",
'text': "j Lalvani, CEO of Vitabiotics and former Dragons' Den star, shares his business advice for our CEO Secrets series.\nProduced, filmed and edited by Dougal Shaw",
'headline_text': "'The barriers to entry have gone - go for it now' j Lalvani, CEO of Vitabiotics and former Dragons' Den star, shares his business advice for our CEO Secrets series.\nProduced, filmed and edited by Dougal Shaw",
'url': '/news/business-61880859'
}
```
### Data Fields
- `label`: news topic id
- `headline`: news title/headline
- `text`: news body
- `headline_text`: concatenation of headline and news body
- `url`: website address
The news topics correspond to this list:
```
"business", "entertainment", "health", "politics", "religion", "sports", "technology"
```
### Data Splits
For all languages, there are three splits.
The original splits were named `train`, `dev` and `test` and they correspond to the `train`, `validation` and `test` splits.
The splits have the following sizes :
| Language | train | validation | test |
|-----------------|------:|-----------:|-----:|
| Amharic | 1311 | 188 | 376 |
| English | 3309 | 472 | 948 |
| French | 1476 | 211 | 422 |
| Hausa | 2219 | 317 | 637 |
| Igbo | 1356 | 194 | 390 |
| Lingala | 608 | 87 | 175 |
| Luganda | 771 | 110 | 223 |
| Oromo | 1015 | 145 | 292 |
| Nigerian-Pidgin | 1060 | 152 | 305 |
| Rundi | 1117 | 159 | 322 |
| chiShona | 1288 | 185 | 369 |
| Somali | 1021 | 148 | 294 |
| Kiswahili | 1658 | 237 | 476 |
| Tigrinya | 947 | 137 | 272 |
| isiXhosa | 1032 | 147 | 297 |
| Yoruba | 1433 | 206 | 411 |
## Dataset Creation
### Curation Rationale
The dataset was introduced to introduce new resources to 20 languages that were under-served for natural language processing.
[More Information Needed]
### Source Data
The source of the data is from the news domain, details can be found here ****
#### Initial Data Collection and Normalization
The articles were word-tokenized, information on the exact pre-processing pipeline is unavailable.
#### Who are the source language producers?
The source language was produced by journalists and writers employed by the news agency and newspaper mentioned above.
### Annotations
#### Annotation process
Details can be found here **
#### Who are the annotators?
Annotators were recruited from [Masakhane](https://www.masakhane.io/)
### Personal and Sensitive Information
The data is sourced from newspaper source and only contains mentions of public figures or individuals
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
Users should keep in mind that the dataset only contains news text, which might limit the applicability of the developed systems to other domains.
## Additional Information
### Dataset Curators
### Licensing Information
The licensing status of the data is CC 4.0 Non-Commercial
### Citation Information
Provide the [BibTex](http://www.bibtex.org/)-formatted reference for the dataset. For example:
```
@article{Adelani2023MasakhaNEWS,
title={MasakhaNEWS: News Topic Classification for African languages},
author={David Ifeoluwa Adelani and Marek Masiak and Israel Abebe Azime and Jesujoba Oluwadara Alabi and Atnafu Lambebo Tonja and Christine Mwase and Odunayo Ogundepo and Bonaventure F. P. Dossou and Akintunde Oladipo and Doreen Nixdorf and Chris Chinenye Emezue and Sana Sabah al-azzawi and Blessing K. Sibanda and Davis David and Lolwethu Ndolela and Jonathan Mukiibi and Tunde Oluwaseyi Ajayi and Tatiana Moteu Ngoli and Brian Odhiambo and Abraham Toluwase Owodunni and Nnaemeka C. Obiefuna and Shamsuddeen Hassan Muhammad and Saheed Salahudeen Abdullahi and Mesay Gemeda Yigezu and Tajuddeen Gwadabe and Idris Abdulmumin and Mahlet Taye Bame and Oluwabusayo Olufunke Awoyomi and Iyanuoluwa Shode and Tolulope Anu Adelani and Habiba Abdulganiy Kailani and Abdul-Hakeem Omotayo and Adetola Adeeko and Afolabi Abeeb and Anuoluwapo Aremu and Olanrewaju Samuel and Clemencia Siro and Wangari Kimotho and Onyekachi Raphael Ogbu and Chinedu E. Mbonu and Chiamaka I. Chukwuneke and Samuel Fanijo and Jessica Ojo and Oyinkansola F. Awosan and Tadesse Kebede Guge and Sakayo Toadoum Sari and Pamela Nyatsine and Freedmore Sidume and Oreen Yousuf and Mardiyyah Oduwole and Ussen Kimanuka and Kanda Patrick Tshinu and Thina Diko and Siyanda Nxakama and Abdulmejid Tuni Johar and Sinodos Gebre and Muhidin Mohamed and Shafie Abdi Mohamed and Fuad Mire Hassan and Moges Ahmed Mehamed and Evrard Ngabire and and Pontus Stenetorp},
journal={ArXiv},
year={2023},
volume={}
}
```
### Contributions
Thanks to [@dadelani](https://github.com/dadelani) for adding this dataset. |
true | https://github.com/rudinger/defeasible-nli
```
@inproceedings{rudinger2020thinking,
title={Thinking like a skeptic:
feasible inference in natural language},
author={Rudinger, Rachel and Shwartz, Vered and Hwang, Jena D and Bhagavatula, Chandra and Forbes, Maxwell and Le Bras, Ronan and Smith, Noah A and Choi, Yejin},
booktitle={Findings of the Association for Computational Linguistics: EMNLP 2020},
pages={4661--4675},
year={2020}
}
``` |
false | # Dataset Card for ShareGPT~~52K~~90K
## Dataset Description
- **Homepage: N/A**
- **Repository: N/A**
- **Paper: N/A**
- **Leaderboard: N/A**
- **Point of Contact:** Ronsor Labs <ronsor@ronsor.com>
### Dataset Summary
This dataset is a collection of approximately ~~52,000~~**90,000** conversations scraped via the ShareGPT API before it was shut down.
These conversations include both user prompts and responses from OpenAI's ChatGPT.
This repository now contains the new 90K conversations version. The previous 52K may
be found in the `old/` directory.
### Supported Tasks and Leaderboards
* text-generation
### Languages
This dataset is expected to primarily consist of messages in English and other Western languages.
## Dataset Structure
### Data Instances
```json
{
"id": "2wtLdZm",
"conversations": [
{
"from": "human",
"value": "Are you familiar with the SAS programming language?"
},
{
"from": "gpt",
"value": "<div class=\"markdown prose w-full break-words dark:prose-invert light\"><p>Yes, I am familiar with the SAS programming language. SAS is a statistical software suite that is widely used in data analysis, data management, and business intelligence applications. It has its own programming language, which is used to manipulate and analyze data, generate reports, and automate data-driven workflows. The language is known for its ease of use and powerful capabilities, and it is commonly used in industries such as healthcare, finance, and government.</p></div>"
},
{
"from": "human",
"value": "Can you write a SAS proc that imports a dataset from a CSV saved on my local machine?"
}
]
}
```
### Data Fields
* **id**: conversation id
* **conversations**: conversation session array
* **from**: ChatGPT ("gpt") or the user ("human")
* **value**: message contents as raw HTML
### Data Splits
N/A
## Dataset Creation
### Curation Rationale
This is a decently large dataset of realistic human-AI conversations which I believe should be released
to the research community.
### Source Data
#### Initial Data Collection and Normalization
This data was collected using the ShareGPT API.
#### Who are the source language producers?
ShareGPT users and OpenAI ChatGPT.
### Annotations
#### Annotation process
N/A
#### Who are the annotators?
N/A
### Personal and Sensitive Information
This dataset *may* contain personal information, if ShareGPT users were sending such information to
ChatGPT. ChatGPT warns users not to submit personal information to it, however, so without further
evaluation, we believe that this dataset should contain little or no personal information.
## Considerations for Using the Data
### Social Impact of Dataset
This dataset may be used to train models that are competitive with OpenAI's ChatGPT. Please filter
this dataset first, as it may contain canned responses, raw HTML, and other undesirable information.
### Discussion of Biases
This dataset exhibits all the biases of OpenAI's ChatGPT models (GPT-3.5 and GPT-4) as well as the
biases of the users who uploaded the conversations.
### Other Known Limitations
N/A
## Additional Information
### Dataset Curators
None.
### Licensing Information
**CC0: No Rights Reserved.**
The output of machine learning algorithms is uncopyrightable in the United States and other jurisdictions.
**Additionally, the OpenAI terms of service do not apply to this dataset as users of this dataset
are not accessing the OpenAI service.**
### Citation Information
TODO
### Contributions
These conversations were allegedly scraped by an anonymous user on 4chan.
The 90K version was sourced from [this post](https://boards.4channel.org/g/thread/92487155/lmg-local-models-general-snail-edition#p92490887).
Thanks, anon!
|
false |
# Dataset Card for Dataset Name
## Dataset Description
- **Homepage:** https://osu-nlp-group.github.io/MagicBrush
- **Repository:** https://github.com/OSU-NLP-Group/MagicBrush
<!-- **Paper:** https://arxiv.org/abs/2306.06070 -->
- **Point of Contact:** [Kai Zhang](mailto:zhang.13253@osu.edu)
### Dataset Summary
MagicBrush is the first large-scale, manually-annotated instruction-guided image editing dataset covering diverse scenarios single-turn, multi-turn, mask-provided, and mask-free editing. MagicBrush comprises 10K (source image, instruction, target image) triples, which is sufficient to train large-scale image editing models.
Please check our [website](https://osu-nlp-group.github.io/MagicBrush/) to explore more visual results.
#### Dataset Structure
"img_id" (str): same from COCO id but in string type, for easier test set loading
"turn_index" (int32): the edit turn in the image
"source_img" (str): input image, could be the original real image (turn_index=1) and edited images from last turn (turn_index >=2)
"mask_img" (str): free-form mask image (white region), can be used in mask-provided setting to limit the region to be edited.
"instruction" (str): edit instruction of how the input image should be changed.
"target_img" (str): the edited image corresponding to the input image and instruction.
If you need auxiliary data, please use [training set](https://buckeyemailosu-my.sharepoint.com/:u:/g/personal/zhang_13253_buckeyemail_osu_edu/EYEqf_yG36lAgiXw2GvRl0QBDBOeZHxvNgxO0Ec9WDMcNg) and [dev set](https://buckeyemailosu-my.sharepoint.com/:u:/g/personal/zhang_13253_buckeyemail_osu_edu/EXkXvvC95C1JsgMNWGL_RcEBElmsGxXwAAAdGamN8PNhrg)
### Splits
train: 8,807 edit turns (4,512 edit sessions).
dev: 528 edit turns (266 edit sessions).
test: (To prevent potential data leakage, please check our repo for information on obtaining the test set.)
### Licensing Information
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
## Citation Information
If you find this dataset useful, please consider citing our paper:
```
@misc{Zhang2023MagicBrush,
title={MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing},
author={Kai Zhang and Lingbo Mo and Wenhu Chen and Huan Sun and Yu Su},
year={2023},
eprint={2306.10012},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
``` |
false |
# Dataset Card for BEIR Benchmark
## 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/UKPLab/beir
- **Repository:** https://github.com/UKPLab/beir
- **Paper:** https://openreview.net/forum?id=wCu6T5xFjeJ
- **Leaderboard:** https://docs.google.com/spreadsheets/d/1L8aACyPaXrL8iEelJLGqlMqXKPX2oSP_R10pZoy77Ns
- **Point of Contact:** nandan.thakur@uwaterloo.ca
### Dataset Summary
BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:
- Fact-checking: [FEVER](http://fever.ai), [Climate-FEVER](http://climatefever.ai), [SciFact](https://github.com/allenai/scifact)
- Question-Answering: [NQ](https://ai.google.com/research/NaturalQuestions), [HotpotQA](https://hotpotqa.github.io), [FiQA-2018](https://sites.google.com/view/fiqa/)
- Bio-Medical IR: [TREC-COVID](https://ir.nist.gov/covidSubmit/index.html), [BioASQ](http://bioasq.org), [NFCorpus](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)
- News Retrieval: [TREC-NEWS](https://trec.nist.gov/data/news2019.html), [Robust04](https://trec.nist.gov/data/robust/04.guidelines.html)
- Argument Retrieval: [Touche-2020](https://webis.de/events/touche-20/shared-task-1.html), [ArguAna](tp://argumentation.bplaced.net/arguana/data)
- Duplicate Question Retrieval: [Quora](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs), [CqaDupstack](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)
- Citation-Prediction: [SCIDOCS](https://allenai.org/data/scidocs)
- Tweet Retrieval: [Signal-1M](https://research.signal-ai.com/datasets/signal1m-tweetir.html)
- Entity Retrieval: [DBPedia](https://github.com/iai-group/DBpedia-Entity/)
All these datasets have been preprocessed and can be used for your experiments.
```python
```
### Supported Tasks and Leaderboards
The dataset supports a leaderboard that evaluates models against task-specific metrics such as F1 or EM, as well as their ability to retrieve supporting information from Wikipedia.
The current best performing models can be found [here](https://eval.ai/web/challenges/challenge-page/689/leaderboard/).
### Languages
All tasks are in English (`en`).
## Dataset Structure
All BEIR datasets must contain a corpus, queries and qrels (relevance judgments file). They must be in the following format:
- `corpus` file: a `.jsonl` file (jsonlines) that contains a list of dictionaries, each with three fields `_id` with unique document identifier, `title` with document title (optional) and `text` with document paragraph or passage. For example: `{"_id": "doc1", "title": "Albert Einstein", "text": "Albert Einstein was a German-born...."}`
- `queries` file: a `.jsonl` file (jsonlines) that contains a list of dictionaries, each with two fields `_id` with unique query identifier and `text` with query text. For example: `{"_id": "q1", "text": "Who developed the mass-energy equivalence formula?"}`
- `qrels` file: a `.tsv` file (tab-seperated) that contains three columns, i.e. the `query-id`, `corpus-id` and `score` in this order. Keep 1st row as header. For example: `q1 doc1 1`
### Data Instances
A high level example of any beir dataset:
```python
corpus = {
"doc1" : {
"title": "Albert Einstein",
"text": "Albert Einstein was a German-born theoretical physicist. who developed the theory of relativity, \
one of the two pillars of modern physics (alongside quantum mechanics). His work is also known for \
its influence on the philosophy of science. He is best known to the general public for his mass–energy \
equivalence formula E = mc2, which has been dubbed 'the world's most famous equation'. He received the 1921 \
Nobel Prize in Physics 'for his services to theoretical physics, and especially for his discovery of the law \
of the photoelectric effect', a pivotal step in the development of quantum theory."
},
"doc2" : {
"title": "", # Keep title an empty string if not present
"text": "Wheat beer is a top-fermented beer which is brewed with a large proportion of wheat relative to the amount of \
malted barley. The two main varieties are German Weißbier and Belgian witbier; other types include Lambic (made\
with wild yeast), Berliner Weisse (a cloudy, sour beer), and Gose (a sour, salty beer)."
},
}
queries = {
"q1" : "Who developed the mass-energy equivalence formula?",
"q2" : "Which beer is brewed with a large proportion of wheat?"
}
qrels = {
"q1" : {"doc1": 1},
"q2" : {"doc2": 1},
}
```
### Data Fields
Examples from all configurations have the following features:
### Corpus
- `corpus`: a `dict` feature representing the document title and passage text, made up of:
- `_id`: a `string` feature representing the unique document id
- `title`: a `string` feature, denoting the title of the document.
- `text`: a `string` feature, denoting the text of the document.
### Queries
- `queries`: a `dict` feature representing the query, made up of:
- `_id`: a `string` feature representing the unique query id
- `text`: a `string` feature, denoting the text of the query.
### Qrels
- `qrels`: a `dict` feature representing the query document relevance judgements, made up of:
- `_id`: a `string` feature representing the query id
- `_id`: a `string` feature, denoting the document id.
- `score`: a `int32` feature, denoting the relevance judgement between query and document.
### Data Splits
| Dataset | Website| BEIR-Name | Type | Queries | Corpus | Rel D/Q | Down-load | md5 |
| -------- | -----| ---------| --------- | ----------- | ---------| ---------| :----------: | :------:|
| MSMARCO | [Homepage](https://microsoft.github.io/msmarco/)| ``msmarco`` | ``train``<br>``dev``<br>``test``| 6,980 | 8.84M | 1.1 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/msmarco.zip) | ``444067daf65d982533ea17ebd59501e4`` |
| TREC-COVID | [Homepage](https://ir.nist.gov/covidSubmit/index.html)| ``trec-covid``| ``test``| 50| 171K| 493.5 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/trec-covid.zip) | ``ce62140cb23feb9becf6270d0d1fe6d1`` |
| NFCorpus | [Homepage](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/) | ``nfcorpus`` | ``train``<br>``dev``<br>``test``| 323 | 3.6K | 38.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nfcorpus.zip) | ``a89dba18a62ef92f7d323ec890a0d38d`` |
| BioASQ | [Homepage](http://bioasq.org) | ``bioasq``| ``train``<br>``test`` | 500 | 14.91M | 8.05 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#2-bioasq) |
| NQ | [Homepage](https://ai.google.com/research/NaturalQuestions) | ``nq``| ``train``<br>``test``| 3,452 | 2.68M | 1.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nq.zip) | ``d4d3d2e48787a744b6f6e691ff534307`` |
| HotpotQA | [Homepage](https://hotpotqa.github.io) | ``hotpotqa``| ``train``<br>``dev``<br>``test``| 7,405 | 5.23M | 2.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/hotpotqa.zip) | ``f412724f78b0d91183a0e86805e16114`` |
| FiQA-2018 | [Homepage](https://sites.google.com/view/fiqa/) | ``fiqa`` | ``train``<br>``dev``<br>``test``| 648 | 57K | 2.6 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fiqa.zip) | ``17918ed23cd04fb15047f73e6c3bd9d9`` |
| Signal-1M(RT) | [Homepage](https://research.signal-ai.com/datasets/signal1m-tweetir.html)| ``signal1m`` | ``test``| 97 | 2.86M | 19.6 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#4-signal-1m) |
| TREC-NEWS | [Homepage](https://trec.nist.gov/data/news2019.html) | ``trec-news`` | ``test``| 57 | 595K | 19.6 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#1-trec-news) |
| ArguAna | [Homepage](http://argumentation.bplaced.net/arguana/data) | ``arguana``| ``test`` | 1,406 | 8.67K | 1.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/arguana.zip) | ``8ad3e3c2a5867cdced806d6503f29b99`` |
| Touche-2020| [Homepage](https://webis.de/events/touche-20/shared-task-1.html) | ``webis-touche2020``| ``test``| 49 | 382K | 19.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/webis-touche2020.zip) | ``46f650ba5a527fc69e0a6521c5a23563`` |
| CQADupstack| [Homepage](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/) | ``cqadupstack``| ``test``| 13,145 | 457K | 1.4 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/cqadupstack.zip) | ``4e41456d7df8ee7760a7f866133bda78`` |
| Quora| [Homepage](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs) | ``quora``| ``dev``<br>``test``| 10,000 | 523K | 1.6 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/quora.zip) | ``18fb154900ba42a600f84b839c173167`` |
| DBPedia | [Homepage](https://github.com/iai-group/DBpedia-Entity/) | ``dbpedia-entity``| ``dev``<br>``test``| 400 | 4.63M | 38.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/dbpedia-entity.zip) | ``c2a39eb420a3164af735795df012ac2c`` |
| SCIDOCS| [Homepage](https://allenai.org/data/scidocs) | ``scidocs``| ``test``| 1,000 | 25K | 4.9 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scidocs.zip) | ``38121350fc3a4d2f48850f6aff52e4a9`` |
| FEVER | [Homepage](http://fever.ai) | ``fever``| ``train``<br>``dev``<br>``test``| 6,666 | 5.42M | 1.2| [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fever.zip) | ``5a818580227bfb4b35bb6fa46d9b6c03`` |
| Climate-FEVER| [Homepage](http://climatefever.ai) | ``climate-fever``|``test``| 1,535 | 5.42M | 3.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/climate-fever.zip) | ``8b66f0a9126c521bae2bde127b4dc99d`` |
| SciFact| [Homepage](https://github.com/allenai/scifact) | ``scifact``| ``train``<br>``test``| 300 | 5K | 1.1 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scifact.zip) | ``5f7d1de60b170fc8027bb7898e2efca1`` |
| Robust04 | [Homepage](https://trec.nist.gov/data/robust/04.guidelines.html) | ``robust04``| ``test``| 249 | 528K | 69.9 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#3-robust04) |
## 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
[Needs More Information]
### Citation Information
Cite as:
```
@inproceedings{
thakur2021beir,
title={{BEIR}: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models},
author={Nandan Thakur and Nils Reimers and Andreas R{\"u}ckl{\'e} and Abhishek Srivastava and Iryna Gurevych},
booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
year={2021},
url={https://openreview.net/forum?id=wCu6T5xFjeJ}
}
```
### Contributions
Thanks to [@Nthakur20](https://github.com/Nthakur20) for adding this dataset. |
true |
# Dataset Card for CSFD movie reviews (Slovak)
## Dataset Description
The dataset contains user reviews from Czech/Slovak movie databse website <https://csfd.cz>.
Each review contains text, rating, date, and basic information about the movie (or TV series).
The dataset has in total (train+validation+test) 30,000 reviews. The data is balanced - each rating has approximately the same frequency.
## Dataset Features
Each sample contains:
- `review_id`: unique string identifier of the review.
- `rating_str`: string representation of the rating (from "0/5" to "5/5")
- `rating_int`: integer representation of the rating (from 0 to 5)
- `date`: date of publishing the review (just date, no time nor timezone)
- `comment_language`: language of the review (always "sk")
- `comment`: the string of the review
- `item_title`: title of the reviewed item
- `item_year`: publishing year of the item (string, can also be a range)
- `item_kind`: kind of the item - either "film" or "seriál"
- `item_genres`: list of genres of the item
- `item_directors`: list of director names of the item
- `item_screenwriters`: list of screenwriter names of the item
- `item_cast`: list of actors and actress in the item
## Dataset Source
The data was mined and sampled from the <https://csfd.cz> website.
Make sure to comply with the terms of conditions of the website operator when using the data.
|
false |
# Dataset Card for DivEMT
*For more details on DivEMT, see our [EMNLP 2022 Paper](https://arxiv.org/abs/2205.12215) and our [Github repository](https://github.com/gsarti/divemt)*
## Dataset Description
- **Source:** [Github](https://github.com/gsarti/divemt)
- **Paper:** [Arxiv](https://arxiv.org/abs/2205.12215)
- **Point of Contact:** [Gabriele Sarti](mailto:g.sarti@rug.nl)
[Gabriele Sarti](https://gsarti.com) • [Arianna Bisazza](https://www.cs.rug.nl/~bisazza/) • [Ana Guerberof Arenas](https://scholar.google.com/citations?user=i6bqaTsAAAAJ) • [Antonio Toral](https://antoniotor.al/)
<img src="https://huggingface.co/datasets/GroNLP/divemt/resolve/main/divemt.png" alt="DivEMT annotation pipeline" width="600"/>
>We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate or post-edit the same set of English documents into Arabic, Dutch, Italian, Turkish, Ukrainian, and Vietnamese. During the process, their edits, keystrokes, editing times and pauses were recorded, enabling an in-depth, cross-lingual evaluation of NMT quality and post-editing effectiveness. Using this new dataset, we assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity. We find that post-editing is consistently faster than translation from scratch. However, the magnitude of productivity gains varies widely across systems and languages, highlighting major disparities in post-editing effectiveness for languages at different degrees of typological relatedness to English, even when controlling for system architecture and training data size. We publicly release the complete dataset including all collected behavioral data, to foster new research on the translation capabilities of NMT systems for typologically diverse languages.
### Dataset Summary
This dataset contains the processed `warmup` and `main` splits of the DivEMT dataset. A sample of documents extracted from the Flores-101 corpus were either translated from scratch or post-edited from an existing automatic translation by a total of 18 professional translators across six typologically diverse languages (Arabic, Dutch, Italian, Turkish, Ukrainian, Vietnamese). During the translation, behavioral data (keystrokes, pauses, editing times) were collected using the [PET](https://github.com/wilkeraziz/PET) platform.
We publicly release the processed dataset including all collected behavioural data, to foster new research on the ability of state-of-the-art NMT systems to generate text in typologically diverse languages.
### News 🎉
**February, 2023**: The DivEMT dataset now contains linguistic annotations (`*_annotations` fields) computed with Stanza and word-level quality estimation tags (`src_wmt22_qe`, `mt_wmt22_qe`) obtained using the same scripts adopted for the WMT22 QE Task 2.
### Languages
The language data of DivEMT is in English (BCP-47 `en`), Italian (BCP-47 `it`), Dutch (BCP-47 `nl`), Arabic (BCP-47 `ar`), Turkish (BCP-47 `tr`), Ukrainian (BCP-47 `uk`) and Vietnamese (BCP-47 `vi`)
## Dataset Structure
### Data Instances
The dataset contains two configurations: `main` and `warmup`. `main` contains the full data collected during the main task and analyzed during our experiments. `warmup` contains the data collected in the verification phase, before the main task begins.
### Data Fields
The following fields are contained in the training set:
|Field|Description|
|-----|-----------|
|`unit_id` | The full entry identifier. Format: `flores101-{config}-{lang}-{doc_id}-{modality}-{sent_in_doc_num}` |
|`flores_id` | Index of the sentence in the original [Flores-101](https://huggingface.co/datasets/gsarti/flores_101) dataset |
|`item_id` | The sentence identifier. The first digits of the number represent the document containing the sentence, while the last digit of the number represents the sentence position inside the document. Documents can contain from 3 to 5 contiguous sentences each. |
|`subject_id` | The identifier for the translator performing the translation from scratch or post-editing task. Values: `t1`, `t2` or `t3`. |
|`lang_id` | Language identifier for the sentence, using Flores-101 three-letter format (e.g. `ara`, `nld`)|
|`doc_id` | Document identifier for the sentence |
|`task_type` | The modality of the translation task. Values: `ht` (translation from scratch), `pe1` (post-editing Google Translate translations), `pe2` (post-editing [mBART 1-to-50](https://huggingface.co/facebook/mbart-large-50-one-to-many-mmt) translations). |
|`translation_type` | Either `ht` for from scratch or `pe` for post-editing |
|`src_len_chr` | Length of the English source text in number of characters |
|`mt_len_chr` | Length of the machine translation in number of characters (NaN for ht) |
|`tgt_len_chr` | Length of the target text in number of characters |
|`src_len_wrd` | Length of the English source text in number of words |
|`mt_len_wrd` | Length of the machine translation in number of words (NaN for ht) |
|`tgt_len_wrd` | Length of the target text in number of words |
|`edit_time` | Total editing time for the translation in seconds. |
|`k_total` | Total number of keystrokes for the translation. |
|`k_letter` | Total number of letter keystrokes for the translation. |
|`k_digit` | Total number of digit keystrokes for the translation. |
|`k_white` | Total number of whitespace keystrokes for the translation. |
|`k_symbol` | Total number of symbol (punctuation, etc.) keystrokes for the translation. |
|`k_nav` | Total number of navigation keystrokes (left-right arrows, mouse clicks) for the translation. |
|`k_erase` | Total number of erase keystrokes (backspace, cancel) for the translation. |
|`k_copy` | Total number of copy (Ctrl + C) actions during the translation. |
|`k_cut` | Total number of cut (Ctrl + X) actions during the translation. |
|`k_paste` | Total number of paste (Ctrl + V) actions during the translation. |
|`k_do` | Total number of Enter actions during the translation. |
|`n_pause_geq_300` | Number of pauses of 300ms or more during the translation. |
|`len_pause_geq_300` | Total duration of pauses of 300ms or more, in milliseconds. |
|`n_pause_geq_1000` | Number of pauses of 1s or more during the translation. |
|`len_pause_geq_1000` | Total duration of pauses of 1000ms or more, in milliseconds. |
|`event_time` | Total time summed across all translation events, should be comparable to `edit_time` in most cases. |
|`num_annotations` | Number of times the translator focused the textbox for performing the translation of the sentence during the translation session. E.g. 1 means the translation was performed once and never revised. |
|`n_insert` | Number of post-editing insertions (empty for modality `ht`) computed using the [tercom](https://github.com/jhclark/tercom) library. |
|`n_delete` | Number of post-editing deletions (empty for modality `ht`) computed using the [tercom](https://github.com/jhclark/tercom) library. |
|`n_substitute` | Number of post-editing substitutions (empty for modality `ht`) computed using the [tercom](https://github.com/jhclark/tercom) library. |
|`n_shift` | Number of post-editing shifts (empty for modality `ht`) computed using the [tercom](https://github.com/jhclark/tercom) library. |
|`tot_shifted_words` | Total amount of shifted words from all shifts present in the sentence. |
|`tot_edits` | Total of all edit types for the sentence. |
|`hter` | Human-mediated Translation Edit Rate score computed between MT and post-edited TGT (empty for modality `ht`) using the [tercom](https://github.com/jhclark/tercom) library. |
|`cer` | Character-level HTER score computed between MT and post-edited TGT (empty for modality `ht`) using [CharacTER](https://github.com/rwth-i6/CharacTER).
|`bleu` | Sentence-level BLEU score between MT and post-edited TGT (empty for modality `ht`) computed using the [SacreBLEU](https://github.com/mjpost/sacrebleu) library with default parameters. |
|`chrf` | Sentence-level chrF score between MT and post-edited TGT (empty for modality `ht`) computed using the [SacreBLEU](https://github.com/mjpost/sacrebleu) library with default parameters. |
|`time_s` | Edit time expressed in seconds. |
|`time_m` | Edit time expressed in minutes. |
|`time_h` | Edit time expressed in hours. |
|`time_per_char` | Edit time per source character, expressed in seconds. |
|`time_per_word` | Edit time per source word, expressed in seconds. |
|`key_per_char` | Proportion of keys per character needed to perform the translation. |
|`words_per_hour` | Amount of source words translated or post-edited per hour. |
|`words_per_minute` | Amount of source words translated or post-edited per minute. |
|`per_subject_visit_order` | Id denoting the order in which the translator accessed documents. 1 correspond to the first accessed document. |
|`src_text` | The original source sentence extracted from Wikinews, wikibooks or wikivoyage. |
|`mt_text` | Missing if tasktype is `ht`. Otherwise, contains the automatically-translated sentence before post-editing. |
|`tgt_text` | Final sentence produced by the translator (either via translation from scratch of `sl_text` or post-editing `mt_text`) |
|`aligned_edit` | Aligned visual representation of REF (`mt_text`), HYP (`tl_text`) and edit operations (I = Insertion, D = Deletion, S = Substitution) performed on the field. Replace `\\n` with `\n` to show the three aligned rows.|
|`src_tokens` | List of tokens obtained tokenizing `src_text` with Stanza using default params. |
|`src_annotations` | List of lists (one per `src_tokens` token) containing dictionaries (one per word, >1 for mwt) with pos, ner and other info parsed by Stanza |
|`mt_tokens` | List of tokens obtained tokenizing `mt_text` with Stanza using default params. |
|`mt_annotations` | List of lists (one per `mt_tokens` token) containing dictionaries (one per word, >1 for mwt) with pos, ner and other info parsed by Stanza |
|`tgt_tokens` | List of tokens obtained tokenizing `tgt_text` with Stanza using default params. |
|`tgt_annotations` | List of lists (one per `tgt_tokens` token) containing dictionaries (one per word, >1 for mwt) with pos, ner and other info parsed by Stanza |
### Data Splits
| config | train|
|-------:|-----:|
|`main` | 7740 (107 docs i.e. 430 sents x 18 translators) |
|`warmup`| 360 (5 docs i.e. 20 sents x 18 translators) |
#### Train Split
The `train` split contains the totality of triplets (or pairs, when translation from scratch is performed) annotated with behavioral data produced during the translation.
The following is an example of the subject `t1` post-editing a machine translation produced by Google Translate (task_type `pe1`) taken from the `train` split for Turkish. The field `aligned_edit` is showed over three lines to provide a visual understanding of its contents.
```json
{
'unit_id': 'flores101-main-tur-46-pe1-3',
'flores_id': 871,
'item_id': 'flores101-main-463',
'subject_id': 'tur_t1',
'task_type': 'pe1',
'translation_type': 'pe',
'src_len_chr': 109,
'mt_len_chr': 129.0,
'tgt_len_chr': 120,
'src_len_wrd': 17,
'mt_len_wrd': 15.0,
'tgt_len_wrd': 13,
'edit_time': 11.762999534606934,
'k_total': 31,
'k_letter': 9,
'k_digit': 0,
'k_white': 0,
'k_symbol': 0,
'k_nav': 20,
'k_erase': 2,
'k_copy': 0,
'k_cut': 0,
'k_paste': 0,
'k_do': 0,
'n_pause_geq_300': 2,
'len_pause_geq_300': 4986,
'n_pause_geq_1000': 1,
'len_pause_geq_1000': 4490,
'event_time': 11763,
'num_annotations': 2,
'last_modification_time': 1643569484,
'n_insert': 0.0,
'n_delete': 2.0,
'n_substitute': 1.0,
'n_shift': 0.0,
'tot_shifted_words': 0.0,
'tot_edits': 3.0,
'hter': 20.0,
'cer': 0.10,
'bleu': 0.0,
'chrf': 2.569999933242798,
'lang_id': 'tur',
'doc_id': 46,
'time_s': 11.762999534606934,
'time_m': 0.1960500031709671,
'time_h': 0.0032675000838935375,
'time_per_char': 0.1079174280166626,
'time_per_word': 0.6919412016868591,
'key_per_char': 0.2844036817550659,
'words_per_hour': 5202.75439453125,
'words_per_minute': 86.71257019042969,
'per_subject_visit_order': 201,
'src_text': 'As one example, American citizens in the Middle East might face different situations from Europeans or Arabs.',
'mt_text': "Bir örnek olarak, Orta Doğu'daki Amerikan vatandaşları, Avrupalılardan veya Araplardan farklı durumlarla karşı karşıya kalabilir.",
'tgt_text': "Örneğin, Orta Doğu'daki Amerikan vatandaşları, Avrupalılardan veya Araplardan farklı durumlarla karşı karşıya kalabilir.",
'aligned_edit': "REF: bir örnek olarak, orta doğu'daki amerikan vatandaşları, avrupalılardan veya araplardan farklı durumlarla karşı karşıya kalabilir.\\n
HYP: *** ***** örneğin, orta doğu'daki amerikan vatandaşları, avrupalılardan veya araplardan farklı durumlarla karşı karşıya kalabilir.\\n
EVAL: D D S"
}
```
The text is provided as-is, without further preprocessing or tokenization.
### Dataset Creation
The dataset was parsed from PET XML files into CSV format using the scripts available in the [DivEMT Github repository](https://github.com/gsarti/divemt).
Those are adapted from the ones by [Antonio Toral](https://research.rug.nl/en/persons/antonio-toral-ruiz) found at the following link: [https://github.com/antot/postediting_novel_frontiers](https://github.com/antot/postediting_novel_frontiers).
## Additional Information
### Dataset Curators
For problems related to this 🤗 Datasets version, please contact me at [g.sarti@rug.nl](mailto:g.sarti@rug.nl).
### Citation Information
```bibtex
@inproceedings{sarti-etal-2022-divemt,
title = "{D}iv{EMT}: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages",
author = "Sarti, Gabriele and
Bisazza, Arianna and
Guerberof-Arenas, Ana and
Toral, Antonio",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.532",
pages = "7795--7816",
}
``` |
false |
# Dataset Card for CodeQueries
## 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)
- [How to use](#how-to-use)
- [Data Splits and Data Fields](#data-splits-and-data-fields)
- [Dataset Creation](#dataset-creation)
- [Additional Information](#additional-information)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** [Data](https://huggingface.co/datasets/thepurpleowl/codequeries)
- **Repository:** [Code](https://github.com/thepurpleowl/codequeries-benchmark)
- **Paper:**
### Dataset Summary
CodeQueries is a dataset to evaluate the ability of neural networks to answer semantic queries over code. Given a query and code, a model is expected to identify answer and supporting-fact spans in the code for the query. This is extractive question-answering over code, for questions with a large scope (entire files) and complexity including both single- and multi-hop reasoning.
### Supported Tasks and Leaderboards
Extractive question answering for code, semantic understanding of code.
### Languages
The dataset contains code context from `python` files.
## Dataset Structure
### How to Use
The dataset can be directly used with the huggingface datasets package. You can load and iterate through the dataset for the proposed five settings with the following two lines of code:
```python
import datasets
# in addition to `twostep`, the other supported settings are <ideal/file_ideal/prefix>.
ds = datasets.load_dataset("thepurpleowl/codequeries", "twostep", split=datasets.Split.TEST)
print(next(iter(ds)))
#OUTPUT:
{'query_name': 'Unused import',
'code_file_path': 'rcbops/glance-buildpackage/glance/tests/unit/test_db.py',
'context_block': {'content': '# vim: tabstop=4 shiftwidth=4 softtabstop=4\n\n# Copyright 2010-2011 OpenStack, LLC\ ...',
'metadata': 'root',
'header': "['module', '___EOS___']",
'index': 0},
'answer_spans': [{'span': 'from glance.common import context',
'start_line': 19,
'start_column': 0,
'end_line': 19,
'end_column': 33}
],
'supporting_fact_spans': [],
'example_type': 1,
'single_hop': False,
'subtokenized_input_sequence': ['[CLS]_', 'Un', 'used_', 'import_', '[SEP]_', 'module_', '\\u\\u\\uEOS\\u\\u\\u_', '#', ' ', 'vim', ':', ...],
'label_sequence': [4, 4, 4, 4, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, ...],
'relevance_label': 1
}
```
### Data Splits and Data Fields
Detailed information on the data splits for proposed settings can be found in the paper.
In general, data splits in all the proposed settings have examples with the following fields -
```
- query_name (query name to uniquely identify the query)
- code_file_path (relative source file path w.r.t. ETH Py150 corpus)
- context_blocks (code blocks as context with metadata) [`prefix` setting doesn't have this field and `twostep` has `context_block`]
- answer_spans (answer spans with metadata)
- supporting_fact_spans (supporting-fact spans with metadata)
- example_type (1(positive)) or 0(negative)) example type)
- single_hop (True or False - for query type)
- subtokenized_input_sequence (example subtokens) [`prefix` setting has the corresponding token ids]
- label_sequence (example subtoken labels)
- relevance_label (0 (not relevant) or 1 (relevant) - relevance label of a block) [only `twostep` setting has this field]
```
## Dataset Creation
The dataset is created using [ETH Py150 Open dataset](https://github.com/google-research-datasets/eth_py150_open) as source for code contexts. To get semantic queries and corresponding answer/supporting-fact spans in ETH Py150 Open corpus files, CodeQL was used.
## Additional Information
### Licensing Information
The source code repositories used for preparing CodeQueries are based on the [ETH Py150 Open dataset](https://github.com/google-research-datasets/eth_py150_open) and are redistributable under the respective licenses. A Huggingface dataset for ETH Py150 Open is available [here](https://huggingface.co/datasets/eth_py150_open). The labeling prepared and provided by us as part of CodeQueries is released under the Apache-2.0 license.
|
false | # Story generation
## Dataset Description
- **Homepage:** https://laion.ai/
### Dataset Summary
This dataset contains summaries and stories from [RUCAIBox/Story-Generation](https://huggingface.co/datasets/RUCAIBox/Story-Generation) dataset.
## Dataset Structure
### Data Fields
- `summary`: The summary of the story
- `story`: The story |
false |
# Dataset Card for Dataset Name
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).
This dataset is a clean version (all NanN removed) of this dataset : https://www.kaggle.com/datasets/devicharith/language-translation-englishfrench . I'm not the person who posted it first on Kaggle.
### 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
[More Information Needed] |
false |
# MediaSum dataset for summarization
Summarization dataset copied from [MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization](https://github.com/zcgzcgzcg1/MediaSum)
This dataset is compatible with the [`run_summarization.py`](https://github.com/huggingface/transformers/tree/master/examples/pytorch/summarization) script from Transformers if you add this line to the `summarization_name_mapping` variable:
```python
"ccdv/mediasum": ("document", "summary")
```
# Configs
4 possibles configs:
- `roberta` will concatenate documents with "\</s\>"
- `newline` will concatenate documents with "\n"
- `bert` will concatenate documents with "[SEP]"
- `list` will return the list of documents instead of a single string
Add `_prepended` to config name to prepend the speaker name before each dialogue: `speaker: text` \
Default is `roberta_prepended` (compatible with BART).
### Data Fields
- `id`: paper id
- `document`: a string/list containing the body of a set of documents
- `summary`: a string containing the abstract of the set
### Data Splits
This dataset has 3 splits: _train_, _validation_, and _test_. \
| Dataset Split | Number of Instances |
| ------------- | --------------------|
| Train | 443596 |
| Validation | 10000 |
| Test | 10000 |
# Cite original article
```
@article{zhu2021mediasum,
title={MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization},
author={Zhu, Chenguang and Liu, Yang and Mei, Jie and Zeng, Michael},
journal={arXiv preprint arXiv:2103.06410},
year={2021}
}
``` |
false |
# Dataset Card for BEIR Benchmark
## 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/UKPLab/beir
- **Repository:** https://github.com/UKPLab/beir
- **Paper:** https://openreview.net/forum?id=wCu6T5xFjeJ
- **Leaderboard:** https://docs.google.com/spreadsheets/d/1L8aACyPaXrL8iEelJLGqlMqXKPX2oSP_R10pZoy77Ns
- **Point of Contact:** nandan.thakur@uwaterloo.ca
### Dataset Summary
BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:
- Fact-checking: [FEVER](http://fever.ai), [Climate-FEVER](http://climatefever.ai), [SciFact](https://github.com/allenai/scifact)
- Question-Answering: [NQ](https://ai.google.com/research/NaturalQuestions), [HotpotQA](https://hotpotqa.github.io), [FiQA-2018](https://sites.google.com/view/fiqa/)
- Bio-Medical IR: [TREC-COVID](https://ir.nist.gov/covidSubmit/index.html), [BioASQ](http://bioasq.org), [NFCorpus](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)
- News Retrieval: [TREC-NEWS](https://trec.nist.gov/data/news2019.html), [Robust04](https://trec.nist.gov/data/robust/04.guidelines.html)
- Argument Retrieval: [Touche-2020](https://webis.de/events/touche-20/shared-task-1.html), [ArguAna](tp://argumentation.bplaced.net/arguana/data)
- Duplicate Question Retrieval: [Quora](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs), [CqaDupstack](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)
- Citation-Prediction: [SCIDOCS](https://allenai.org/data/scidocs)
- Tweet Retrieval: [Signal-1M](https://research.signal-ai.com/datasets/signal1m-tweetir.html)
- Entity Retrieval: [DBPedia](https://github.com/iai-group/DBpedia-Entity/)
All these datasets have been preprocessed and can be used for your experiments.
```python
```
### Supported Tasks and Leaderboards
The dataset supports a leaderboard that evaluates models against task-specific metrics such as F1 or EM, as well as their ability to retrieve supporting information from Wikipedia.
The current best performing models can be found [here](https://eval.ai/web/challenges/challenge-page/689/leaderboard/).
### Languages
All tasks are in English (`en`).
## Dataset Structure
All BEIR datasets must contain a corpus, queries and qrels (relevance judgments file). They must be in the following format:
- `corpus` file: a `.jsonl` file (jsonlines) that contains a list of dictionaries, each with three fields `_id` with unique document identifier, `title` with document title (optional) and `text` with document paragraph or passage. For example: `{"_id": "doc1", "title": "Albert Einstein", "text": "Albert Einstein was a German-born...."}`
- `queries` file: a `.jsonl` file (jsonlines) that contains a list of dictionaries, each with two fields `_id` with unique query identifier and `text` with query text. For example: `{"_id": "q1", "text": "Who developed the mass-energy equivalence formula?"}`
- `qrels` file: a `.tsv` file (tab-seperated) that contains three columns, i.e. the `query-id`, `corpus-id` and `score` in this order. Keep 1st row as header. For example: `q1 doc1 1`
### Data Instances
A high level example of any beir dataset:
```python
corpus = {
"doc1" : {
"title": "Albert Einstein",
"text": "Albert Einstein was a German-born theoretical physicist. who developed the theory of relativity, \
one of the two pillars of modern physics (alongside quantum mechanics). His work is also known for \
its influence on the philosophy of science. He is best known to the general public for his mass–energy \
equivalence formula E = mc2, which has been dubbed 'the world's most famous equation'. He received the 1921 \
Nobel Prize in Physics 'for his services to theoretical physics, and especially for his discovery of the law \
of the photoelectric effect', a pivotal step in the development of quantum theory."
},
"doc2" : {
"title": "", # Keep title an empty string if not present
"text": "Wheat beer is a top-fermented beer which is brewed with a large proportion of wheat relative to the amount of \
malted barley. The two main varieties are German Weißbier and Belgian witbier; other types include Lambic (made\
with wild yeast), Berliner Weisse (a cloudy, sour beer), and Gose (a sour, salty beer)."
},
}
queries = {
"q1" : "Who developed the mass-energy equivalence formula?",
"q2" : "Which beer is brewed with a large proportion of wheat?"
}
qrels = {
"q1" : {"doc1": 1},
"q2" : {"doc2": 1},
}
```
### Data Fields
Examples from all configurations have the following features:
### Corpus
- `corpus`: a `dict` feature representing the document title and passage text, made up of:
- `_id`: a `string` feature representing the unique document id
- `title`: a `string` feature, denoting the title of the document.
- `text`: a `string` feature, denoting the text of the document.
### Queries
- `queries`: a `dict` feature representing the query, made up of:
- `_id`: a `string` feature representing the unique query id
- `text`: a `string` feature, denoting the text of the query.
### Qrels
- `qrels`: a `dict` feature representing the query document relevance judgements, made up of:
- `_id`: a `string` feature representing the query id
- `_id`: a `string` feature, denoting the document id.
- `score`: a `int32` feature, denoting the relevance judgement between query and document.
### Data Splits
| Dataset | Website| BEIR-Name | Type | Queries | Corpus | Rel D/Q | Down-load | md5 |
| -------- | -----| ---------| --------- | ----------- | ---------| ---------| :----------: | :------:|
| MSMARCO | [Homepage](https://microsoft.github.io/msmarco/)| ``msmarco`` | ``train``<br>``dev``<br>``test``| 6,980 | 8.84M | 1.1 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/msmarco.zip) | ``444067daf65d982533ea17ebd59501e4`` |
| TREC-COVID | [Homepage](https://ir.nist.gov/covidSubmit/index.html)| ``trec-covid``| ``test``| 50| 171K| 493.5 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/trec-covid.zip) | ``ce62140cb23feb9becf6270d0d1fe6d1`` |
| NFCorpus | [Homepage](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/) | ``nfcorpus`` | ``train``<br>``dev``<br>``test``| 323 | 3.6K | 38.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nfcorpus.zip) | ``a89dba18a62ef92f7d323ec890a0d38d`` |
| BioASQ | [Homepage](http://bioasq.org) | ``bioasq``| ``train``<br>``test`` | 500 | 14.91M | 8.05 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#2-bioasq) |
| NQ | [Homepage](https://ai.google.com/research/NaturalQuestions) | ``nq``| ``train``<br>``test``| 3,452 | 2.68M | 1.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nq.zip) | ``d4d3d2e48787a744b6f6e691ff534307`` |
| HotpotQA | [Homepage](https://hotpotqa.github.io) | ``hotpotqa``| ``train``<br>``dev``<br>``test``| 7,405 | 5.23M | 2.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/hotpotqa.zip) | ``f412724f78b0d91183a0e86805e16114`` |
| FiQA-2018 | [Homepage](https://sites.google.com/view/fiqa/) | ``fiqa`` | ``train``<br>``dev``<br>``test``| 648 | 57K | 2.6 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fiqa.zip) | ``17918ed23cd04fb15047f73e6c3bd9d9`` |
| Signal-1M(RT) | [Homepage](https://research.signal-ai.com/datasets/signal1m-tweetir.html)| ``signal1m`` | ``test``| 97 | 2.86M | 19.6 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#4-signal-1m) |
| TREC-NEWS | [Homepage](https://trec.nist.gov/data/news2019.html) | ``trec-news`` | ``test``| 57 | 595K | 19.6 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#1-trec-news) |
| ArguAna | [Homepage](http://argumentation.bplaced.net/arguana/data) | ``arguana``| ``test`` | 1,406 | 8.67K | 1.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/arguana.zip) | ``8ad3e3c2a5867cdced806d6503f29b99`` |
| Touche-2020| [Homepage](https://webis.de/events/touche-20/shared-task-1.html) | ``webis-touche2020``| ``test``| 49 | 382K | 19.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/webis-touche2020.zip) | ``46f650ba5a527fc69e0a6521c5a23563`` |
| CQADupstack| [Homepage](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/) | ``cqadupstack``| ``test``| 13,145 | 457K | 1.4 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/cqadupstack.zip) | ``4e41456d7df8ee7760a7f866133bda78`` |
| Quora| [Homepage](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs) | ``quora``| ``dev``<br>``test``| 10,000 | 523K | 1.6 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/quora.zip) | ``18fb154900ba42a600f84b839c173167`` |
| DBPedia | [Homepage](https://github.com/iai-group/DBpedia-Entity/) | ``dbpedia-entity``| ``dev``<br>``test``| 400 | 4.63M | 38.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/dbpedia-entity.zip) | ``c2a39eb420a3164af735795df012ac2c`` |
| SCIDOCS| [Homepage](https://allenai.org/data/scidocs) | ``scidocs``| ``test``| 1,000 | 25K | 4.9 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scidocs.zip) | ``38121350fc3a4d2f48850f6aff52e4a9`` |
| FEVER | [Homepage](http://fever.ai) | ``fever``| ``train``<br>``dev``<br>``test``| 6,666 | 5.42M | 1.2| [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fever.zip) | ``5a818580227bfb4b35bb6fa46d9b6c03`` |
| Climate-FEVER| [Homepage](http://climatefever.ai) | ``climate-fever``|``test``| 1,535 | 5.42M | 3.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/climate-fever.zip) | ``8b66f0a9126c521bae2bde127b4dc99d`` |
| SciFact| [Homepage](https://github.com/allenai/scifact) | ``scifact``| ``train``<br>``test``| 300 | 5K | 1.1 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scifact.zip) | ``5f7d1de60b170fc8027bb7898e2efca1`` |
| Robust04 | [Homepage](https://trec.nist.gov/data/robust/04.guidelines.html) | ``robust04``| ``test``| 249 | 528K | 69.9 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#3-robust04) |
## 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
[Needs More Information]
### Citation Information
Cite as:
```
@inproceedings{
thakur2021beir,
title={{BEIR}: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models},
author={Nandan Thakur and Nils Reimers and Andreas R{\"u}ckl{\'e} and Abhishek Srivastava and Iryna Gurevych},
booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
year={2021},
url={https://openreview.net/forum?id=wCu6T5xFjeJ}
}
```
### Contributions
Thanks to [@Nthakur20](https://github.com/Nthakur20) for adding this dataset. |
false |
# Dataset Card for Letras Carnaval Cádiz
<h4 align="center">
<p>
<b>English</b> |
<a href="https://huggingface.co/datasets/IES-Rafael-Alberti/letras-carnaval-cadiz/blob/main/README_es.md">Español</a>
<p>
</h4>
## Dataset Description
- **Homepage:** https://letrascarnavalcadiz.com
- **Repository:** https://huggingface.co/datasets/IES-Rafael-Alberti/letras-carnaval-cadiz
- **Point of Contact:** contacto@letrascarnavalcadiz.com
### Changelog
|Release|Description|
|-|-|
|v1.0| Initial release of the dataset. Included more than 1K lyrics. It is necessary to verify the accuracy of the data, especially the subset midaccurate. |
### Dataset Summary
This dataset is a comprehensive collection of lyrics from the Carnaval de Cádiz, a significant cultural heritage of the city of Cádiz, Spain. Despite its cultural importance, there has been a lack of a structured database for these lyrics, hindering research and public access to this cultural heritage. This dataset aims to address this gap.
The dataset was created by the Cádiz AI Learning Community, a branch of the non-profit association Spain AI, and was developed by Iván Romero Reyna and Jesús Federico Franco Medinilla, students of the Specialization Course in Artificial Intelligence and Big Data at IES Rafael Alberti during the 2022-2023 academic year. The project is supervised by Jesús Carlos Avecilla de la Herrán, a computational linguist.
Collaboration is encouraged, with individuals able to verify the different records of the dataset at [letrascarnavalcadiz.com](https://letrascarnavalcadiz.com), ensuring the transcription of the lyrics and all data are correct. New lyrics can also be added to the dataset. Corrections and additions are not immediately reflected in the dataset but are updated periodically.
For more information or to report a problem, you can write to [contacto@letrascarnavalcadiz.com](mailto:contacto@letrascarnavalcadiz.com).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is in Spanish, reflecting the language of the Carnaval de Cádiz.
## Dataset Structure
### Data Instances
A typical instance in the dataset is formatted in JSON and contains the following fields:
```json
{
"id": "9de8647521b728c45ff45c1c11208708d055397fd7781b31cf91b473dff224d5",
"authors": ["Juan Carlos Aragón Becerra"],
"song_type": 2,
"year": "2018",
"group": "Los Mafiosos",
"group_type": 2,
"lyrics": [
"Mujer va llegando el momento",
"de ser la que lleve la rienda",
"el camino ha sido largo y polvoriento",
"pero ya no habrá varón que te detenga",
"gritad larga vida a la reina",
"que va a comenzar tu gobierno",
"ojalá no heredes nada",
"de aquel macho que te odiaba",
"porque en el fondo sabía",
"que ya tú te le acercabas",
"y el contigo no podía",
"ten en cuenta cuando hagas justicia",
"de volver a nivelar la balanza",
"y aguantar aunque tragando saliva",
"el deseo de venganza",
"de ser oh humano fatal",
"de ser o que puedo entender",
"tan solo con una mirada",
"la llaga que baña tu alma y tu piel",
"que te sirva la experiencia",
"del macho de la manada",
"la fuerza no vale nada",
"si no es con la inteligencia",
"y ojalá que tu conciencia",
"a mí me brinde la suerte",
"de nunca volver a verte",
"con los pies en una iglesia",
"que ella fue quien escribió",
"que ella fue quien escribió",
"la historia contra vosotras",
"y encima se la cobró",
"y encima se la cobró",
"con mil millones de devotas",
"ojalá que tu corona y tu bandera",
"abran paso a una vida nueva",
"como un mundo en primavera",
"ojalá que a ti no te envenene el poder",
"y que no dejes nunca de ser la mujer",
"que siempre fue nuestra gran compañera"
]
}
```
The `id` field uniquely identifies each instance in the dataset, providing a way to reference specific entries. The `authors`, `song_type`, `year`, `group`, and `group_type` fields provide context for the lyrics, while the `lyrics` field itself contains the actual text of the song. The relationships between these fields are implicit in the structure of the dataset, with each instance representing a single song from the Carnaval de Cádiz.
### Data Fields
`id`
Unique identifier for each song in the dataset. A SHA-256 hash calculated from the first four verses of the lyrics and the group name, with all spaces removed and converted to lowercase (string).
`authors`
List of authors who have written the song (string array).
`song_type`
The type of song (1: presentación, 2: pasodoble/tango, 3: cuplé, 4: estribillo, 5: popurrí, 6: cuarteta).
`year`
Year the song was written or performed (string).
`group`
Name of the group that performed the song (string).
`group_type`
The type of the group (1: coro, 2: comparsa, 3: chirigota, 4: cuarteto).
`lyrics`
The lyrics of the song, represented as an array of verses (string array).
### Data Splits
This dataset does not have traditional training, validation, and test splits. Instead, it is divided into two subsets: "accurate" and "midaccurate".
The "accurate" subset contains 958 instances. All fields of first 957 instances in this subset have been obtained through web scraping and have undergone at least one human review for accuracy. The rest have been added by users at [letrascarnavalcadiz.com](https://letrascarnavalcadiz.com).
The "midaccurate" subset contains 226 instances. The 'group' and 'lyrics' fields in this subset were collected through web scraping, but the remaining fields were filled in by querying language models connected to the Internet. Therefore, the data in these fields may not be accurate.
| Subset | Instances |
|-------------|----------:|
| Accurate | 958 |
| Midaccurate | 226 |
Please note that the division into subsets is based on the method and reliability of data collection, rather than a random or stratified split typically used in machine learning tasks. Users of the dataset should consider this when deciding how to use the data.
## Dataset Creation
### Curation Rationale
The dataset was created to address a significant need in the cultural heritage of the city of Cádiz, Spain. The Carnaval de Cádiz is a major cultural event, yet there was no structured database of its lyrics that could be consulted for research or public access. This lack of a structured database hindered the exploration and appreciation of this cultural heritage. The dataset was curated to respond to this need.
### Source Data
#### Initial Data Collection and Normalization
The initial collection of lyrics was carried out through automatic scraping of various websites and multimedia content on the Internet. To maximize the number of records with minimal effort, all collection is being done using different Artificial Intelligence models.
#### Who are the source language producers?
The source language producers of the dataset are the authors and performers of the songs from the Carnaval de Cádiz. These include a wide range of individuals and groups who have participated in the Carnaval over the years. The dataset does not include self-reported demographic or identity information for these individuals or groups.
The data in the dataset was collected from two websites: https://www.alsondelcarnaval.es and http://letrasdesdeelparaiso.blogspot.com. The first 957 instances of "accurate" subset of the dataset was collected from the former, while the "midaccurate" subset was collected from the latter. The data was extracted through automatic web scraping, and in the case of the "midaccurate" subset, some fields were filled in by querying language models connected to the Internet.
The rest of "accurate" subset have been added by users at [letrascarnavalcadiz.com](https://letrascarnavalcadiz.com).
### Personal and Sensitive Information
The only sensitive information in the dataset is the names and surnames of the authors of the lyrics.
## Considerations for Using the Data
### Social Impact of Dataset
The use of this dataset has significant social impact.
Firstly, this dataset can positively contribute to the understanding and preservation of Cadiz's culture and traditions, as the Carnaval de Cádiz is an integral part of the city's cultural identity. By providing an accessible and easily searchable resource for carnival song lyrics, this dataset can assist cultural researchers, linguists, and the general public in better understanding and appreciating the rich tradition of the Carnaval de Cádiz.
Additionally, this dataset can be utilized to enhance natural language processing (NLP) technologies in Spanish, a language that can sometimes be underrepresented in NLP research. By providing a high-quality, culture-specific Spanish text corpus, this dataset can aid in improving the accuracy and cultural relevance of Spanish NLP models.
However, there are also risks associated with the use of this dataset. For instance, if used to train text generation models, these models could generate content that reinforces cultural stereotypes or perpetuates existing biases. Moreover, the automatic interpretation of carnival song lyrics can be challenging due to cultural and linguistic subtleties, and errors in this interpretation could lead to misunderstandings or misrepresentations of Cadiz's culture.
Finally, although this dataset does not contain a low-resource or underrepresented language, it does focus on a specific cultural tradition from a specific region of Spain. Therefore, its use can impact the Cadiz community by helping to preserve and disseminate its unique culture and traditions.
### Discussion of Biases
The dataset is subject to several biases due to the nature of the data collection and the historical context of the Cadiz Carnival.
Firstly, there is a temporal bias in the dataset. More recent lyrics are overrepresented compared to older ones, as there is more information available on the internet about modern groups. This may lead to a skewed understanding of the evolution of the Carnival's themes over time.
Secondly, the dataset exhibits a popularity bias. Lyrics from more popular groups are overrepresented because individuals have chosen to write about them more frequently. This could potentially limit the diversity of styles and themes represented in the dataset.
Thirdly, there is a competition bias. Lyrics from groups that advanced further in the competition stages are overrepresented, resulting in more available lyrics from these groups. This might lead to an overemphasis on the styles and themes that tend to be more successful in the competition.
Lastly, the dataset reflects a gender bias. Given that there have historically been more male authors than female authors in the Cadiz Carnival, the majority of the dataset consists of lyrics written by men. This could potentially limit the representation of diverse perspectives and themes in the lyrics.
To mitigate these biases, we actively encourage the participation of the community. By verifying the different records of the dataset, reviewing the transcription of the lyrics and all the data for accuracy, and adding new lyrics, we hope to broaden the diversity and representation.
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
- Iván Romero Reyna. Student of the Specialisation Course in Artificial Intelligence and Big Data at [IES Rafael Alberti](https://iesrafaelalberti.es) during the academic year 2022-2023.
- Jesús Federico Franco Medinilla. Student of the Specialisation Course in Artificial Intelligence and Big Data at [IES Rafael Alberti](https://iesrafaelalberti.es) during the academic year 2022-2023.
- Jesús Carlos Avecilla de la Herrán. Promoter in [Cádiz AI](https://www.spain-ai.com).
### Licensing Information
[CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0)
### Citation Information
```
@misc{letrascarnavalcadiz2023,
author = {Romero Reyna, Iván and Franco Medinilla, Jesús Federico and Avecilla de la Herrán, Jesús Carlos},
title = {letras-carnaval-cadiz},
year = {2023},
url = {https://huggingface.co/datasets/IES-Rafael-Alberti/letras-carnaval-cadiz}
}
```
### Contributions
Thanks to [@ivanro](https://huggingface.co/ivanro), [@jframed281](https://huggingface.co/jframed281) for adding this dataset.
Thanks to all the reviewers and contributors at [letrascarnavalcadiz.com](https://letrascarnavalcadiz.com). |
false |
# Dataset Card for "moss-002-sft-data"
## Dataset Description
- **Homepage:** [https://txsun1997.github.io/blogs/moss.html](https://txsun1997.github.io/blogs/moss.html)
- **Repository:** [https://github.com/OpenLMLab/MOSS](https://github.com/OpenLMLab/MOSS)
- **Total amount of disk used:** 2.16 GB
### Dataset Summary
An open-source conversational dataset that was used to train MOSS-002. The user prompts are extended based on a small set of human-written seed prompts in a way similar to [Self-Instruct](https://arxiv.org/abs/2212.10560). The AI responses are generated using `text-davinci-003`. The user prompts of `en_harmlessness` are from [Anthropic red teaming data](https://github.com/anthropics/hh-rlhf/tree/master/red-team-attempts).
### Data Splits
| name | \# samples |
|----------------------|-----------:|
| en_helpfulness.json | 419049 |
| en_honesty.json | 112580 |
| en_harmlessness.json | 38873 |
| zh_helpfulness.json | 447750 |
| zh_honesty.json | 142885 |
|
true | # Dataset Card for [Dataset Name]
## 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:** [The official homepage of Språkbanken](https://spraakbanken.gu.se/resurser/superlim/)
- **Repository:**
- **Paper:**[SwedishGLUE – Towards a Swedish Test Set for Evaluating Natural Language Understanding Models](https://gup.ub.gu.se/publication/299130?lang=sv)
- **Leaderboard:** [To be implemented]
- **Point of Contact:**[sb-info@svenska.gu.se](sb-info@svenska.gu.se)
### Dataset Summary
SuperLim 2.0 is a continuation of SuperLim 1.0, which aims for a standardized suite for evaluation and analysis of Swedish natural language understanding systems. The projects is inspired by the GLUE/SuperGLUE projects from which the name is derived: "lim" is the Swedish translation of "glue".
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Swedish
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
Most datasets have a train, dev and test split. However, there are a few (`supersim`, `sweanalogy` and `swesat-synonyms`) who only have a train and test split. The diagnostic tasks `swediagnostics` and `swewinogender` only have a test split, but they could be evaluated on models trained on `swenli` since they are also NLI-based.
## 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
To cite as a whole, use the standard reference. If you use or reference individual resources, cite the references specific for these resources:
Standard reference:
Yvonne Adesam, Aleksandrs Berdicevskis, Felix Morger (2020): [SwedishGLUE – Towards a Swedish Test Set for Evaluating Natural Language Understanding Models] (https://gup.ub.gu.se/publication/299130?lang=sv)
Dataset references:
[More information needed]
Thanks to [Felix Morger](https://github.com/felixhultin) for adding this dataset. |
false |
# Dataset Card for youtube_subs_howto100M
## 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:** [HowTo100M homepage](https://www.di.ens.fr/willow/research/howto100m/)
- **Repository:** [HowTo100M repository](https://github.com/antoine77340/howto100m)
- **Paper:** [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://arxiv.org/abs/1906.03327)
### Dataset Summary
The `youtube_subs_howto100M` dataset is an English-language dataset of instruction-response pairs extracted from 309136 YouTube videos. The dataset was orignally inspired by and sourced from the HowTo100M dataset, which was developed for natural language search for video clips.
### Supported Tasks and Leaderboards
- `conversational`: The dataset can be used to train a model for instruction(request) and a long form of response generation. This dataset is originally prepared for the [Open Assistant](https://github.com/LAION-AI/Open-Assistant), which is an open-source chat-based large language model.
### Languages
Currently, all text in the dataset is in English.
## Dataset Structure
### Data Instances
A typical data point comprises an `instruction`, `response`, and a `source`
An example from the youtube_subs_howto100M looks as follows:
```
{"instruction": "Please explain how to remove plaque without going to the dentist 2016", "response": "mineral deposit on teeth is known as tartar or plaque as time passes by the amount of tartar increases and if you don't take care it can cause periodontitis of course the best way to remove tartar is paying a visit to your dentist but another way is to remove plaque at your home in this video you will learn how to remove plaque at home to do so you will need baking soda toothbrush salt you hydrogen peroxide cup you gentle pick you water anti septic mouthwash you step one first mix one tablespoon of bacon soda with TSP of salt into the cup after you at the toothbrush with warm water dip it into the mixture scrub teeth with an in spit continue the same process for five minutes step to mix a cup full with hydrogen peroxide with cup of warm water and rinse your mouth for one minute then spit and rinse with cup of cool water step 3 rub the yellow tartar from teeth with a dental pick be careful not to scrape the gums it may irritate and damage them step 4 rinse mouth with an antiseptic mouthwash and repeat every second day here are some other advice is to help you keep your beautiful smile tomatoes and strawberries tomatoes and strawberries are rich in vitamin C which is excellent for oral health you can rub these fruits directly onto your teeth and let it sit for five minutes this way the tartar buildup will soften cheese being a Swiss or cheddar before meals helps neutralize the acids that involve black creation an ingredient in a cheese works as a barrier agent guava both guava fruit and leaves are considered excellent anti black agents to help remove plaque accumulated on the teeth and gums gloss they have anti-inflammatory and analgesic properties that help reduce swelling and pain in the gums brush your teeth regularly with a soft brush and make vertical movements pay attention on the space between gums and teeth floss regularly consuming spicy food stimulates syllabary glands that way saliva cleans mouth in a natural way five bacteria with an orange peel before going to bed and don't rinse mouth", "source": "YouTube"}
```
### Data Fields
- `instruction`: a request for an explanation.
- `response`: a long text of response sentences, currently not punctuated.
- `source`: the source of the datapoint, currently all `YouTube`.
### Data Splits
The dataset does not have train/valid/eval splits now.
## Dataset Creation
### Curation Rationale
The original HowTo100M dataset was developed for natural language search for video clips, not necessarily for conversational or chat based training. However, the long monologue response can be regarded as a sequence of answers for a question, which can be induced from the video title. Therefore, a good amount of high-quality request-response(long) pairs can be extracted from HowTo100M youtube videos.
Concretely, this dataset is curated like below:
```
for each video in YouTube100M dataset
if video_title starts with `how to`
add `Please explain` to the title to make an `instruction`
extract subtitles from the video to make a `response`
```
### Source Data
#### Initial Data Collection and Normalization
Refer to the [Curation Rationale](#curation-rationale)
#### Who are the source language producers?
The language producers are YouTube users of the videos in HowTo100M dataset.
### Annotations
#### Annotation process
Refer to the [Curation Rationale](#curation-rationale)
#### Who are the annotators?
[N/A]
### Personal and Sensitive Information
[N/A]
## Considerations for Using the Data
### Social Impact of Dataset
[N/A]
### Discussion of Biases
[N/A]
### Other Known Limitations
Apache license 2.0
## Additional Information
### Dataset Curators
The youtube_subs_howto100M dataset was created by [@totuta](https://github.com/totuta). The original HowTo100M dataset was created by Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac, Makarand Tapaswi, Ivan Laptev, and Josef Sivic.
### Licensing Information
[N/A]
### Citation Information
@inproceedings{miech19howto100m,
title={How{T}o100{M}: {L}earning a {T}ext-{V}ideo {E}mbedding by {W}atching {H}undred {M}illion {N}arrated {V}ideo {C}lips},
author={Miech, Antoine and Zhukov, Dimitri and Alayrac, Jean-Baptiste and Tapaswi, Makarand and Laptev, Ivan and Sivic, Josef},
booktitle={ICCV},
year={2019},
}
### Contributions
Thanks to [@totuta](https://github.com/totuta) for adding this dataset. |
false | # Dataset Card for "instructional_code-search-net-python"
## Dataset Description
- **Homepage:** None
- **Repository:** https://huggingface.co/datasets/Nan-Do/instructional_code-search-net-python
- **Paper:** None
- **Leaderboard:** None
- **Point of Contact:** [@Nan-Do](https://github.com/Nan-Do)
### Dataset Summary
This is an instructional dataset for Python.
The dataset contains two different kind of tasks:
- Given a piece of code generate a description of what it does.
- Given a description generate a piece of code that fulfils the description.
### Languages
The dataset is in English.
### Data Splits
There are no splits.
## Dataset Creation
May of 2023
### Curation Rationale
This dataset was created to improve the coding capabilities of LLMs.
### Source Data
The summarized version of the code-search-net dataset can be found at https://huggingface.co/datasets/Nan-Do/code-search-net-python
### Annotations
The dataset includes an instruction and response columns.
#### Annotation process
The annotation procedure was done using templates and NLP techniques to generate human-like instructions and responses.
A sample notebook of the process can be found at https://github.com/Nan-Do/OpenAssistantInstructionResponsePython
The annontations have been cleaned to make sure there are no repetitions and/or meaningless summaries.
### Licensing Information
Apache 2.0 |
false | # Wikipedia Turkish Summarization Dataset
## Dataset Description
This is a Turkish summarization dataset 🇹🇷 prepared from the 2023 Wikipedia dump. The dataset has been cleaned, tokenized, and summarized using Huggingface Wikipedia dataset cleaner script, custom cleaning scripts, and OpenAI's gpt3.5-turbo API.
### Data Source
- Wikipedia's latest Turkish dump (2023 version) 🌐
### Features
- text: string (The original text extracted from Wikipedia articles 📖)
- summary: string (The generated summary of the original text 📝)
### Data Splits
| Split | Num Bytes | Num Examples |
|------------|--------------------|--------------|
| train | 324,460,408.048 | 119,110 |
| validation | 17,077,006.952 | 6,269 |
### Download Size
- 216,029,002 bytes
### Dataset Size
- 341,537,415 bytes
## Data Preparation
### Data Collection
1. The latest Turkish Wikipedia dump was downloaded 📥.
2. Huggingface Wikipedia dataset cleaner script was used to clean the text 🧹.
3. A custom script was used to further clean the text, removing sections like "Kaynakca" (References) and other irrelevant information 🛠️.
### Tokenization
The dataset was tokenized using Google's MT5 tokenizer. The following criteria were applied:
- Articles with a token count between 300 and 900 were selected ✔️.
- Articles with less than 300 tokens were ignored ❌.
- For articles with more than 900 tokens, only the first 900 tokens ending with a paragraph were selected 🔍.
### Summarization
The generated raw texts were summarized using OpenAI's gpt3.5-turbo API 🤖.
## Dataset Usage
This dataset can be used for various natural language processing tasks 👩💻, such as text summarization, machine translation, and language modeling in the Turkish language.
Example usage:
```python
from datasets import load_dataset
# Load the dataset
dataset = load_dataset("musabg/wikipedia-tr-summarization")
# Access the data
train_data = dataset["train"]
validation_data = dataset["validation"]
# Iterate through the data
for example in train_data:
text = example["text"]
summary = example["summary"]
# Process the data as needed
```
Please make sure to cite the dataset as follows 📝:
```bibtex
@misc{musabg2023wikipediatrsummarization,
author = {Musab Gultekin},
title = {Wikipedia Turkish Summarization Dataset},
year = {2023},
publisher = {HuggingFace},
howpublished = {\url{https://huggingface.co/datasets/musabg/wikipedia-tr-summarization}},
}
```
---
## Wikipedia Türkçe Özetleme Veri Seti
Bu, 2023 Wikipedia dökümünden hazırlanan Türkçe özetleme veri kümesidir. Veri kümesi, Huggingface Wikipedia veri kümesi temizleme betiği, özel temizleme betikleri ve OpenAI'nin gpt3.5-turbo API'si kullanılarak temizlenmiş, tokenleştirilmiş ve özetlenmiştir.
### Veri Kaynağı
- Wikipedia'nın en güncel Türkçe dökümü (2023 sürümü)
### Özellikler
- text: string (Wikipedia makalelerinden çıkarılan orijinal metin)
- summary: string (Orijinal metnin oluşturulan özeti)
### Veri Bölümleri
| Bölüm | Numara Baytı | Örnek Sayısı |
|------------|--------------------|--------------|
| train | 324.460.408,048 | 119.110 |
| validation | 17.077.006,952 | 6.269 |
### İndirme Boyutu
- 216.029.002 bayt
### Veri Kümesi Boyutu
- 341.537.415 bayt
## Veri Hazırlama
### Veri Toplama
1. En güncel Türkçe Wikipedia dökümü indirildi.
2. Huggingface Wikipedia veri kümesi temizleme betiği metni temizlemek için kullanıldı.
3. "Kaynakça" (Referanslar) gibi bölümleri ve diğer alakasız bilgileri kaldırmak için özel bir betik kullanıldı.
### Tokenleştirme
Veri kümesi, Google'ın MT5 tokenleştiricisi kullanılarak tokenleştirildi. Aşağıdaki kriterler uygulandı:
- 300 ile 900 token arasında olan makaleler seçildi.
- 300'den az tokeni olan makaleler dikkate alınmadı.
- 900'den fazla tokeni olan makalelerde, sadece bir paragraf ile biten ilk 900 token kısmı alındı.
### Özetleme
Oluşturulan ham metinler, OpenAI'nin gpt3.5-turbo API'si kullanılarak özetlendi.
## Veri Kümesi Kullanımı
Bu veri kümesi, Türkçe dilinde metin özetleme, makine çevirisi ve dil modelleme gibi çeşitli doğal dil işleme görevleri için kullanılabilir.
Örnek kullanım:
```python
from datasets import load_dataset
# Veri kümesini yükle
dataset = load_dataset("musabg/wikipedia-tr-summarization")
# Verilere erişin
train_data = dataset["train"]
validation_data = dataset["validation"]
# Verilerin üzerinden geçin
for example in train_data:
text = example["text"]
summary = example["summary"]
# Veriyi gerektiği gibi işleyin
``` |
false |
# Dataset Card for FaQuAD-NLI
## Dataset Description
- **Homepage:** https://github.com/liafacom/faquad
- **Repository:** https://github.com/liafacom/faquad
- **Paper:** https://ieeexplore.ieee.org/document/8923668/
<!-- - **Leaderboard:** -->
- **Point of Contact:** Eraldo R. Fernandes <eraldoluis@gmail.com>
### Dataset Summary
FaQuAD is a Portuguese reading comprehension dataset that follows the format of the Stanford Question Answering Dataset (SQuAD). It is a pioneer Portuguese reading comprehension dataset using the challenging format of SQuAD. The dataset aims to address the problem of abundant questions sent by academics whose answers are found in available institutional documents in the Brazilian higher education system. It consists of 900 questions about 249 reading passages taken from 18 official documents of a computer science college from a Brazilian federal university and 21 Wikipedia articles related to the Brazilian higher education system.
FaQuAD-NLI is a modified version of the [FaQuAD dataset](https://huggingface.co/datasets/eraldoluis/faquad) that repurposes the question answering task as a textual entailment task between a question and its possible answers.
### Supported Tasks and Leaderboards
- `question_answering`: The dataset can be used to train a model for question-answering tasks in the domain of Brazilian higher education institutions.
- `textual_entailment`: FaQuAD-NLI can be used to train a model for textual entailment tasks, where answers in Q&A pairs are classified as either suitable or unsuitable.
### Languages
This dataset is in Brazilian Portuguese.
## Dataset Structure
### Data Fields
- `document_index`: an integer representing the index of the document.
- `document_title`: a string containing the title of the document.
- `paragraph_index`: an integer representing the index of the paragraph within the document.
- `question`: a string containing the question related to the paragraph.
- `answer`: a string containing the answer related to the question.
- `label`: an integer (0 or 1) representing if the answer is suitable (1) or unsuitable (0) for the question.
### Data Splits
The dataset is split into three subsets: train, validation, and test.
The splits were made carefully to avoid question and answer pairs belonging to the same document appearing in more than one split.
| | Train | Validation | Test |
|------------|-------|------------|------|
| Instances | 3128 | 731 | 650 |
### Contributions
Thanks to [@ruanchaves](https://github.com/ruanchaves) for adding this dataset. |
true |
# ニコニコ実況 過去ログアーカイブ
ニコニコ実況 過去ログアーカイブは、[ニコニコ実況](https://jk.nicovideo.jp)のサービス開始から現在までのすべての過去ログコメントを収集したデータセットです。
去る2020年12月、ニコニコ実況は[ニコニコ生放送内の一公式チャンネルとしてリニューアル](https://blog.nicovideo.jp/niconews/143148.html)されました。
これに伴い、2009年11月から運用されてきた旧システムは提供終了となり（事実上のサービス終了）、torne や BRAVIA などの家電への対応が軒並み終了する中、当時の生の声が詰まった約11年分の過去ログも同時に失われることとなってしまいました。
そこで 5ch の DTV 板の住民が中心となり、旧ニコニコ実況が終了するまでに11年分の全チャンネルの過去ログをアーカイブする計画が立ち上がりました。紆余曲折あり Nekopanda 氏が約11年分のラジオや BS も含めた全チャンネルの過去ログを完璧に取得してくださったおかげで、11年分の過去ログが電子の海に消えていく事態は回避できました。
しかし、旧 API が廃止されてしまったため過去ログを API 経由で取得することができなくなり、またアーカイブされた過去ログから見たい範囲のログを探す場合も、アーカイブのサイズが合計約 150GB もあることから、とても以前のように手軽に過去ログに触れることはできなくなってしまいました。
一方、ニコニコ生放送内の一公式チャンネルとして移行した新ニコニコ実況では、タイムシフト（旧ニコニコ実況での過去ログに相当）の視聴期限は3週間までとなっているため、その期限を過ぎると過去ログは視聴できなくなってしまいます。
また一般会員は事前にタイムシフト予約をしておく必要があるなど、以前のような利便性は失われています。
私たちは、ニコニコ実況に投稿された日本のテレビ放送についてのコメントは、当時の世相や時代背景を端的に表す、歴史的価値のある資料だと考えています。
このデータセットでは、ニコニコ実況のすべての過去ログを後世に残すべく、Nekopanda 氏が配布されていた旧ニコニコ実況の 2020/12/15 までのすべての過去ログに加え、コミュニティベースの番組も含めた新ニコニコ実況の当日分の過去ログを5分に1回収集し、随時反映しています。
過去ログをかんたんに取得するための [API](https://jikkyo.tsukumijima.net/) もあります。
よろしければそちらもご活用ください。
## Dataset Structure
### Builder Config
| Key | Value Type | Default Value | Description |
| --------------- | ---------- | ------------- | ----------- |
| channel_id | string | None | 過去ログを取得するニコニコ実況チャンネルの ID (省略時はすべてのチャンネル) |
| year | int | None | 取得する過去ログの年 (省略時はすべての年) |
| number_of_files | int | None | 取得する過去ログファイルの数 (省略時はすべてのファイル) |
### Data Splits
| Split | Approximate Size | Description |
| ------- | ---------------- | ----------- |
| sample | 1GB | サンプルとして、2022年中に投稿された TOKYO MX (ID: jk9) のすべての過去ログコメントを取得します。1GB ほどあります。 |
| all | 180GB | 全チャンネル/全期間のすべての過去ログコメントを取得します。180GB 近くあるため注意してください。 |
### Data Fields
| Field | Type | Description |
| --------------- | -------- | ----------- |
| thread | string | コメントのスレッド ID |
| no | int64 | コメント番号 (コメ番) |
| vpos | int64 | スレッド ID から起算したコメントの再生位置 (1/100秒) |
| date | int64 | コメント投稿時間の UNIX タイムスタンプ |
| date_usec | int64 | コメント投稿時間の小数点以下の時間 |
| user_id | string | ユーザー ID (コマンドに 184 が指定されている場合は匿名化され、1週間ほどでシャッフルされる) |
| mail | string | コメントのコマンド (184, red naka big など、省略されることもある) |
| premium | boolean | コメントしたユーザーがプレミアム会員であれば True |
| anonymity | boolean | 匿名コメントであれば True |
| content | string | コメント本文 (AA など、まれに複数行コメントがあるので注意) |
## Example
```python
from datasets import load_dataset
dataset = load_dataset('KakologArchives/KakologArchives', 'all', channel_id='jk211', year=2023, number_of_files=10)
for data in dataset['train']:
print(data)
```
## Licensing Information
[MIT License](https://opensource.org/license/mit/)
|
true | SMS Spam Multilingual Collection Dataset
Collection of Multilingual SMS messages tagged as spam or legitimate
About Dataset
Context
The SMS Spam Collection is a set of SMS-tagged messages that have been collected for SMS Spam research. It originally contained one set of SMS messages in English of 5,574 messages, tagged according to being ham (legitimate) or spam and later Machine Translated into Hindi, German and French.
The text has been further translated into Spanish, Chinese, Arabic, Bengali, Russian, Portuguese, Indonesian, Urdu, Japanese, Punjabi, Javanese, Turkish, Korean, Marathi, Ukrainian, Swedish, and Norwegian using M2M100_418M a multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation created by Facebook AI.
Content
The augmented Dataset contains multilingual text and corresponding labels.
ham- non-spam text
spam- spam text
Acknowledgments
The original English text was taken from- https://www.kaggle.com/uciml/sms-spam-collection-dataset
Hindi, German and French taken from - https://www.kaggle.com/datasets/rajnathpatel/multilingual-spam-data |
false |
<div align="center">
<img width="640" alt="keremberke/pothole-segmentation" src="https://huggingface.co/datasets/keremberke/pothole-segmentation/resolve/main/thumbnail.jpg">
</div>
### Dataset Labels
```
['pothole']
```
### Number of Images
```json
{'test': 5, 'train': 80, 'valid': 5}
```
### How to Use
- Install [datasets](https://pypi.org/project/datasets/):
```bash
pip install datasets
```
- Load the dataset:
```python
from datasets import load_dataset
ds = load_dataset("keremberke/pothole-segmentation", name="full")
example = ds['train'][0]
```
### Roboflow Dataset Page
[https://universe.roboflow.com/imacs-pothole-detection-wo8mu/pothole-detection-irkz9/dataset/4](https://universe.roboflow.com/imacs-pothole-detection-wo8mu/pothole-detection-irkz9/dataset/4?ref=roboflow2huggingface)
### Citation
```
@misc{ pothole-detection-irkz9_dataset,
title = { Pothole Detection Dataset },
type = { Open Source Dataset },
author = { IMACS Pothole Detection },
howpublished = { \\url{ https://universe.roboflow.com/imacs-pothole-detection-wo8mu/pothole-detection-irkz9 } },
url = { https://universe.roboflow.com/imacs-pothole-detection-wo8mu/pothole-detection-irkz9 },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2023 },
month = { jan },
note = { visited on 2023-01-15 },
}
```
### License
CC BY 4.0
### Dataset Summary
This dataset was exported via roboflow.com on January 15, 2023 at 6:38 PM GMT
Roboflow is an end-to-end computer vision platform that helps you
* collaborate with your team on computer vision projects
* collect & organize images
* understand and search unstructured image data
* annotate, and create datasets
* export, train, and deploy computer vision models
* use active learning to improve your dataset over time
For state of the art Computer Vision training notebooks you can use with this dataset,
visit https://github.com/roboflow/notebooks
To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com
The dataset includes 90 images.
Pothole are annotated in COCO format.
The following pre-processing was applied to each image:
No image augmentation techniques were applied.
|
false | |
false | Датасет русских диалогов собранных с Telegram чатов.
Диалоги имеют разметку по релевантности.
Также были сгенерированы негативные примеры с помощью перемешивания похожих ответов.
Количество диалогов - 2 миллиона
Формат датасета:
```
{
'question': 'Привет',
'answer': 'Привет, как дела?'
'relevance': 1
}
```
Программа парсинга: https://github.com/Den4ikAI/telegram_chat_parser
### Citation:
```
@MISC{russian_instructions,
author = {Denis Petrov},
title = {Russian dialogues dataset for conversational agents},
url = {https://huggingface.co/datasets/Den4ikAI/russian_dialogues},
year = 2023
}
``` |
false |
# Dataset Card for NERDE
## 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
- **Repository:** [NERDE repository](https://github.com/guipaiva/NERDE)
- **Point of Contact:** [Guilherme P. Paiva](mailto:guipaivagpp@gmail.com)
### Dataset Summary
NERDE is a dataset for Named Entity Recognition for Economic Defense. It was created in collaboration with LATITUDE/UnB Laboratory and the Administrative Council for Economic Defense (Cade)
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The language in the dataset is Brazilian Portuguese from legal documents. The BCP-47 code for Brazilian Portuguese is pt-BR
## 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 [@guipaiva](https://github.com/guipaiva) for adding this dataset.
|
true | # Dataset Card for "spam-detection-dataset"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) |
false | # ~300K English ↔ Traditional Chinese Sentences from the COCT Database
The data in this dataset are collected from the Corpus of Contemporary Taiwanese Mandarin (COCT), mostly contributed by the [Taiwan Panorama](https://www.taiwan-panorama.com/) magazine. |
true |
# Battery Abstracts Dataset
This dataset includes 29,472 battery papers and 17,191 non-battery papers, a total of 46,663 papers. These papers are manually labelled in terms of the journals to which they belong. 14 battery journals and 1,044 non battery journals were selected to form this database.
- training_data.csv: Battery papers: 20,629, Non-battery papers: 12,034. Total: 32,663.
- val_data.csv: Battery papers: 5,895, Non-battery papers: 3,438. Total: 9,333.
- test_data.csv: Battery papers: 2,948, Non-battery papers: 1,719. Total: 4,667.
# Usage
```
from datasets import load_dataset
dataset = load_dataset("batterydata/paper-abstracts")
```
# Citation
```
@article{huang2022batterybert,
title={BatteryBERT: A Pretrained Language Model for Battery Database Enhancement},
author={Huang, Shu and Cole, Jacqueline M},
journal={J. Chem. Inf. Model.},
year={2022},
doi={10.1021/acs.jcim.2c00035},
url={DOI:10.1021/acs.jcim.2c00035},
pages={DOI: 10.1021/acs.jcim.2c00035},
publisher={ACS Publications}
}
``` |
false |
# Oxford-IIIT Pet Dataset
Images from [The Oxford-IIIT Pet Dataset](https://www.robots.ox.ac.uk/~vgg/data/pets/). Only images and labels have been pushed, segmentation annotations were ignored.
- **Homepage:** https://www.robots.ox.ac.uk/~vgg/data/pets/
License:
Same as the original dataset.
|
false | # Summarization dataset for Norwegian Court Decisions
This data was scraped from www.lovdata.no, April 2023, and contains about 27k samples.
## How to Use
```python
from datasets import load_dataset
data = load_dataset("MasterThesisCBS/Court_Decisions_Lovdata")
```
### Dataset Curators
[John Oskar Holmen Skjeldrum](mailto:josk18ad@student.cbs.dk) and [Peder Tanberg](mailto:peha28ae@student.cbs.dk) |
false |
# Dataset Card for Romanian Named Entity Recognition in the Legal domain (LegalNERo)
## 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:**
- **Repository:** https://zenodo.org/record/4922385
- **Paper:** Pais, V., Mitrofan, M., Gasan, C. L., Coneschi, V., & Ianov, A. (2021). Named Entity Recognition in the {R}omanian Legal Domain. Proceedings of the Natural Legal Language Processing Workshop 2021, 9–18. https://doi.org/10.18653/v1/2021.nllp-1.2
- **Leaderboard:**
- **Point of Contact:** [Joel Niklaus](mailto:joel.niklaus.2@bfh.ch)
### Dataset Summary
LegalNERo is a manually annotated corpus for named entity recognition in the Romanian legal domain. It provides gold annotations for organizations, locations, persons, time and legal resources mentioned in legal documents. Additionally it offers GEONAMES codes for the named entities annotated as location (where a link could be established).
### Supported Tasks and Leaderboards
The dataset supports the task of named entity recognition.
### Languages
Since legal documents for LegalNERo are extracted from the larger [MARCELL-RO corpus](https://elrc-share.eu/repository/browse/marcell-romanian-legislative-subcorpus-v2/2da548428b9d11eb9c1a00155d026706ce94a6b59ffc4b0e9fb5cd9cebe6889e/), the language in the dataset is Romanian as it used in national legislation ranging from 1881 to 2021.
## Dataset Structure
### Data Instances
The file format is jsonl and three data splits are present (train, validation and test). Named Entity annotations are non-overlapping.
Rows only containing one word (mostly words such as `\t\t\t`, `\n` or `-----`) have been filtered out.
### Data Fields
The files contain the following data fields
- `file_name`: The file_name of the applicable annotation document
- `words`: The list of tokens obtained by applying the spacy (v 3.3.1) Greek tokenizer on the sentences. For more information see `convert_to_hf_dataset.py`.
- `ner`: The list of ner tags. The list of labels for the named entities that are covered by the dataset are the following:
- `LEGAL`: Legal reference/resources
- `LOC`: Location
- `ORG`: Organization
- `PER`: Person
- `TIME`: Time reference
- `O`: No entity annotation present
The final tagset (in IOB notation) is the following: `['O', 'B-TIME', 'I-TIME', 'B-LEGAL', 'I-LEGAL', 'B-ORG', 'I-ORG', 'B-LOC', 'I-LOC', 'B-PER', 'I-PER']`
### Data Splits
Splits created by Joel Niklaus.
| split | number of documents | number of sentences |
|:---------------|--------------------:|--------------------:|
| train | 296 (80%) | 7552 |
| validation | 37 (10%) | 966 |
| test | 37 (10%) | 907 |
## Dataset Creation
### Curation Rationale
The dataset provides gold annotations for organizations, locations, persons, time and legal resources mentioned in Romanian legal documents.
### Source Data
#### Initial Data Collection and Normalization
The LegalNERo corpus consists of 370 documents from the larger [MARCELL-RO corpus](https://elrc-share.eu/repository/browse/marcell-romanian-legislative-subcorpus-v2/2da548428b9d11eb9c1a00155d026706ce94a6b59ffc4b0e9fb5cd9cebe6889e/). In the following we give a short description of the crawling process for the MARCELL-RO corpus.
*The MARCELL-RO corpus "contains 163,274 files, which represent the body of national legislation ranging from 1881 to 2021. This corpus includes mainly: governmental decisions, ministerial orders, decisions, decrees and laws. All the texts were obtained via crawling from the public Romanian legislative portal . We have not distinguished between in force and "out of force" laws because it is difficult to do this automatically and there is no external resource to use to distinguish between them. The texts were extracted from the original HTML format and converted into TXT files. Each file has multiple levels of annotation: firstly the texts were tokenized, lemmatized and morphologically annotated using the Tokenizing, Tagging and Lemmatizing (TTL) text processing platform developed at RACAI, then dependency parsed with NLP-Cube, named entities were identified using a NER tool developed at RACAI, nominal phrases were identified also with TTL, while IATE terms and EuroVoc descriptors were identified using an internal tool. All processing tools were integrated into an end-to-end pipeline available within the RELATE platform and as a dockerized version. The files were annotated with the latest version of the pipeline completed within Activity 4 of the MARCELL project."* [Link](https://elrc-share.eu/repository/browse/marcell-romanian-legislative-subcorpus-v2/2da548428b9d11eb9c1a00155d026706ce94a6b59ffc4b0e9fb5cd9cebe6889e/)
#### Who are the source language producers?
The source language producers are presumably politicians and lawyers.
### Annotations
#### Annotation process
*“Annotation of the LegalNERo corpus was performed by 5 human annotators, supervised by two senior researchers at the Institute for Artificial Intelligence "Mihai Drăgănescu" of the Romanian Academy (RACAI). For annotation purposes we used the BRAT tool4 […].
Inside the legal reference class, we considered sub-entities of type *organization* and *time*. This allows for using the LegalNERo corpus in two scenarios: using all the 5 entity classes or using only the remaining general-purpose classes. The LegalNERo corpus contains a total of 370 documents from the larger MARCELL-RO corpus. These documents were split amongst the 5 annotators, with certain documents being annotated by multiple annotators. Each annotator manually annotated 100 documents. The annotators were unaware of the overlap, which allowed us to compute an inter-annotator agreement. We used the Cohen’s Kappa measure and obtained a value of 0.89, which we consider to be a good result.”* (Pais et al., 2021)
#### Who are the annotators?
*"[...] 5 human annotators, supervised by two senior researchers at the Institute for Artificial Intelligence "Mihai Drăgănescu" of the Romanian Academy (RACAI)."*
### 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
Note that the information given in this dataset card refer to the dataset version as provided by Joel Niklaus and Veton Matoshi. The dataset at hand is intended to be part of a bigger benchmark dataset. Creating a benchmark dataset consisting of several other datasets from different sources requires postprocessing. Therefore, the structure of the dataset at hand, including the folder structure, may differ considerably from the original dataset. In addition to that, differences with regard to dataset statistics as give in the respective papers can be expected. The reader is advised to have a look at the conversion script ```convert_to_hf_dataset.py``` in order to retrace the steps for converting the original dataset into the present jsonl-format. For further information on the original dataset structure, we refer to the bibliographical references and the original Github repositories and/or web pages provided in this dataset card.
## Additional Information
### Dataset Curators
The names of the original dataset curators and creators can be found in references given below, in the section *Citation Information*.
Additional changes were made by Joel Niklaus ([Email](mailto:joel.niklaus.2@bfh.ch); [Github](https://github.com/joelniklaus)) and Veton Matoshi ([Email](mailto:veton.matoshi@bfh.ch); [Github](https://github.com/kapllan)).
### Licensing Information
[Creative Commons Attribution Non Commercial No Derivatives 4.0 International](https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode)
### Citation Information
```
@dataset{pais_vasile_2021_4922385,
author = {Păiș, Vasile and
Mitrofan, Maria and
Gasan, Carol Luca and
Ianov, Alexandru and
Ghiță, Corvin and
Coneschi, Vlad Silviu and
Onuț, Andrei},
title = {{Romanian Named Entity Recognition in the Legal
domain (LegalNERo)}},
month = may,
year = 2021,
publisher = {Zenodo},
doi = {10.5281/zenodo.4922385},
url = {https://doi.org/10.5281/zenodo.4922385}
}
```
```
@inproceedings{pais-etal-2021-named,
author = {Pais, Vasile and Mitrofan, Maria and Gasan, Carol Luca and Coneschi, Vlad and Ianov, Alexandru},
booktitle = {Proceedings of the Natural Legal Language Processing Workshop 2021},
doi = {10.18653/v1/2021.nllp-1.2},
month = {nov},
pages = {9--18},
publisher = {Association for Computational Linguistics},
title = {{Named Entity Recognition in the {R}omanian Legal Domain}},
url = {https://aclanthology.org/2021.nllp-1.2},
year = {2021}
}
```
### Contributions
Thanks to [@JoelNiklaus](https://github.com/joelniklaus) and [@kapllan](https://github.com/kapllan) for adding this dataset.
|
false |
# Dataset Card for ATCO2 test set corpus (1hr set)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages and Other Details](#languages-and-other-details)
- [Dataset Structure](#dataset-structure)
- [Data Fields](#data-fields)
- [Additional Information](#additional-information)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** [ATCO2 project homepage](https://www.atco2.org/)
- **Repository:** [ATCO2 corpus](https://github.com/idiap/atco2-corpus)
- **Paper:** [ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications](https://arxiv.org/abs/2211.04054)
### Dataset Summary
ATCO2 project aims at developing a unique platform allowing to collect, organize and pre-process air-traffic control (voice communication) data from air space. This project has received funding from the Clean Sky 2 Joint Undertaking (JU) under grant agreement No 864702. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and the Clean Sky 2 JU members other than the Union.
The project collected the real-time voice communication between air-traffic controllers and pilots available either directly through publicly accessible radio frequency channels or indirectly from air-navigation service providers (ANSPs). In addition to the voice communication data, contextual information is available in a form of metadata (i.e. surveillance data). The dataset consists of two distinct packages:
- A corpus of 5000+ hours (pseudo-transcribed) of air-traffic control speech collected across different airports (Sion, Bern, Zurich, etc.) in .wav format for speech recognition. Speaker distribution is 90/10% between males and females and the group contains native and non-native speakers of English.
- A corpus of 4 hours (transcribed) of air-traffic control speech collected across different airports (Sion, Bern, Zurich, etc.) in .wav format for speech recognition. Speaker distribution is 90/10% between males and females and the group contains native and non-native speakers of English. This corpus has been transcribed with orthographic information in XML format with speaker noise information, SNR values and others. Read Less
- A free sample of the 4 hours transcribed data is in [ATCO2 project homepage](https://www.atco2.org/data)
### Supported Tasks and Leaderboards
- `automatic-speech-recognition`. Already adapted/fine-tuned models are available here --> [Wav2Vec 2.0 LARGE mdel](https://huggingface.co/Jzuluaga/wav2vec2-large-960h-lv60-self-en-atc-uwb-atcc-and-atcosim).
### Languages and other details
The text and the recordings are in English. For more information see Table 3 and Table 4 of [ATCO2 corpus paper](https://arxiv.org/abs/2211.04054)
## Dataset Structure
### Data Fields
- `id (string)`: a string of recording identifier for each example, corresponding to its.
- `audio (audio)`: audio data for the given ID
- `text (string)`: transcript of the file already normalized. Follow these repositories for more details [w2v2-air-traffic](https://github.com/idiap/w2v2-air-traffic) and [bert-text-diarization-atc](https://github.com/idiap/bert-text-diarization-atc)
- `segment_start_time (float32)`: segment start time (normally 0)
- `segment_end_time (float32): segment end time
- `duration (float32)`: duration of the recording, compute as segment_end_time - segment_start_time
## Additional Information
### Licensing Information
The licensing status of the ATCO2-test-set-1h corpus is in the file **ATCO2-ASRdataset-v1_beta - End-User Data Agreement** in the data folder. Download the data in [ATCO2 project homepage](https://www.atco2.org/data)
### Citation Information
Contributors who prepared, processed, normalized and uploaded the dataset in HuggingFace:
```
@article{zuluaga2022how,
title={How Does Pre-trained Wav2Vec2. 0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications},
author={Zuluaga-Gomez, Juan and Prasad, Amrutha and Nigmatulina, Iuliia and Sarfjoo, Saeed and others},
journal={IEEE Spoken Language Technology Workshop (SLT), Doha, Qatar},
year={2022}
}
@article{zuluaga2022bertraffic,
title={BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications},
author={Zuluaga-Gomez, Juan and Sarfjoo, Seyyed Saeed and Prasad, Amrutha and others},
journal={IEEE Spoken Language Technology Workshop (SLT), Doha, Qatar},
year={2022}
}
@article{zuluaga2022atco2,
title={ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications},
author={Zuluaga-Gomez, Juan and Vesel{\`y}, Karel and Sz{\"o}ke, Igor and Motlicek, Petr and others},
journal={arXiv preprint arXiv:2211.04054},
year={2022}
}
```
|
false |
# Dataset Card for IWSLT 2017
## 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/site/iwsltevaluation2017/TED-tasks](https://sites.google.com/site/iwsltevaluation2017/TED-tasks)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [Overview of the IWSLT 2017 Evaluation Campaign](https://aclanthology.org/2017.iwslt-1.1/)
- **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:** 4.24 GB
- **Size of the generated dataset:** 1.14 GB
- **Total amount of disk used:** 5.38 GB
*This repository contain a modified version of the loading script used in the official [iwslt2017](https://huggingface.co/datasets/iwslt2017) repository updated to include document and segment information for all available sentence pairs, enabling their usage for document-level and context-aware MT applications. Refer to the original repository for additional information.*
|
false |
# MQuAD
The Medical Question and Answering dataset(MQuAD) has been refined, including the following datasets. You can download it through the Hugging Face dataset. Use the DATASETS method as follows.
## Quick Guide
```python
from datasets import load_dataset
dataset = load_dataset("danielpark/MQuAD-v1")
```
Medical Q/A datasets gathered from the following websites.
- eHealth Forum
- iCliniq
- Question Doctors
- WebMD
Data was gathered at the 5th of May 2017.
The MQuAD provides embedded question and answer arrays in string format, so it is recommended to convert the string-formatted arrays into float format as follows. This measure has been applied to save resources and time used for embedding.
```python
from datasets import load_dataset
from utilfunction import col_convert
import pandas as pd
qa = load_dataset("danielpark/MQuAD-v1", "csv")
df_qa = pd.DataFrame(qa['train'])
df_qa = col_convert(df_qa, ['Q_FFNN_embeds', 'A_FFNN_embeds'])
```
|
true |
C-Eval is a comprehensive Chinese evaluation suite for foundation models. It consists of 13948 multi-choice questions spanning 52 diverse disciplines and four difficulty levels. Please visit our [website](https://cevalbenchmark.com/) and [GitHub](https://github.com/SJTU-LIT/ceval/tree/main) or check our [paper](https://arxiv.org/abs/2305.08322) for more details.
Each subject consists of three splits: dev, val, and test. The dev set per subject consists of five exemplars with explanations for few-shot evaluation. The val set is intended to be used for hyperparameter tuning. And the test set is for model evaluation. Labels on the test split are not released, users are required to submit their results to automatically obtain test accuracy. [How to submit?](https://github.com/SJTU-LIT/ceval/tree/main#how-to-submit)
### Load the data
```python
from datasets import load_dataset
dataset=load_dataset(r"ceval/ceval-exam",name="computer_network")
print(dataset['val'][0])
# {'id': 0, 'question': '使用位填充方法，以01111110为位首flag，数据为011011111111111111110010，求问传送时要添加几个0____', 'A': '1', 'B': '2', 'C': '3', 'D': '4', 'answer': 'C', 'explanation': ''}
```
More details on loading and using the data are at our [github page](https://github.com/SJTU-LIT/ceval#data).
Please cite our paper if you use our dataset.
```
@article{huang2023ceval,
title={C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models},
author={Huang, Yuzhen and Bai, Yuzhuo and Zhu, Zhihao and Zhang, Junlei and Zhang, Jinghan and Su, Tangjun and Liu, Junteng and Lv, Chuancheng and Zhang, Yikai and Lei, Jiayi and Fu, Yao and Sun, Maosong and He, Junxian},
journal={arXiv preprint arXiv:2305.08322},
year={2023}
}
```
|
false |
# ANTILLES : An Open French Linguistically Enriched Part-of-Speech Corpus
## Table of Contents
- [Dataset Card for [Needs More Information]](#dataset-card-for-needs-more-information)
- [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)
- [sent_id = fr-ud-dev_00005](#sent_id--fr-ud-dev_00005)
- [text = Travail de trés grande qualité exécuté par un imprimeur artisan passionné.](#text--travail-de-trs-grande-qualit-excut-par-un-imprimeur-artisan-passionn)
- [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)
## Dataset Description
- **Homepage:** https://qanastek.github.io/ANTILLES/
- **Repository:** https://github.com/qanastek/ANTILLES
- **Paper:** https://hal.archives-ouvertes.fr/hal-03696042/document
- **Leaderboard:** https://paperswithcode.com/dataset/antilles
- **Point of Contact:** [Yanis Labrak](mailto:yanis.labrak@univ-avignon.fr)
### Dataset Summary
`ANTILLES` is a part-of-speech tagging corpora based on [UD_French-GSD](https://universaldependencies.org/treebanks/fr_gsd/index.html) which was originally created in 2015 and is based on the [universal dependency treebank v2.0](https://github.com/ryanmcd/uni-dep-tb).
Originally, the corpora consists of 400,399 words (16,341 sentences) and had 17 different classes. Now, after applying our tags augmentation script `transform.py`, we obtain 60 different classes which add semantic information such as: the gender, number, mood, person, tense or verb form given in the different CoNLL-U fields from the original corpora.
We based our tags on the level of details given by the [LIA_TAGG](http://pageperso.lif.univ-mrs.fr/frederic.bechet/download.html) statistical POS tagger written by [Frédéric Béchet](http://pageperso.lif.univ-mrs.fr/frederic.bechet/index-english.html) in 2001.
<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>.
### Supported Tasks and Leaderboards
`part-of-speech-tagging`: The dataset can be used to train a model for part-of-speech-tagging. The performance is measured by how high its F1 score is. A Flair Sequence-To-Sequence model trained to tag tokens from Wikipedia passages achieves a F1 score (micro) of 0.952.
### Languages
The text in the dataset is in French, as spoken by [Wikipedia](https://en.wikipedia.org/wiki/Main_Page) users. The associated [BCP-47](https://tools.ietf.org/html/bcp47) code is `fr`.
## Load the dataset
### HuggingFace
```python
from datasets import load_dataset
dataset = load_dataset("qanastek/ANTILLES")
print(dataset)
```
### FlairNLP
```python
from flair.datasets import UniversalDependenciesCorpus
corpus: Corpus = UniversalDependenciesCorpus(
data_folder='ANTILLES',
train_file="train.conllu",
test_file="test.conllu",
dev_file="dev.conllu"
)
```
## Load the model
### Flair ([model](https://huggingface.co/qanastek/pos-french))
```python
from flair.models import SequenceTagger
tagger = SequenceTagger.load("qanastek/pos-french")
```
## HuggingFace Spaces
<table style="width: fit-content;">
<thead>
<tr>
<td>
<a href="https://huggingface.co/spaces/qanastek/French-Part-Of-Speech-Tagging">
<img src="https://huggingface.co/datasets/qanastek/ANTILLES/raw/main/imgs/en.png" width="160">
</a>
</td>
<td>
<a href="https://huggingface.co/spaces/qanastek/Etiqueteur-Morphosyntaxique-Etendu">
<img src="https://huggingface.co/datasets/qanastek/ANTILLES/raw/main/imgs/fr.png" width="160">
</a>
</td>
</tr>
</thead>
</table>
## Dataset Structure
### Data Instances
```plain
# sent_id = fr-ud-dev_00005
# text = Travail de trés grande qualité exécuté par un imprimeur artisan passionné.
1 Travail travail NMS _ Gender=Masc|Number=Sing 0 root _ wordform=travail
2 de de PREP _ _ 5 case _ _
3 trés trés ADV _ _ 4 advmod _ _
4 grande grand ADJFS _ Gender=Fem|Number=Sing 5 amod _ _
5 qualité qualité NFS _ Gender=Fem|Number=Sing 1 nmod _ _
6 exécuté exécuter VPPMS _ Gender=Masc|Number=Sing|Tense=Past|VerbForm=Part 1 acl _ _
7 par par PREP _ _ 9 case _ _
8 un un DINTMS _ Definite=Ind|Gender=Masc|Number=Sing|PronType=Art 9 det _ _
9 imprimeur imprimeur NMS _ Gender=Masc|Number=Sing 6 obl:agent _ _
10 artisan artisan NMS _ Gender=Masc|Number=Sing 9 nmod _ _
11 passionné passionné ADJMS _ Gender=Masc|Number=Sing 9 amod _ SpaceAfter=No
12 . . YPFOR _ _ 1 punct _ _
```
### Data Fields
| Abbreviation | Description | Examples | # tokens |
|:--------:|:--------:|:--------:|:--------:|
| PREP | Preposition | de | 63 738 |
| AUX | Auxiliary Verb | est | 12 886 |
| ADV | Adverb | toujours | 14 969 |
| COSUB | Subordinating conjunction | que | 3 007 |
| COCO | Coordinating Conjunction | et | 10 102 |
| PART | Demonstrative particle | -t | 93 |
| PRON | Pronoun | qui ce quoi | 667 |
| PDEMMS | Singular Masculine Demonstrative Pronoun | ce | 1 950 |
| PDEMMP | Plurial Masculine Demonstrative Pronoun | ceux | 108 |
| PDEMFS | Singular Feminine Demonstrative Pronoun | cette | 1 004 |
| PDEMFP | Plurial Feminine Demonstrative Pronoun | celles | 53 |
| PINDMS | Singular Masculine Indefinite Pronoun | tout | 961 |
| PINDMP | Plurial Masculine Indefinite Pronoun | autres | 89 |
| PINDFS | Singular Feminine Indefinite Pronoun | chacune | 136 |
| PINDFP | Plurial Feminine Indefinite Pronoun | certaines | 31 |
| PROPN | Proper noun | houston | 22 135 |
| XFAMIL | Last name | levy | 6 449 |
| NUM | Numerical Adjectives | trentaine vingtaine | 67 |
| DINTMS | Masculine Numerical Adjectives | un | 4 254 |
| DINTFS | Feminine Numerical Adjectives | une | 3 543 |
| PPOBJMS | Singular Masculine Pronoun complements of objects | le lui | 1 425 |
| PPOBJMP | Plurial Masculine Pronoun complements of objects | eux y | 212 |
| PPOBJFS | Singular Feminine Pronoun complements of objects | moi la | 358 |
| PPOBJFP | Plurial Feminine Pronoun complements of objects | en y | 70 |
| PPER1S | Personal Pronoun First Person Singular | je | 571 |
| PPER2S | Personal Pronoun Second Person Singular | tu | 19 |
| PPER3MS | Personal Pronoun Third Person Masculine Singular | il | 3 938 |
| PPER3MP | Personal Pronoun Third Person Masculine Plurial | ils | 513 |
| PPER3FS | Personal Pronoun Third Person Feminine Singular | elle | 992 |
| PPER3FP | Personal Pronoun Third Person Feminine Plurial | elles | 121 |
| PREFS | Reflexive Pronouns First Person of Singular | me m' | 120 |
| PREF | Reflexive Pronouns Third Person of Singular | se s' | 2 337 |
| PREFP | Reflexive Pronouns First / Second Person of Plurial | nous vous | 686 |
| VERB | Verb | obtient | 21 131 |
| VPPMS | Singular Masculine Participle Past Verb | formulé | 6 275 |
| VPPMP | Plurial Masculine Participle Past Verb | classés | 1 352 |
| VPPFS | Singular Feminine Participle Past Verb | appelée | 2 434 |
| VPPFP | Plurial Feminine Participle Past Verb | sanctionnées | 813 |
| VPPRE | Present participle | étant | 2 |
| DET | Determinant | les l' | 25 206 |
| DETMS | Singular Masculine Determinant | les | 15 444 |
| DETFS | Singular Feminine Determinant | la | 10 978 |
| ADJ | Adjective | capable sérieux | 1 075 |
| ADJMS | Singular Masculine Adjective | grand important | 8 338 |
| ADJMP | Plurial Masculine Adjective | grands petits | 3 274 |
| ADJFS | Singular Feminine Adjective | franéaise petite | 8 004 |
| ADJFP | Plurial Feminine Adjective | légéres petites | 3 041 |
| NOUN | Noun | temps | 1 389 |
| NMS | Singular Masculine Noun | drapeau | 29 698 |
| NMP | Plurial Masculine Noun | journalistes | 10 882 |
| NFS | Singular Feminine Noun | téte | 25 414 |
| NFP | Plurial Feminine Noun | ondes | 7 448 |
| PREL | Relative Pronoun | qui dont | 2 976 |
| PRELMS | Singular Masculine Relative Pronoun | lequel | 94 |
| PRELMP | Plurial Masculine Relative Pronoun | lesquels | 29 |
| PRELFS | Singular Feminine Relative Pronoun | laquelle | 70 |
| PRELFP | Plurial Feminine Relative Pronoun | lesquelles | 25 |
| PINTFS | Singular Feminine Interrogative Pronoun | laquelle | 3 |
| INTJ | Interjection | merci bref | 75 |
| CHIF | Numbers | 1979 10 | 10 417 |
| SYM | Symbol | é % | 705 |
| YPFOR | Endpoint | . | 15 088 |
| PUNCT | Ponctuation | : , | 28 918 |
| MOTINC | Unknown words | Technology Lady | 2 022 |
| X | Typos & others | sfeir 3D statu | 175 |
### Data Splits
| | Train | Dev | Test |
|:------------------:|:------:|:------:|:-----:|
| # Docs | 14 449 | 1 476 | 416 |
| Avg # Tokens / Doc | 24.54 | 24.19 | 24.08 |
## 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
The corpora is free of personal or sensitive information since it has been based on `Wikipedia` articles content.
## Considerations for Using the Data
### Social Impact of Dataset
[Needs More Information]
### Discussion of Biases
The nature of the corpora introduce various biases such as the names of the streets which are temporaly based and can therefore introduce named entity like author or event names. For example, street names such as `Rue Victor-Hugo` or `Rue Pasteur` doesn't exist before the 20's century in France.
### Other Known Limitations
[Needs More Information]
## Additional Information
### Dataset Curators
__ANTILLES__: Labrak Yanis, Dufour Richard
__UD_FRENCH-GSD__: de Marneffe Marie-Catherine, Guillaume Bruno, McDonald Ryan, Suhr Alane, Nivre Joakim, Grioni Matias, Dickerson Carly, Perrier Guy
__Universal Dependency__: Ryan McDonald, Joakim Nivre, Yvonne Quirmbach-Brundage, Yoav Goldberg, Dipanjan Das, Kuzman Ganchev, Keith Hall, Slav Petrov, Hao Zhang, Oscar Tackstrom, Claudia Bedini, Nuria Bertomeu Castello and Jungmee Lee
### Licensing Information
```plain
For the following languages
German, Spanish, French, Indonesian, Italian, Japanese, Korean and Brazilian
Portuguese
we will distinguish between two portions of the data.
1. The underlying text for sentences that were annotated. This data Google
asserts no ownership over and no copyright over. Some or all of these
sentences may be copyrighted in some jurisdictions. Where copyrighted,
Google collected these sentences under exceptions to copyright or implied
license rights. GOOGLE MAKES THEM AVAILABLE TO YOU 'AS IS', WITHOUT ANY
WARRANTY OF ANY KIND, WHETHER EXPRESS OR IMPLIED.
2. The annotations -- part-of-speech tags and dependency annotations. These are
made available under a CC BY-SA 4.0. GOOGLE MAKES
THEM AVAILABLE TO YOU 'AS IS', WITHOUT ANY WARRANTY OF ANY KIND, WHETHER
EXPRESS OR IMPLIED. See attached LICENSE file for the text of CC BY-NC-SA.
Portions of the German data were sampled from the CoNLL 2006 Tiger Treebank
data. Hans Uszkoreit graciously gave permission to use the underlying
sentences in this data as part of this release.
Any use of the data should reference the above plus:
Universal Dependency Annotation for Multilingual Parsing
Ryan McDonald, Joakim Nivre, Yvonne Quirmbach-Brundage, Yoav Goldberg,
Dipanjan Das, Kuzman Ganchev, Keith Hall, Slav Petrov, Hao Zhang,
Oscar Tackstrom, Claudia Bedini, Nuria Bertomeu Castello and Jungmee Lee
Proceedings of ACL 2013
```
### Citation Information
Please cite the following paper when using this model.
ANTILLES extended corpus:
```latex
@inproceedings{labrak:hal-03696042,
TITLE = {{ANTILLES: An Open French Linguistically Enriched Part-of-Speech Corpus}},
AUTHOR = {Labrak, Yanis and Dufour, Richard},
URL = {https://hal.archives-ouvertes.fr/hal-03696042},
BOOKTITLE = {{25th International Conference on Text, Speech and Dialogue (TSD)}},
ADDRESS = {Brno, Czech Republic},
PUBLISHER = {{Springer}},
YEAR = {2022},
MONTH = Sep,
KEYWORDS = {Part-of-speech corpus ; POS tagging ; Open tools ; Word embeddings ; Bi-LSTM ; CRF ; Transformers},
PDF = {https://hal.archives-ouvertes.fr/hal-03696042/file/ANTILLES_A_freNch_linguisTIcaLLy_Enriched_part_of_Speech_corpus.pdf},
HAL_ID = {hal-03696042},
HAL_VERSION = {v1},
}
```
UD_French-GSD corpora:
```latex
@misc{
universaldependencies,
title={UniversalDependencies/UD_French-GSD},
url={https://github.com/UniversalDependencies/UD_French-GSD}, journal={GitHub},
author={UniversalDependencies}
}
```
{U}niversal {D}ependency Annotation for Multilingual Parsing:
```latex
@inproceedings{mcdonald-etal-2013-universal,
title = "{U}niversal {D}ependency Annotation for Multilingual Parsing",
author = {McDonald, Ryan and
Nivre, Joakim and
Quirmbach-Brundage, Yvonne and
Goldberg, Yoav and
Das, Dipanjan and
Ganchev, Kuzman and
Hall, Keith and
Petrov, Slav and
Zhang, Hao and
T{\"a}ckstr{\"o}m, Oscar and
Bedini, Claudia and
Bertomeu Castell{\'o}, N{\'u}ria and
Lee, Jungmee},
booktitle = "Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = aug,
year = "2013",
address = "Sofia, Bulgaria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P13-2017",
pages = "92--97",
}
```
LIA TAGG:
```latex
@techreport{LIA_TAGG,
author = {Frédéric Béchet},
title = {LIA_TAGG: a statistical POS tagger + syntactic bracketer},
institution = {Aix-Marseille University & CNRS},
year = {2001}
}
```
|
false | # Splice
The [Splice dataset](https://archive-beta.ics.uci.edu/dataset/69/molecular+biology+splice+junction+gene+sequences) from the [UCI repository](https://archive-beta.ics.uci.edu/).
# Configurations and tasks
| **Configuration** | **Task** |
|-------------------|---------------------------|
| splice | Multiclass classification |
| splice_EI | Binary classification |
| splice_IE | Binary classification |
| splice_N | Binary classification | |
false | # ShareGPT-ko-74k
ShareGPT 90k의 cleaned 버전을 구글 번역기를 이용하여 번역하였습니다.\
원본 데이터셋은 [여기](https://github.com/lm-sys/FastChat/issues/90)에서 확인하실 수 있습니다.
Korean-translated version of ShareGPT-90k, translated by Google Translaton.\
You can check the original dataset [here](https://github.com/lm-sys/FastChat/issues/90).
## Dataset Description
json 파일의 구조는 원본 데이터셋과 동일합니다.\
`*_unclneaed.json`은 원본 데이터셋을 번역하고 따로 후처리하지 않은 데이터셋입니다. (총 74k)\
`*_cleaned.json`은 위의 데이터에서 코드가 포함된 데이터를 러프하게 제거한 데이터셋입니다. (총 55k)\
**주의**: 코드는 번역되었을 수 있으므로 cleaned를 쓰시는 걸 추천합니다.
The structure of the dataset is the same with the original dataset.\
`*_unclneaed.json` are Korean-translated data, without any post-processing. (total 74k dialogues)\
`*_clneaed.json` are post-processed version which dialogues containing code snippets are eliminated from. (total 55k dialogues)\
**WARNING**: Code snippets might have been translated into Korean. I recommend you use cleaned files.
## Licensing Information
GPT를 이용한 데이터셋이므로 OPENAI의 [약관](https://openai.com/policies/terms-of-use)을 따릅니다.\
그 외의 경우 [CC BY 2.0 KR](https://creativecommons.org/licenses/by/2.0/kr/)을 따릅니다.
The licensing status of the datasets follows [OPENAI Licence](https://openai.com/policies/terms-of-use) as it contains GPT-generated sentences.\
For all the other cases, the licensing status follows [CC BY 2.0 KR](https://creativecommons.org/licenses/by/2.0/kr/).
## Code
번역에 사용한 코드는 아래 리포지토리에서 확인 가능합니다. Check out the following repository to see the translation code used.\
https://github.com/dubuduru/ShareGPT-translation
You can use the repository to translate ShareGPT-like dataset into your preferred language. |
true |
# Dataset Card for Elsevier OA CC-By
## Table of Contents
- [Dataset Card for Elsevier OA CC-By](#dataset-card-for-elsevier-oa-cc-by)
- [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://elsevier.digitalcommonsdata.com/datasets/zm33cdndxs
- **Repository:** https://elsevier.digitalcommonsdata.com/datasets/zm33cdndxs
- **Paper:** https://arxiv.org/abs/2008.00774
- **Leaderboard:**
- **Point of Contact:** [@orieg](https://huggingface.co/orieg)
### Dataset Summary
Elsevier OA CC-By: This is a corpus of 40k (40,091) open access (OA) CC-BY articles from across Elsevier’s journals
representing a large scale, cross-discipline set of research data to support NLP and ML research. The corpus include full-text
articles published in 2014 to 2020 and are categorized in 27 Mid Level ASJC Code (subject classification).
***Distribution of Publication Years***
| Publication Year | Number of Articles |
| :---: | :---: |
| 2014 | 3018 |
| 2015 | 4438 |
| 2016 | 5913 |
| 2017 | 6419 |
| 2018 | 8016 |
| 2019 | 10135 |
| 2020 | 2159 |
***Distribution of Articles Per Mid Level ASJC Code. Each article can belong to multiple ASJC codes.***
| Discipline | Count |
| --- | ---: |
| General | 3847 |
| Agricultural and Biological Sciences | 4840 |
| Arts and Humanities | 982 |
| Biochemistry, Genetics and Molecular Biology | 8356 |
| Business, Management and Accounting | 937 |
| Chemical Engineering | 1878 |
| Chemistry | 2490 |
| Computer Science | 2039 |
| Decision Sciences | 406 |
| Earth and Planetary Sciences | 2393 |
| Economics, Econometrics and Finance | 976 |
| Energy | 2730 |
| Engineering | 4778 |
| Environmental Science | 6049 |
| Immunology and Microbiology | 3211 |
| Materials Science | 3477 |
| Mathematics | 538 |
| Medicine | 7273 |
| Neuroscience | 3669 |
| Nursing | 308 |
| Pharmacology, Toxicology and Pharmaceutics | 2405 |
| Physics and Astronomy | 2404 |
| Psychology | 1760 |
| Social Sciences | 3540 |
| Veterinary | 991 |
| Dentistry | 40 |
| Health Professions | 821 |
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English (`en`).
## Dataset Structure
### Data Instances
The original dataset was published with the following json structure:
```
{
"docId": <str>,
"metadata":{
"title": <str>,
"authors": [
{
"first": <str>,
"initial": <str>,
"last": <str>,
"email": <str>
},
...
],
"issn": <str>,
"volume": <str>,
"firstpage": <str>,
"lastpage": <str>,
"pub_year": <int>,
"doi": <str>,
"pmid": <str>,
"openaccess": "Full",
"subjareas": [<str>],
"keywords": [<str>],
"asjc": [<int>],
},
"abstract":[
{
"sentence": <str>,
"startOffset": <int>,
"endOffset": <int>
},
...
],
"bib_entries":{
"BIBREF0":{
"title":<str>,
"authors":[
{
"last":<str>,
"initial":<str>,
"first":<str>
},
...
],
"issn": <str>,
"volume": <str>,
"firstpage": <str>,
"lastpage": <str>,
"pub_year": <int>,
"doi": <str>,
"pmid": <str>
},
...
},
"body_text":[
{
"sentence": <str>,
"secId": <str>,
"startOffset": <int>,
"endOffset": <int>,
"title": <str>,
"refoffsets": {
<str>:{
"endOffset":<int>,
"startOffset":<int>
}
},
"parents": [
{
"id": <str>,
"title": <str>
},
...
]
},
...
]
}
```
***docId*** The docID is the identifier of the document. This is unique to the document, and can be resolved into a URL
for the document through the addition of `https//www.sciencedirect.com/science/pii/<docId>`
***abstract*** This is the author provided abstract for the document
***body_text*** The full text for the document. The text has been split on sentence boundaries, thus making it easier to
use across research projects. Each sentence has the title (and ID) of the section which it is from, along with titles (and
IDs) of the parent section. The highest-level section takes index 0 in the parents array. If the array is empty then the
title of the section for the sentence is the highest level section title. This will allow for the reconstruction of the article
structure. References have been extracted from the sentences. The IDs of the extracted reference and their respective
offset within the sentence can be found in the “refoffsets” field. The complete list of references are can be found in
the “bib_entry” field along with the references’ respective metadata. Some will be missing as we only keep ‘clean’
sentences,
***bib_entities*** All the references from within the document can be found in this section. If the meta data for the
reference is available, it has been added against the key for the reference. Where possible information such as the
document titles, authors, and relevant identifiers (DOI and PMID) are included. The keys for each reference can be
found in the sentence where the reference is used with the start and end offset of where in the sentence that reference
was used.
***metadata*** Meta data includes additional information about the article, such as list of authors, relevant IDs (DOI and
PMID). Along with a number of classification schemes such as ASJC and Subject Classification.
***author_highlights*** Author highlights were included in the corpus where the author(s) have provided them. The
coverage is 61% of all articles. The author highlights, consisting of 4 to 6 sentences, is provided by the author with
the aim of summarising the core findings and results in the article.
### Data Fields
* ***title***: This is the author provided title for the document. 100% coverage.
* ***abstract***: This is the author provided abstract for the document. 99.25% coverage.
* ***keywords***: This is the author and publisher provided keywords for the document. 100% coverage.
* ***asjc***: This is the disciplines for the document as represented by 334 ASJC (All Science Journal Classification) codes. 100% coverage.
* ***subjareas***: This is the Subject Classification for the document as represented by 27 ASJC top-level subject classifications. 100% coverage.
* ***body_text***: The full text for the document. 100% coverage.
* ***author_highlights***: This is the author provided highlights for the document. 61.31% coverage.
### Data Splits
***Distribution of Publication Years***
| | Train | Test | Validation |
| --- | :---: | :---: | :---: |
| All Articles | 32072 | 4009 | 4008 |
| With Author Highlights | 19644 | 2420 | 2514 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
Date the data was collected: 2020-06-25T11:00:00.000Z
See the [original paper](https://doi.org/10.48550/arXiv.2008.00774) for more detail on the data collection process.
#### Who are the source language producers?
See `3.1 Data Sampling` in the [original paper](https://doi.org/10.48550/arXiv.2008.00774).
### 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](https://creativecommons.org/licenses/by/4.0/)
### Citation Information
```
@article{Kershaw2020ElsevierOC,
title = {Elsevier OA CC-By Corpus},
author = {Daniel James Kershaw and R. Koeling},
journal = {ArXiv},
year = {2020},
volume = {abs/2008.00774},
doi = {https://doi.org/10.48550/arXiv.2008.00774},
url = {https://elsevier.digitalcommonsdata.com/datasets/zm33cdndxs},
keywords = {Science, Natural Language Processing, Machine Learning, Open Dataset},
abstract = {We introduce the Elsevier OA CC-BY corpus. This is the first open
corpus of Scientific Research papers which has a representative sample
from across scientific disciplines. This corpus not only includes the
full text of the article, but also the metadata of the documents,
along with the bibliographic information for each reference.}
}
```
```
@dataset{https://10.17632/zm33cdndxs.3,
doi = {10.17632/zm33cdndxs.2},
url = {https://data.mendeley.com/datasets/zm33cdndxs/3},
author = "Daniel Kershaw and Rob Koeling",
keywords = {Science, Natural Language Processing, Machine Learning, Open Dataset},
title = {Elsevier OA CC-BY Corpus},
publisher = {Mendeley},
year = {2020},
month = {sep}
}
```
### Contributions
Thanks to [@orieg](https://github.com/orieg) for adding this dataset. |
false | # Dataset Card for AIO Version 2.0
This dataset is used for AIO (AI王), a competition to promote research on question answering systems for the Japanese language.
Each data point consists of a question and the answer to the question.
Please refer to [the official website](https://sites.google.com/view/project-aio/home) for further details. |
true |
# Dataset Card for "IndicXNLI"
## Table of Contents
- [Dataset Card for "IndicXNLI"](#dataset-card-for-indicxnli)
- [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 Description
- **Homepage:** <https://github.com/divyanshuaggarwal/IndicXNLI>
- **Paper:** [IndicXNLI: Evaluating Multilingual Inference for Indian Languages](https://arxiv.org/abs/2204.08776)
- **Point of Contact:** [Divyanshu Aggarwal](mailto:divyanshuggrwl@gmail.com)
### Dataset Summary
INDICXNLI is similar to existing
XNLI dataset in shape/form, but focusses on Indic language family. INDICXNLI include NLI
data for eleven major Indic languages that includes
Assamese (‘as’), Gujarat (‘gu’), Kannada (‘kn’),
Malayalam (‘ml’), Marathi (‘mr’), Odia (‘or’),
Punjabi (‘pa’), Tamil (‘ta’), Telugu (‘te’), Hindi
(‘hi’), and Bengali (‘bn’).
### Supported Tasks and Leaderboards
**Tasks:** Natural Language Inference
**Leaderboards:** Currently there is no Leaderboard for this dataset.
### Languages
- `Assamese (as)`
- `Bengali (bn)`
- `Gujarati (gu)`
- `Kannada (kn)`
- `Hindi (hi)`
- `Malayalam (ml)`
- `Marathi (mr)`
- `Oriya (or)`
- `Punjabi (pa)`
- `Tamil (ta)`
- `Telugu (te)`
## Dataset Structure
### Data Instances
One example from the `hi` dataset is given below in JSON format.
```python
{'premise': 'अवधारणात्मक रूप से क्रीम स्किमिंग के दो बुनियादी आयाम हैं-उत्पाद और भूगोल।',
'hypothesis': 'उत्पाद और भूगोल क्रीम स्किमिंग का काम करते हैं।',
'label': 1 (neutral) }
```
### Data Fields
- `premise (string)`: Premise Sentence
- `hypothesis (string)`: Hypothesis Sentence
- `label (integer)`: Integer label `0` if hypothesis `entails` the premise, `2` if hypothesis `negates` the premise and `1` otherwise.
### Data Splits
<!-- Below is the dataset split given for `hi` dataset.
```python
DatasetDict({
train: Dataset({
features: ['premise', 'hypothesis', 'label'],
num_rows: 392702
})
test: Dataset({
features: ['premise', 'hypothesis', 'label'],
num_rows: 5010
})
validation: Dataset({
features: ['premise', 'hypothesis', 'label'],
num_rows: 2490
})
})
``` -->
Language | ISO 639-1 Code |Train | Test | Dev |
--------------|----------------|-------|-----|------|
Assamese | as | 392,702 | 5,010 | 2,490 |
Bengali | bn | 392,702 | 5,010 | 2,490 |
Gujarati | gu | 392,702 | 5,010 | 2,490 |
Hindi | hi | 392,702 | 5,010 | 2,490 |
Kannada | kn | 392,702 | 5,010 | 2,490 |
Malayalam | ml |392,702 | 5,010 | 2,490 |
Marathi | mr |392,702 | 5,010 | 2,490 |
Oriya | or | 392,702 | 5,010 | 2,490 |
Punjabi | pa | 392,702 | 5,010 | 2,490 |
Tamil | ta | 392,702 | 5,010 | 2,490 |
Telugu | te | 392,702 | 5,010 | 2,490 |
<!-- The dataset split remains same across all languages. -->
## Dataset usage
Code snippet for using the dataset using datasets library.
```python
from datasets import load_dataset
dataset = load_dataset("Divyanshu/indicxnli")
```
## Dataset Creation
Machine translation of XNLI english dataset to 11 listed Indic Languages.
### Curation Rationale
[More information needed]
### Source Data
[XNLI dataset](https://cims.nyu.edu/~sbowman/xnli/)
#### Initial Data Collection and Normalization
[Detailed in the paper](https://arxiv.org/abs/2204.08776)
#### Who are the source language producers?
[Detailed in the paper](https://arxiv.org/abs/2204.08776)
#### Human Verification Process
[Detailed in the paper](https://arxiv.org/abs/2204.08776)
## Considerations for Using the Data
### Social Impact of Dataset
[Detailed in the paper](https://arxiv.org/abs/2204.08776)
### Discussion of Biases
[Detailed in the paper](https://arxiv.org/abs/2204.08776)
### Other Known Limitations
[Detailed in the paper](https://arxiv.org/abs/2204.08776)
### Dataset Curators
Divyanshu Aggarwal, Vivek Gupta, Anoop Kunchukuttan
### Licensing Information
Contents of this repository are restricted to only non-commercial research purposes under the [Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/). Copyright of the dataset contents belongs to the original copyright holders.
### Citation Information
If you use any of the datasets, models or code modules, please cite the following paper:
```
@misc{https://doi.org/10.48550/arxiv.2204.08776,
doi = {10.48550/ARXIV.2204.08776},
url = {https://arxiv.org/abs/2204.08776},
author = {Aggarwal, Divyanshu and Gupta, Vivek and Kunchukuttan, Anoop},
keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {IndicXNLI: Evaluating Multilingual Inference for Indian Languages},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!-- ### Contributions -->
|
false |
# Dataset Card for resd
## 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://huggingface.co/datasets/Aniemore/resd**
- **Repository: https://github.com/aniemore/Aniemore**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
Russian dataset of emotional speech dialogues. This dataset was assembled from ~3.5 hours of live speech by actors who voiced pre-distributed emotions in the dialogue for ~3 minutes each.
### 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
This dataset was created by Artem Amentes, Nikita Davidchuk and Ilya Lubenets
### Citation Information
```
@misc{Aniemore,
author = {Артем Аментес, Илья Лубенец, Никита Давидчук},
title = {Открытая библиотека искусственного интеллекта для анализа и выявления эмоциональных оттенков речи человека},
year = {2022},
publisher = {Hugging Face},
journal = {Hugging Face Hub},
howpublished = {\url{https://huggingface.com/aniemore/Aniemore}},
email = {hello@socialcode.ru}
}
```
### Contributions
Thanks to [@Ar4ikov](https://github.com/Ar4ikov) for adding this dataset. |
false | # Dataset Card for "DPhi_Sprint_25_Flowers"
All images in this archive are licensed under the Creative Commons By-Attribution License, available at:
https://creativecommons.org/licenses/by/2.0/
The photographers are listed in LICENSE.txt, thanks to all of them for making their work available.
However, you will observe the image file names are different in this file than those we have provided. The file names were changed solely for the purpose of the data sprint. |
false | # Dataset Card for "matreshka"
(image generated by Kandinsky-2.1 neural network)
Russian dialogues, the persona of the first interlocutor, and a summary of the dialogue generated by GPT-3.5, starting with the first phrase given in the prompt.
The matreshka dataset is a multi task datasey, you can use it for the task of summarizing a dialogue or generating a dialogue. Contains life dialogues and is also filled with facts about the world. The dataset was going to give the interlocutor a human manner of communication.
After generation, some data contained a format that did not match the request, so we stripped the data with regular expressions. Next, we checked for the correct data type in each line, and changed to the correct format if necessary.
authors' telegram channels: [@nadlskom](https://t.me/nadlskom), [@lovedeathtransformers](https://t.me/lovedeathtransformers) |
false |
Chinese-Dolly-15k是骆驼团队翻译的Dolly instruction数据集
最后49条数据因为翻译长度超过限制，没有翻译成功，建议删除或者手动翻译一下
原来的数据集'databricks/databricks-dolly-15k'是由数千名Databricks员工根据InstructGPT论文中概述的几种行为类别生成的遵循指示记录的开源数据集。这几个行为类别包括头脑风暴、分类、封闭型问答、生成、信息提取、开放型问答和摘要。
在知识共享署名-相同方式共享3.0（CC BY-SA 3.0）许可下，此数据集可用于任何学术或商业用途。
我们会陆续将更多数据集发布到hf，包括
- [ ] Coco Caption的中文翻译
- [x] CoQA的中文翻译
- [ ] CNewSum的Embedding数据
- [x] 增广的开放QA数据
- [x] WizardLM的中文翻译
- [x] MMC4的中文翻译
如果你也在做这些数据集的筹备，欢迎来联系我们，避免重复花钱。
# 骆驼(Luotuo): 开源中文大语言模型
[https://github.com/LC1332/Luotuo-Chinese-LLM](https://github.com/LC1332/Luotuo-Chinese-LLM)
骆驼(Luotuo)项目是由[冷子昂](https://blairleng.github.io) @ 商汤科技, 陈启源 @ 华中师范大学 以及 李鲁鲁 @ 商汤科技 发起的中文大语言模型开源项目，包含了一系列语言模型。
骆驼项目**不是**商汤科技的官方产品。
## Citation
Please cite the repo if you use the data or code in this repo.
```
@misc{alpaca,
author={Ziang Leng, Qiyuan Chen and Cheng Li},
title = {Luotuo: An Instruction-following Chinese Language model, LoRA tuning on LLaMA},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/LC1332/Luotuo-Chinese-LLM}},
}
```
|
false | |
true |
# Dataset Card for ParaPhraser
### Dataset Summary
ParaPhraser is a news headlines corpus annotated according to the following schema:
```
1: precise paraphrases
0: near paraphrases
-1: non-paraphrases
```
The _Plus_ part is also available.
It contains clusters of news headline paraphrases labeled automatically by a fine-tuned paraphrase detection BERT model.
In order to load it:
```python
from datasets import load_dataset
corpus = load_dataset('merionum/ru_paraphraser', data_files='plus.jsonl')
```
## Dataset Structure
```
train: 7,227 pairs
test: 1,924 pairs
plus: 1,725,393 clusters (total: ~7m texts)
```
### Citation Information
```
@inproceedings{pivovarova2017paraphraser,
title={ParaPhraser: Russian paraphrase corpus and shared task},
author={Pivovarova, Lidia and Pronoza, Ekaterina and Yagunova, Elena and Pronoza, Anton},
booktitle={Conference on artificial intelligence and natural language},
pages={211--225},
year={2017},
organization={Springer}
}
```
```
@inproceedings{gudkov-etal-2020-automatically,
title = "Automatically Ranked {R}ussian Paraphrase Corpus for Text Generation",
author = "Gudkov, Vadim and
Mitrofanova, Olga and
Filippskikh, Elizaveta",
booktitle = "Proceedings of the Fourth Workshop on Neural Generation and Translation",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.ngt-1.6",
doi = "10.18653/v1/2020.ngt-1.6",
pages = "54--59",
abstract = "The article is focused on automatic development and ranking of a large corpus for Russian paraphrase generation which proves to be the first corpus of such type in Russian computational linguistics. Existing manually annotated paraphrase datasets for Russian are limited to small-sized ParaPhraser corpus and ParaPlag which are suitable for a set of NLP tasks, such as paraphrase and plagiarism detection, sentence similarity and relatedness estimation, etc. Due to size restrictions, these datasets can hardly be applied in end-to-end text generation solutions. Meanwhile, paraphrase generation requires a large amount of training data. In our study we propose a solution to the problem: we collect, rank and evaluate a new publicly available headline paraphrase corpus (ParaPhraser Plus), and then perform text generation experiments with manual evaluation on automatically ranked corpora using the Universal Transformer architecture.",
}
```
### Contributions
Dataset maintainer:
Vadim Gudkov: [@merionum](https://github.com/merionum)
|
true |
This is the filtered Japanese subset of [XL-Sum](https://huggingface.co/datasets/csebuetnlp/xlsum) followed by [PaLM 2](https://arxiv.org/abs/2305.10403)
**filters**
- 15-gram overlap
\* code: https://gist.github.com/mkshing/d6371cbfdd50d4f352cee247fd4dd86a
**number of examples**
- train: 4215 (before: 7113)
- validation: 758 (before: 889)
- test: 766 (before: 889)
|
true | # Dataset for project: kor_hate_eval(APEACH)
## Sample Code
<a href="https://colab.research.google.com/drive/1djd0fuoMYIaf7VCHaLQIziJi4_yBJruP#scrollTo=VPR24ysr5Q7k"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="base"/></a>
## Dataset Descritpion
Korean Hate Speech Evaluation Datasets : trained with [BEEP!](https://huggingface.co/datasets/kor_hate) and evaluate with [APEACH](https://github.com/jason9693/APEACH)
- **Repository: [Korean HateSpeech Evaluation Dataset](https://github.com/jason9693/APEACH)**
- **Paper: [APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets](https://arxiv.org/abs/2202.12459)**
- **Point of Contact: [Kichang Yang](ykcha9@gmail.com)**
### Languages
ko-KR
## Dataset Structure
### Data Instances
A sample from this dataset looks as follows:
```json
{'text': ['(현재 호텔주인 심정) 아18 난 마른하늘에 날벼락맞고 호텔망하게생겼는데 누군 계속 추모받네....',
'....한국적인 미인의 대표적인 분...너무나 곱고아름다운모습...그모습뒤의 슬픔을 미처 알지못했네요ㅠ'],
'class': ['Spoiled', 'Default']}
```
### Dataset Fields
The dataset has the following fields (also called "features"):
```json
{
"text": "Value(dtype='string', id=None)",
"class": "ClassLabel(num_classes=2, names=['Default', 'Spoiled'], id=None)"
}
```
### Dataset Splits
This dataset is split into a train and validation split. The split sizes are as follow:
| Split name | Num samples |
| ------------ | ------------------- |
| train (binarized BEEP!) | 7896 |
| valid (APEACH) | 3770 |
## Citation
```
@article{yang2022apeach,
title={APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets},
author={Yang, Kichang and Jang, Wonjun and Cho, Won Ik},
journal={arXiv preprint arXiv:2202.12459},
year={2022}
}
```
|
false | This is a handmade dataset for making a Japanese chatbot. Conversations will continue to grow. |
true | # Dataset Card for "tacred"
## 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://nlp.stanford.edu/projects/tacred](https://nlp.stanford.edu/projects/tacred)
- **Paper:** [Position-aware Attention and Supervised Data Improve Slot Filling](https://aclanthology.org/D17-1004/)
- **Point of Contact:** See [https://nlp.stanford.edu/projects/tacred/](https://nlp.stanford.edu/projects/tacred/)
- **Size of downloaded dataset files:** 62.3 MB
- **Size of the generated dataset:** 139.2 MB
- **Total amount of disk used:** 201.5 MB
### Dataset Summary
The TAC Relation Extraction Dataset (TACRED) is a large-scale relation extraction dataset with 106,264 examples built over newswire and web text from the corpus used in the yearly TAC Knowledge Base Population (TAC KBP) challenges. Examples in TACRED cover 41 relation types as used in the TAC KBP challenges (e.g., per:schools_attended
and org:members) or are labeled as no_relation if no defined relation is held. These examples are created by combining available human annotations from the TAC
KBP challenges and crowdsourcing. Please see [Stanford's EMNLP paper](https://nlp.stanford.edu/pubs/zhang2017tacred.pdf), or their [EMNLP slides](https://nlp.stanford.edu/projects/tacred/files/position-emnlp2017.pdf) for full details.
Note:
- There is currently a [label-corrected version](https://github.com/DFKI-NLP/tacrev) of the TACRED dataset, which you should consider using instead of
the original version released in 2017. For more details on this new version, see the [TACRED Revisited paper](https://aclanthology.org/2020.acl-main.142/)
published at ACL 2020.
- There is also a [relabeled and pruned version](https://github.com/gstoica27/Re-TACRED) of the TACRED dataset.
For more details on this new version, see the [Re-TACRED paper](https://arxiv.org/abs/2104.08398)
published at ACL 2020.
This repository provides all three versions of the dataset as BuilderConfigs - `'original'`, `'revisited'` and `'re-tacred'`.
Simply set the `name` parameter in the `load_dataset` method in order to choose a specific version. The original TACRED is loaded per default.
### Supported Tasks and Leaderboards
- **Tasks:** Relation Classification
- **Leaderboards:** [https://paperswithcode.com/sota/relation-extraction-on-tacred](https://paperswithcode.com/sota/relation-extraction-on-tacred)
### Languages
The language in the dataset is English.
## Dataset Structure
### Data Instances
- **Size of downloaded dataset files:** 62.3 MB
- **Size of the generated dataset:** 139.2 MB
- **Total amount of disk used:** 201.5 MB
An example of 'train' looks as follows:
```json
{
"id": "61b3a5c8c9a882dcfcd2",
"docid": "AFP_ENG_20070218.0019.LDC2009T13",
"relation": "org:founded_by",
"token": ["Tom", "Thabane", "resigned", "in", "October", "last", "year", "to", "form", "the", "All", "Basotho", "Convention", "-LRB-", "ABC", "-RRB-", ",", "crossing", "the", "floor", "with", "17", "members", "of", "parliament", ",", "causing", "constitutional", "monarch", "King", "Letsie", "III", "to", "dissolve", "parliament", "and", "call", "the", "snap", "election", "."],
"subj_start": 10,
"subj_end": 13,
"obj_start": 0,
"obj_end": 2,
"subj_type": "ORGANIZATION",
"obj_type": "PERSON",
"stanford_pos": ["NNP", "NNP", "VBD", "IN", "NNP", "JJ", "NN", "TO", "VB", "DT", "DT", "NNP", "NNP", "-LRB-", "NNP", "-RRB-", ",", "VBG", "DT", "NN", "IN", "CD", "NNS", "IN", "NN", ",", "VBG", "JJ", "NN", "NNP", "NNP", "NNP", "TO", "VB", "NN", "CC", "VB", "DT", "NN", "NN", "."],
"stanford_ner": ["PERSON", "PERSON", "O", "O", "DATE", "DATE", "DATE", "O", "O", "O", "O", "O", "O", "O", "ORGANIZATION", "O", "O", "O", "O", "O", "O", "NUMBER", "O", "O", "O", "O", "O", "O", "O", "O", "PERSON", "PERSON", "O", "O", "O", "O", "O", "O", "O", "O", "O"],
"stanford_head": [2, 3, 0, 5, 3, 7, 3, 9, 3, 13, 13, 13, 9, 15, 13, 15, 3, 3, 20, 18, 23, 23, 18, 25, 23, 3, 3, 32, 32, 32, 32, 27, 34, 27, 34, 34, 34, 40, 40, 37, 3],
"stanford_deprel": ["compound", "nsubj", "ROOT", "case", "nmod", "amod", "nmod:tmod", "mark", "xcomp", "det", "compound", "compound", "dobj", "punct", "appos", "punct", "punct", "xcomp", "det", "dobj", "case", "nummod", "nmod", "case", "nmod", "punct", "xcomp", "amod", "compound", "compound", "compound", "dobj", "mark", "xcomp", "dobj", "cc", "conj", "det", "compound", "dobj", "punct"]
}
```
### Data Fields
The data fields are the same among all splits.
- `id`: the instance id of this sentence, a `string` feature.
- `docid`: the TAC KBP document id of this sentence, a `string` feature.
- `token`: the list of tokens of this sentence, obtained with the StanfordNLP toolkit, a `list` of `string` features.
- `relation`: the relation label of this instance, a `string` classification label.
- `subj_start`: the 0-based index of the start token of the relation subject mention, an `ìnt` feature.
- `subj_end`: the 0-based index of the end token of the relation subject mention, exclusive, an `ìnt` feature.
- `subj_type`: the NER type of the subject mention, among 23 fine-grained types used in the [Stanford NER system](https://stanfordnlp.github.io/CoreNLP/ner.html), a `string` feature.
- `obj_start`: the 0-based index of the start token of the relation object mention, an `ìnt` feature.
- `obj_end`: the 0-based index of the end token of the relation object mention, exclusive, an `ìnt` feature.
- `obj_type`: the NER type of the object mention, among 23 fine-grained types used in the [Stanford NER system](https://stanfordnlp.github.io/CoreNLP/ner.html), a `string` feature.
- `stanford_pos`: the part-of-speech tag per token. the NER type of the subject mention, among 23 fine-grained types used in the [Stanford NER system](https://stanfordnlp.github.io/CoreNLP/ner.html), a `list` of `string` features.
- `stanford_ner`: the NER tags of tokens (IO-Scheme), among 23 fine-grained types used in the [Stanford NER system](https://stanfordnlp.github.io/CoreNLP/ner.html), a `list` of `string` features.
- `stanford_deprel`: the Stanford dependency relation tag per token, a `list` of `string` features.
- `stanford_head`: the head (source) token index (0-based) for the dependency relation per token. The root token has a head index of -1, a `list` of `int` features.
### Data Splits
To miminize dataset bias, TACRED is stratified across years in which the TAC KBP challenge was run:
| | Train | Dev | Test |
| ----- | ------ | ----- | ---- |
| TACRED | 68,124 (TAC KBP 2009-2012) | 22,631 (TAC KBP 2013) | 15,509 (TAC KBP 2014) |
| Re-TACRED | 58,465 (TAC KBP 2009-2012) | 19,584 (TAC KBP 2013) | 13,418 (TAC KBP 2014) |
## 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
See the Stanford paper and the Tacred Revisited paper, plus their appendices.
To ensure that models trained on TACRED are not biased towards predicting false positives on real-world text,
all sampled sentences where no relation was found between the mention pairs were fully annotated to be negative examples. As a result, 79.5% of the examples
are labeled as no_relation.
#### 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
To respect the copyright of the underlying TAC KBP corpus, TACRED is released via the
Linguistic Data Consortium ([LDC License](https://catalog.ldc.upenn.edu/license/ldc-non-members-agreement.pdf)).
You can download TACRED from the [LDC TACRED webpage](https://catalog.ldc.upenn.edu/LDC2018T24).
If you are an LDC member, the access will be free; otherwise, an access fee of $25 is needed.
### Citation Information
The original dataset:
```
@inproceedings{zhang2017tacred,
author = {Zhang, Yuhao and Zhong, Victor and Chen, Danqi and Angeli, Gabor and Manning, Christopher D.},
booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP 2017)},
title = {Position-aware Attention and Supervised Data Improve Slot Filling},
url = {https://nlp.stanford.edu/pubs/zhang2017tacred.pdf},
pages = {35--45},
year = {2017}
}
```
For the revised version (`"revisited"`), please also cite:
```
@inproceedings{alt-etal-2020-tacred,
title = "{TACRED} Revisited: A Thorough Evaluation of the {TACRED} Relation Extraction Task",
author = "Alt, Christoph and
Gabryszak, Aleksandra and
Hennig, Leonhard",
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.142",
doi = "10.18653/v1/2020.acl-main.142",
pages = "1558--1569",
}
```
For the relabeled version (`"re-tacred"`), please also cite:
```
@inproceedings{DBLP:conf/aaai/StoicaPP21,
author = {George Stoica and
Emmanouil Antonios Platanios and
Barnab{\'{a}}s P{\'{o}}czos},
title = {Re-TACRED: Addressing Shortcomings of the {TACRED} Dataset},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {13843--13850},
publisher = {{AAAI} Press},
year = {2021},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/17631},
}
```
### Contributions
Thanks to [@dfki-nlp](https://github.com/dfki-nlp) and [@phucdev](https://github.com/phucdev) for adding this dataset.
|
false | # Dataset Card for "stackoverflow_python"
### Dataset Summary
This dataset comes originally from [kaggle](https://www.kaggle.com/stackoverflow/pythonquestions).
It was originally split into three tables (CSV files) (Questions, Answers, and Tags)
now merged into a single table. Each row corresponds to a pair (question-answer) and
their associated tags.
The dataset contains all questions asked between August 2, 2008 and Ocotober 19, 2016.
### Supported Tasks and Leaderboards
This might be useful for open-domain question-answering tasks.
## Additional information
### License
All Stack Overflow user contributions are licensed under CC-BY-SA 3.0 with attribution required. |
false |
# Dataset Card for RixVox
## Dataset Description
- **Repository:** [Riksdagen anföranden repository](https://github.com/kb-labb/riksdagen_anforanden)
- **Paper:** ["RixVox: A Swedish Speech Corpus with 5500 Hours of Speech from Parliamentary Debates"](https://kb-labb.github.io/posts/2023-03-09-rixvox-a-swedish-speech-corpus/)
- **Point of Contact:** [KBLab](mailto:kblabb@kb.se)
- **Total amount of disk used:** ca. 1.2 TB
### Dataset Summary
RixVox is a speech dataset comprised of speeches from the Riksdag (the Swedish Parliament). It covers speeches from debates during the period 2003-2023. Audio from speeches have been aligned, on the sentence level, with transcripts from written protocols using `aeneas`. An observation may consist of one or several concatenated sentences (up to 30 seconds in duration). Detailed speaker metadata is available for each observation, including the speaker's name, gender, political party, birth year and the electoral district they represent. The dataset contains a total of 5493 hours of speech with transcriptions.
## How to use & Supported Tasks
### Supported Tasks
Tasks are not supported by default (there are no label fields). The dataset may however be suited for:
- Automatic Speech Recognition (ASR).
- Speaker identification and verification.
- Creation of synthetic diarization datasets.
- Research on bias in ASR systems.
### How to use
To download and extract the files locally you can use `load_dataset()`. We recommend you set the `cache_dir` argument to point to a location that has plenty of disk space (1.2TB+). Here's how to download the `train` split:
```python
from datasets import load_dataset
# To download/load all splits at once, don't specify a split
rixvox = load_dataset("KBLab/rixvox", split="train", cache_dir="data_rixvox")
```
You can also stream the dataset. This is useful if you want to explore the dataset or if you don't have enough disk space to download the entire dataset. Here's how to stream the `train` split:
```python
from datasets import load_dataset
rixvox = load_dataset("KBLab/rixvox", cache_dir="data_rixvox", split="train", streaming=True)
print(next(iter(rixvox)))
# Grab 5 observations
rixvox_subset = rixvox.take(5)
for example in rixvox_subset:
print(example)
```
**Create a [PyTorch dataloader](https://huggingface.co/docs/datasets/use_with_pytorch)** with your dataset.
Local mode:
```python
from datasets import load_dataset
from torch.utils.data.sampler import BatchSampler, RandomSampler
# Dataset is not pre-shuffled, recommend shuffling it before training.
rixvox = load_dataset("KBLab/rixvox", split="train", cache_dir="data_rixvox")
batch_sampler = BatchSampler(RandomSampler(rixvox), batch_size=32, drop_last=False)
dataloader = DataLoader(rixvox, batch_sampler=batch_sampler)
```
Streaming mode:
```python
from datasets import load_dataset
from torch.utils.data import DataLoader
rixvox = load_dataset("KBLab/rixvox", split="train", cache_dir="data_rixvox")
dataloader = DataLoader(rixvox, batch_size=32)
```
See Huggingface's guide on [streaming datasets](https://huggingface.co/docs/datasets/v1.11.0/dataset_streaming.html) for more information on how to shuffle in streaming mode.
### Languages
- Swedish. The BCP 47 language tag for Swedish is `sv`.
## Dataset Structure
### Data Instances
There are a total of `835044` observations from `1194` different speakers. Each observation can be up to 30 seconds in duration. An observation belongs to a debate (`dokid`), is extratected from a speech (`anforande_nummer`), and is numbered according to its order within the speech (`observation_nr`). Here is an example of an observation:
```
{'dokid': 'GR01BOU3',
'anforande_nummer': 191,
'observation_nr': 0,
'audio': {'path': 'GR01BOU3/2442210220028601121_anf191_1_25.wav',
'array': array([0.01171875, 0.01242065, 0.01071167, ..., 0.00689697, 0.00918579,
0.00650024]),
'sampling_rate': 16000},
'text': 'Kristdemokraterna står bakom alla reservationer med kristdemokratiska förtecken, men jag nöjer mig med att yrka bifall till reservation 1. Jag ska i det här inlägget beröra några av de åtta punkter som är föremål för reservationer från kristdemokratiskt håll, i vissa fall tillsammans med andra partier.',
'debatedate': datetime.datetime(2003, 12, 4, 0, 0),
'speaker': 'Göran Hägglund',
'party': 'KD',
'gender': 'male',
'birth_year': 1959,
'electoral_district': 'Hallands län',
'intressent_id': '0584659199514',
'speaker_from_id': True,
'speaker_audio_meta': 'Göran Hägglund (Kd)',
'start': 1.4,
'end': 24.96,
'duration': 23.560000000000002,
'bleu_score': 0.7212783273624307,
'filename': 'GR01BOU3/2442210220028601121_anf191_1_25.wav',
'path': 'GR01BOU3/2442210220028601121_anf191_1_25.wav',
'speaker_total_hours': 30.621333333333332}
```
See more examples in the [dataset viewer](https://huggingface.co/datasets/KBLab/rixvox/viewer/default/train).
### Data Fields
* `dokid`: Document id for the debate used by the Riksdag. This is the same for all speeches in a debate.
* `anforande_nummer`: Speech number within the debate, or within the debate sessions on a particular day. Should create a unique primary key for a speech in combination with `dokid` (sometimes there are duplicates, but we removed them from this dataset).
* `observation_nr`: Observation number within the speech. Creates a unique identifier for an observation in combination with `dokid` and `anforande_nummer`.
* `text`: The text transcript from written protocols. The transcripts are not always verbatim. Transcribers have to different degrees adjusted sentence ordering, words and phrasing when they deemed it appropriate.
* `debatedate`: The date of the debate.
* `start`: The start time of the observation within a speech (in seconds).
* `end`: The end time of the observation within a speech (in seconds).
* `duration`: The duration of the observation (`end` subtracted with `start`).
* `intressent_id`: Unique id for the speaker within the Riksdag's database (see [person.csv.zip](https://data.riksdagen.se/dataset/person/person.csv.zip) from the Riksdag).
* `speaker`: The speaker's name retrieved via the `intressent_id`.
* `party`: The speaker's party retrieved via the `intressent_id`.
* `gender`: The speaker's gender retrieved via the `intressent_id`.
* `birth_year`: The speaker's bith year retrieved via the `intressent_id`.
* `electoral_district`: The electoral district which the speaker represents if they are/were a member of parliament (retrieved via the `intressent_id`).
* `speaker_audio_meta`: The speaker's name and title as listed in the Riksdag's oroginal text format metadata (sometimes wrong and mismatched against `intressent_id`).
* `speaker_from_id`: Whether the speaker metadata was retrieved via the `intressent_id` or via the Riksdag's original metadata (for those speeches with a missing `intressent_id`).
* `bleu_score`: The BLEU score of the automatic speech recognition (ASR) transcript against the Riksdag's written protocol. Calculated on the entirity of the speech that an observation (30s snippet) is extracted from. A low number for a speech may indicate that either i) the ASR model had trouble transcribing the speaker's accent or dialect, or ii) the transcription took certain liberties in editing and rephrasing the speech.
* `speaker_total_hours`: The total number of hours of speech from the speaker in the RixVox dataset.
* `filename`: The filename of the observation in the compressed tar.gz files. Useful if you don't want to use Huggingface `datasets`, but would rather manually download and extract the files from the data shards.
* `path`: Dynamically created variable. Contains the local path to the observation's audio file after you download and extract the files via `load_dataset()` in the `datasets` library.
### Data Splits
Dataset splits were randomly sampled on the speaker level. That is, a speaker is only present in a single split. We sample speakers for each split until the following conditions are met:
- 98% of the total number of hours of speech are included in the train split.
- 1% of the total number of hours of speech are included in the validation split.
- 1% of the total number of hours of speech are included in the test split.
| Dataset Split | Observations | Total duration of speech (hours) | Average duration obs. (seconds) | Number of speakers |
| ------------- | ----------------: | -------------------------------: | ------------------------------: | -----------------: |
| Train | 818227 | 5383 | 23.69 | 1165 |
| Validation | 7933 | 52 | 23.50 | 18 |
| Test | 8884 | 59 | 23.74 | 11 |
## Dataset Creation
For more information about the creation of this dataset, see the article ["Finding Speeches in the Riksdag's Debates"](https://kb-labb.github.io/posts/2023-02-15-finding-speeches-in-the-riksdags-debates/) from our blog.
### Curation Rationale
Before RixVox, there was only a couple of hundred hours of transcribed speech available to train ASR models for Swedish. ASR models such as Whisper have shown that the performance of models can benefit significantly from adding more supervised data during pretraining or finetuning. Media from debates in the Riksdag are published openly on the web together with transcripts and other metadata. The open data initiatives of the Riksdag presented an opportunity to create a high quality open speech corpus for Swedish.
### Source Data
The Swedish Parliament.
- [Transcripts of speeches](https://data.riksdagen.se/data/anforanden/).
- Use the `rel_dok_id` of transcripts of speeches to query the Riksdag's media API (e.g. https://data.riksdagen.se/api/mhs-vodapi?H901FiU1 ) for available media and metadata.
#### Initial Data Collection and Normalization
For information on how the speeches were segmented and identified in debate audio files, see the article ["Finding Speeches in the Riksdag's Debates"](https://kb-labb.github.io/posts/2023-02-15-finding-speeches-in-the-riksdags-debates/).
For information on how the speech segmentations were used to create the final RixVox dataset, see the article ["RixVox: A Swedish Speech Corpus with 5500 Hours of Speech from Parliamentary Debates"](https://kb-labb.github.io/posts/2023-03-09-rixvox-a-swedish-speech-corpus/).
The code to replicate the creation of the dataset is open and available at the GitHub repository [KBLab/riksdagen_anforanden](https://github.com/kb-labb/riksdagen_anforanden). Processing everything can take 1-3 weeks on a workstation with consumer grade GPU.
#### Who are the source language producers?
The written protocols of speeches are manually produced by the Riksdag. Transcription is not always verbatim, but rather catches the intent of the speaker.
Segmenting speeches to determine when they start and end in a debate was done automatically. Sentence level alignment of the written protocols to the audio files was also done automatically using `aeneas`. See the articles in citation information for more details.
### Annotations
#### Annotation process
The process of aligning speech to written protocols was automatic. It followed the following general steps:
1. We used ASR to automatically transcribe the debate audio files and get word timestamps for the machine generated transcription.
2. We used fuzzy string matching to determine approximate start/end of a speech, matching the official written protocol of the speech to the machine generated transcription of the debate.
3. We perform speaker diarization using pyannote.audio.
4. We assign speaker diarization segments to speeches by the degree of overlap between approximate start/end from fuzzy string matching and the speaker diarization segments. The start and end of the diarization segment is used as our new adjusted start and end metadata of the speech.
5. Based on adjusted metadata of start/end of as speech, we split and extract the audio of speeches from the debates and then align the segmented speeches to the written protocol using `aeneas` (sentence-level alignment).
#### Who are the annotators?
No manual annotations.
### Personal and Sensitive Information
The speakers are members of parliament or ministers speaking publicly in the Riksdag. The Riksdag is a public institution and the speeches are publicly available on the web as open data.
## Considerations for Using the Data
### Social Impact of Dataset
We except the dataset primarily to be used in training ASR models for Swedish. The performance of Swedish text-to-speech in multillingual ASR models may also benefit from the availability of a large Swedish speech corpus. In turn, improved ASR models can serve to help increase accessibility of audio and video media content for people with hearing impairments.
The dataset can also be used to train models for other audio tasks such as speaker diarization, speaker verification, and speaker recognition.
Since metadata regarding the age, gender, and electoral district of the speaker is included, the dataset can possibly also be used to study bias in ASR models.
### Discussion of Biases
The dataset includes parliamentary speeches, which are often more formal than everyday speech.
During the creation of the dataset, we found that speech segmentations based on speaker diarization were more likely to fail when a preceding speaker, the speaker of the house, and the speaker of the following speech were all of the same gender. However, all in all, only a small number of speeches were filtered out of the final RixVox dataset. After quality filtering of the dataset, 5500 out of 5858 hours remained. We do not believe any significant systematic bias was introduced by this filtering.
Only minimal deduplication was performed to weed out commonly repeated phrases. For example, certain phrases such as "Fru talman!", "Herr Talman!", tend to be used a lot as a matter of formality. These phrases tend to be present at the beginning of most transcripts regardless whether it was uttered by the speaker or not. For this reason we have removed the first aligned sentence of each speech when creating RixVox. The aforementioned phrases are repeated frequently in speeches as well, though. As such it might be beneficial to perform more aggressive deduplication of the dataset before training models.
### Other Known Limitations
## Additional Information
### Dataset Curators
KBLab at the the National Library of Sweden.
### Future updates
There is a possiblity RixVox will be periodically, and irregularly, updated by including both older and newer speeches. Older recordings of parliamentary debates from 1966 to 2002 do exist, but they are not yet part of the Riksdag's open data. KBLab are exploring the possibility of adding metadata to these recordings by applying the existing speech segmentation and alignment pipeline to them.
Each year also brings new parliamentary debates, with recent years adding 400-500 hours of speech per year.
### Licensing Information
[CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/)
Cite the Swedish Parliament.
To reference RixVox, feel free to cite KBLab blog posts in the citation information below.
### Citation Information
```
@misc{rekathati2023rixvox:,
author = {Rekathati, Faton},
title = {The KBLab Blog: RixVox: A Swedish Speech Corpus with 5500 Hours of Speech from Parliamentary Debates},
url = {https://kb-labb.github.io/posts/2023-03-09-rixvox-a-swedish-speech-corpus/},
year = {2023}
}
```
```
@misc{rekathati2023finding,
author = {Rekathati, Faton},
title = {The KBLab Blog: Finding Speeches in the Riksdag's Debates},
url = {https://kb-labb.github.io/posts/2023-02-15-finding-speeches-in-the-riksdags-debates/},
year = {2023}
}
```
The Swedish Parliament.
### Contributions
Thanks to [@lhoestq](https://huggingface.co/lhoestq) for reviewing the dataset script. |
true | # Dataset Card for Auditor Sentiment
## 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)
## Dataset Description
Auditor review sentiment collected by News Department
- **Point of Contact:**
Talked to COE for Auditing, currently sue@demo.org
### Dataset Summary
Auditor sentiment dataset of sentences from financial news. The dataset consists of several thousand sentences from English language financial news categorized by sentiment.
### Supported Tasks and Leaderboards
Sentiment Classification
### Languages
English
## Dataset Structure
### Data Instances
```
"sentence": "Pharmaceuticals group Orion Corp reported a fall in its third-quarter earnings that were hit by larger expenditures on R&D and marketing .",
"label": "negative"
```
### Data Fields
- sentence: a tokenized line from the dataset
- label: a label corresponding to the class as a string: 'positive' - (2), 'neutral' - (1), or 'negative' - (0)
### Data Splits
A train/test split was created randomly with a 75/25 split
## Dataset Creation
### Curation Rationale
To gather our auditor evaluations into one dataset. Previous attempts using off-the-shelf sentiment had only 70% F1, this dataset was an attempt to improve upon that performance.
### Source Data
#### Initial Data Collection and Normalization
The corpus used in this paper is made out of English news reports.
#### Who are the source language producers?
The source data was written by various auditors.
### Annotations
#### Annotation process
This release of the auditor reviews covers a collection of 4840
sentences. The selected collection of phrases was annotated by 16 people with
adequate background knowledge on financial markets. The subset here is where inter-annotation agreement was greater than 75%.
#### Who are the annotators?
They were pulled from the SME list, names are held by sue@demo.org
### Personal and Sensitive Information
There is no personal or sensitive information in this dataset.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
All annotators were from the same institution and so interannotator agreement
should be understood with this taken into account.
### Licensing Information
License: Demo.Org Proprietary - DO NOT SHARE
This dataset is based on the [financial phrasebank](https://huggingface.co/datasets/financial_phrasebank) dataset. |
false |
# Habr dataset
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Description](#description)
- [Usage](#usage)
- [Data Instances](#data-instances)
- [Source Data](#source-data)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
## Description
**Summary:** Dataset of posts and comments from [habr.com](https://habr.com/ru/all/), a Russian collaborative blog about IT, computer science and anything related to the Internet.
**Script:** [create_habr.py](https://github.com/IlyaGusev/rulm/blob/master/data_processing/create_habr.py)
**Point of Contact:** [Ilya Gusev](ilya.gusev@phystech.edu)
**Languages:** Russian, English, some programming code.
## Usage
Prerequisites:
```bash
pip install datasets zstandard jsonlines pysimdjson
```
Dataset iteration:
```python
from datasets import load_dataset
dataset = load_dataset('IlyaGusev/habr', split="train", streaming=True)
for example in dataset:
print(example["text_markdown"])
```
## Data Instances
```
{
"id": 12730,
"language": "ru",
"url": "https://habr.com/ru/post/12730/",
"text_markdown": "...",
"text_html": "...",
"lead_markdown": "...",
"lead_html": "...",
"type": "article",
"labels": [],
"original_author": null,
"original_url": null,
"time_published": 1185962380,
"author": "...",
"title": "Хочешь в университет — сделай презентацию",
"statistics": {
"commentsCount": 23,
"favoritesCount": 1,
"readingCount": 1542,
"score": 7,
"votesCount": 15,
"votesCountPlus": 11,
"votesCountMinus": 4
},
"hubs": [
"itcompanies"
],
"flows": [
"popsci"
],
"tags": [
"PowerPoint",
"презентация",
"абитуриенты",
],
"reading_time": 1,
"format": null,
"complexity": null,
"comments": {
"id": [11653537, 11653541],
"parent_id": [null, 11653537],
"level": [0, 1],
"time_published": [1185963192, 1185967886],
"score": [-1, 0],
"votes": [1, 0],
"message_html": ["...", "..."],
"author": ["...", "..."],
"children": [[11653541], []]
}
}
```
You can use this little helper to unflatten sequences:
```python
def revert_flattening(records):
fixed_records = []
for key, values in records.items():
if not fixed_records:
fixed_records = [{} for _ in range(len(values))]
for i, value in enumerate(values):
fixed_records[i][key] = value
return fixed_records
```
The original JSONL is already unflattened.
## Source Data
* The data source is the [Habr](https://habr.com/) website.
* API call example: [post 709430](https://habr.com/kek/v2/articles/709430).
* Processing script is [here](https://github.com/IlyaGusev/rulm/blob/master/data_processing/create_habr.py).
## Personal and Sensitive Information
The dataset is not anonymized, so individuals' names can be found in the dataset. Information about the original authors is included in the dataset where possible.
|
false |
# dolly_hhrlhf-text2text
This is `mosaicml/dolly_hhrlhf` with the following changes:
- clean up/adapt `prompt` column for the `text2text-generation` task (no need for a special template)
- split the original `train` set into a 95% train and an explicit validation set (5%)
- fixed extra spaces in puncuation (as this is not a French dataset)
details on extra spaces:
```
Original sentence 1: How can I be healthy ?
Fixed sentence 1: How can I be healthy?
``` |
false |
# Dataset for evaluation of (zero-shot) recommendation with language models
We showed that pretrained large language models can act as a recommender system, and compare few-shot learning results to matrix factorization baselines.
This is the BIG-Bench version of our language-based movie recommendation dataset.
<https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/movie_recommendation>
GPT-2 has a 48.8% accuracy, chance is 25%.
Human accuracy is 60.4%.
# Citation
```
@InProceedings{sileodreclm22,
author="Sileo, Damien
and Vossen, Wout
and Raymaekers, Robbe",
editor="Hagen, Matthias
and Verberne, Suzan
and Macdonald, Craig
and Seifert, Christin
and Balog, Krisztian
and N{\o}rv{\aa}g, Kjetil
and Setty, Vinay",
title="Zero-Shot Recommendation as Language Modeling",
booktitle="Advances in Information Retrieval",
year="2022",
publisher="Springer International Publishing",
address="Cham",
pages="223--230",
isbn="978-3-030-99739-7"
}
``` |
true | |
false |
# Dataset Card for feature vector embeddings of the 20newsgroup dataset
## 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:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This dataset contains vector embeddings of the [20newsgroups dataset](http://qwone.com/~jason/20Newsgroups/).
The embeddings were created with the [Sentence Transformers library](https://www.sbert.net/index.html) using the `multi-qa-MiniLM-L6-cos-v1` model.
### 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 [@github-username](https://github.com/<github-username>) for adding this dataset. |
false | Новая версия: https://huggingface.co/datasets/Den4ikAI/russian_instructions_2
Русский датасет инструкций и QA.
Структура датасета:
```
{
"dialogue":[
"Как я могу улучшить свою связь между телом и разумом?",
"Начните с разработки регулярной практики осознанности. 2. Обязательно практикуйте баланс на нескольких уровнях: физическом, эмоциональном, умственном и духовном. 3. Свяжитесь с природой, когда это возможно - идите на прогулки или бегайте на улице, или просто сидите в парке и наблюдайте природу вокруг вас. 4. Развивайте позитивные утверждения, которые вы можете использовать, чтобы помочь поддерживать оптимизм и сильные отношения с вашим телом.",
"Больше пожалуйста",
"Конечно, вот еще несколько: 5. Включите здоровую диету цельных продуктов и много воды, которая питает ваш ум и тело. 6. Научитесь быть в гармонии с вашим телом, замечая изменения в том, как вы себя чувствуете, и уделите время, чтобы оценить и решить любые возникающие потребности."
],
"rounds":[
1,
2
],
"uuid":"53e8d08b-1f45-4ef4-b6d8-3a04758cafd8"
}
```
### Citation:
```
@MISC{russian_instructions,
author = {Denis Petrov},
title = {Russian instructions dataset for conversational agents},
url = {https://huggingface.co/datasets/Den4ikAI/russian_instructions},
year = 2023
}
``` |
false |
# Dataset Card for Alpaca Cleaned Dutch
## Dataset Description
- **Homepage:** N/A
- **Repository:** N/A
- **Paper:** N/A
- **Leaderboard:** N/A
- **Point of Contact:** Bram Vanroy
### Dataset Summary
This dataset contains 51,712 conversations between een AI assistant and a (fake) "Human" (generated) in Dutch. They are translations of [Alpaca Cleaned Dataset](https://huggingface.co/datasets/yahma/alpaca-cleaned).
☕ [**Want to help me out?**](https://www.buymeacoffee.com/bramvanroy) Translating the data with the OpenAI API, and prompt testing, cost me 💸$57.99💸. If you like this dataset, please consider [buying me a coffee](https://www.buymeacoffee.com/bramvanroy) to offset a portion of this cost, I appreciate it a lot! ☕
### Languages
- Dutch
## Dataset Structure
### Data Instances
```python
{
'id': 7,
'instruction': 'Leg uit waarom de volgende breuk gelijk is aan 1/4',
'input': '4/16',
'output': 'De breuk 4/16 is gelijk aan 1/4 omdat zowel de teller als de '
'noemer deelbaar zijn door 4. Door zowel de teller als de noemer '
'door 4 te delen, krijgen we de breuk 1/4.'
}
```
### Data Fields
- **id**: the ID of the item. The following ID is not included because they could not be translated: `[23019]`
- **instruction**: the given instruction
**input**: optional input to accompany the instruction. Can be empty.
- **output**: the "answer" to the instruction
## Dataset Creation
The instructions, inputs and outputs were translated with OpenAI's API for `gpt-3.5-turbo`. `max_tokens=1024, temperature=0` as parameters.
The prompt template to translate is (where `src_lang` is English and `tgt_lang` is Dutch):
```python
TRANSLATION_PROMPT = """You are asked to translate a task's instruction, optional input to the task, and the output of the task, from {src_lang} into {tgt_lang}.
Here are the requirements that you should adhere to:
1. maintain the format: the task consists of a task instruction (marked `instruction: `), optional input to the task (marked `input: `) and output for the task marked with `output: `;
2. do not translate the identifiers `instruction: `, `input: `, and `output: ` but instead copy them to your output;
3. make sure that text is fluent to read and does not contain grammatical errors. Use standard {tgt_lang} without regional bias;
4. translate the instruction and input text using informal, but standard, language;
5. make sure to avoid biases (such as gender bias, grammatical bias, social bias);
6. if the instruction is to correct grammar mistakes or spelling mistakes then you have to generate a similar mistake in the input in {tgt_lang}, and then also generate a corrected output version in the output in {tgt_lang};
7. if the instruction is to translate text from one language to another, then you do not translate the text that needs to be translated in the instruction or the input, nor the translation in the output (just copy them as-is);
8. do not translate code fragments but copy them to your output. If there are English examples, variable names or definitions in code fragments, keep them in English.
Now translate the following task with the requirements set out above. Do not provide an explanation and do not add anything else.\n\n"""
```
This prompt is concatenated with the instruction, optionally the input, and the output. In code, that last part looks like this:
```python
text = f'instruction: "{instruction}"\n\n'
if inputstr:
text += f'input: "{inputstr}"\n\n'
text += f'output: "{outputstr}"'
```
The system message was:
```
You are a helpful assistant that translates English to Dutch to the requirements that are given to you.
```
Note that 1 item (0.0001%) was not successfully translated. The translation was missing the input, instruction, or output keywords where those were expected. The ID for the missing item is `[23019]`.
### Source Data
#### Initial Data Collection and Normalization
Initial data creation by [Tatsu lab](https://huggingface.co/datasets/tatsu-lab/alpaca) and cleaned by [Yahma](https://huggingface.co/datasets/yahma/alpaca-cleaned).
#### Who are the source language producers?
The original dataset was generated with OpenAI's `text-davinci-003`.
## Considerations for Using the Data
Note that the translations in this new dataset have not been verified by humans.
### Discussion of Biases
As with any machine-generated texts, users should be aware of potential biases that are included in this dataset. Although the prompt specifically includes `make sure to avoid biases (such as gender bias, grammatical bias, social bias)`, of course the impact of such command is not known. It is likely that biases remain in the dataset so use with caution.
### Other Known Limitations
The translation quality has not been verified. Use at your own risk!
### Licensing Information
As per OpenAI's terms of use, this dataset cannot be used to build [a commercial system that competes with OpenAI's services](https://openai.com/policies/terms-of-use). Similar to the original Alpaca dataset, this dataset is released under CC NC 4.0.
This text was generated (either in part or in full) with GPT-3 (`gpt-3.5-turbo`), OpenAI’s large-scale language-generation model. Upon generating draft language, the author reviewed, edited, and revised the language to their own liking and takes ultimate responsibility for the content of this publication.
If you use this dataset, you must also follow the [Sharing](https://openai.com/policies/sharing-publication-policy) and [Usage](https://openai.com/policies/usage-policies) policies.
As clearly stated in their [Terms of Use](https://openai.com/policies/terms-of-use), specifically 2c.iii, "[you may not] use output from the Services to develop models that compete with OpenAI". That means that you cannot use this dataset to build models that are intended to commercially compete with OpenAI. [As far as I am aware](https://law.stackexchange.com/questions/93308/licensing-material-generated-with-chatgpt), that is a specific restriction that should serve as an addendum to the current license.
### Citation Information
If you use this data set, please cite :
Bram Vanroy. (2023). Alpaca Cleaned Dutch [Data set]. Hugging Face. https://doi.org/10.57967/HF/0530
```bibtex
@misc{https://doi.org/10.57967/hf/0530,
doi = {10.57967/HF/0530},
url = {https://huggingface.co/datasets/BramVanroy/alpaca-cleaned-dutch},
author = {{Bram Vanroy}},
title = {{A}lpaca {C}leaned {D}utch},
publisher = {Hugging Face},
year = {2023}
}
```
### Contributions
Thanks to [Tatsu lab](https://huggingface.co/datasets/tatsu-lab/alpaca) for the initial machine-generated dataset and yahma for [cleaning it](https://huggingface.co/datasets/yahma/alpaca-cleaned). |
false |
## Dataset Description
A segmentation dataset for anime character
My project: [anime-segmentation](https://github.com/SkyTNT/anime-segmentation)
### Dataset Summary
| Dir | Description | Format | Images |
| ---- | ---- | ---- | ---- |
| bg | background images | jpg | 8057 |
| fg | foreground images, transparent background | png | 11802 |
| imgs | real images with background and foreground| jpg | 1111 |
| masks| labels for imgs | jpg | 1111 |
Total size: 18GB
### Collection Method
Collect background from [character_bg_seg_data](https://github.com/ShuhongChen/bizarre-pose-estimator#download)
Collect foreground from danbooru website.
Collect imgs and masks from [AniSeg](https://github.com/jerryli27/AniSeg#about-the-models) and danbooru website.
I use [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) to restore the background images.
I clean the dataset using [DeepDanbooru](https://github.com/KichangKim/DeepDanbooru) first then manually, to make sue all foreground is anime character.
### Contributions
Thanks to [@SkyTNT](https://github.com/SkyTNT) for adding this dataset.
Thanks to [@ShuhongChen](https://github.com/ShuhongChen) for [character_bg_seg_data](https://github.com/ShuhongChen/bizarre-pose-estimator#download)
Thanks to [@jerryli27](https://github.com/jerryli27) for [AniSeg](https://github.com/jerryli27/AniSeg#about-the-models)
|
false |
<div align="center">
<img width="640" alt="keremberke/german-traffic-sign-detection" src="https://huggingface.co/datasets/keremberke/german-traffic-sign-detection/resolve/main/thumbnail.jpg">
</div>
### Dataset Labels
```
['animals', 'construction', 'cycles crossing', 'danger', 'no entry', 'pedestrian crossing', 'school crossing', 'snow', 'stop', 'bend', 'bend left', 'bend right', 'give way', 'go left', 'go left or straight', 'go right', 'go right or straight', 'go straight', 'keep left', 'keep right', 'no overtaking', 'no overtaking -trucks-', 'no traffic both ways', 'no trucks', 'priority at next intersection', 'priority road', 'restriction ends', 'restriction ends -overtaking -trucks--', 'restriction ends -overtaking-', 'restriction ends 80', 'road narrows', 'roundabout', 'slippery road', 'speed limit 100', 'speed limit 120', 'speed limit 20', 'speed limit 30', 'speed limit 50', 'speed limit 60', 'speed limit 70', 'speed limit 80', 'traffic signal', 'uneven road']
```
### Number of Images
```json
{'test': 54, 'valid': 108, 'train': 383}
```
### How to Use
- Install [datasets](https://pypi.org/project/datasets/):
```bash
pip install datasets
```
- Load the dataset:
```python
from datasets import load_dataset
ds = load_dataset("keremberke/german-traffic-sign-detection", name="full")
example = ds['train'][0]
```
### Roboflow Dataset Page
[https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark/dataset/1](https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark/dataset/1?ref=roboflow2huggingface)
### Citation
```
@misc{ gtsdb---german-traffic-sign-detection-benchmark_dataset,
title = { GTSDB - German Traffic Sign Detection Benchmark Dataset },
type = { Open Source Dataset },
author = { Mohamed Traore },
howpublished = { \\url{ https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark } },
url = { https://universe.roboflow.com/mohamed-traore-2ekkp/gtsdb---german-traffic-sign-detection-benchmark },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { jul },
note = { visited on 2023-01-16 },
}
```
### License
CC BY 4.0
### Dataset Summary
This dataset was exported via roboflow.com on January 16, 2023 at 9:04 PM GMT
Roboflow is an end-to-end computer vision platform that helps you
* collaborate with your team on computer vision projects
* collect & organize images
* understand and search unstructured image data
* annotate, and create datasets
* export, train, and deploy computer vision models
* use active learning to improve your dataset over time
For state of the art Computer Vision training notebooks you can use with this dataset,
visit https://github.com/roboflow/notebooks
To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com
The dataset includes 545 images.
Signs are annotated in COCO format.
The following pre-processing was applied to each image:
* Auto-orientation of pixel data (with EXIF-orientation stripping)
No image augmentation techniques were applied.
|
false |
# Dataset Card
- **Homepage:** https://bit.ly/ischool-berkeley-capstone
- **Repository:** https://github.com/daniel-furman/Capstone
- **Point of Contact:** daniel_furman@berkeley.edu
## Dataset Summary
This is the dataset for **Polyglot or Not?: Measuring Multilingual Encyclopedic Knowledge Retrieval from Foundation Language Models**.
## Test Description
Given a factual association such as *The capital of France is **Paris***, we determine whether a model adequately "knows" this information with the following test:
* Step **1**: prompt the model to predict the likelihood of the token **Paris** following *The Capital of France is*
* Step **2**: prompt the model to predict the average likelihood of a set of false, counterfactual tokens following the same stem.
If the value from **1** is greater than the value from **2** we conclude that model adequately recalls that fact. Formally, this is an application of the Contrastive Knowledge Assessment proposed in [[1][bib]].
For every foundation model of interest (like [LLaMA](https://arxiv.org/abs/2302.13971)), we perform this assessment on a set of facts translated into 20 languages. All told, we score foundation models on 303k fact-completions ([results](https://github.com/daniel-furman/capstone#multilingual-fact-completion-results)).
We also score monolingual models (like [GPT-2](https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf)) on English-only fact-completion ([results](https://github.com/daniel-furman/capstone#english-fact-completion-results)).
## Languages
The dataset covers 20 languages, which use either the Latin or Cyrillic scripts: bg, ca, cs, da, de, en, es, fr, hr, hu, it,
nl, pl, pt, ro, ru, sl, sr, sv, uk.
## Data Splits
The dataset splits correspond to the 20 languages above.
## Source Data
We sourced the English cut of the dataset from [1] and [2] and used the Google Translate API to produce the other 19 language cuts.
## Licensing Information
The dataset is licensed under the Apache 2.0 license and may be used with the corresponding affordances without limit.
## Citation Information
```
@misc{schott2023polyglot,
doi = {10.48550/arXiv.2305.13675},
title={Polyglot or Not? Measuring Multilingual Encyclopedic Knowledge Retrieval from Foundation Language Models},
author={Tim Schott and Daniel Furman and Shreshta Bhat},
year={2023},
eprint={2305.13675,
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## Bibliography
[1] Dong, Qingxiu, Damai Dai, Yifan Song, Jingjing Xu, Zhifang Sui, and Lei Li. "Calibrating Factual Knowledge in Pretrained Language Models". In Findings of the Association for Computational Linguistics: EMNLP 2022. [arXiv:2210.03329][cka] (2022).
```
@misc{dong2022calibrating,
doi = {10.48550/arXiv.2210.03329},
title={Calibrating Factual Knowledge in Pretrained Language Models},
author={Qingxiu Dong and Damai Dai and Yifan Song and Jingjing Xu and Zhifang Sui and Lei Li},
year={2022},
eprint={2210.03329},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
[2] Meng, Kevin, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, and David Bau. "Mass Editing Memory in a Transformer." arXiv preprint [arXiv:2210.07229][memit] (2022).
```
@misc{meng2022massediting,
doi = {10.48550/arXiv.2210.07229},
title={Mass-Editing Memory in a Transformer},
author={Kevin Meng and Arnab Sen Sharma and Alex Andonian and Yonatan Belinkov and David Bau},
year={2022},
eprint={2210.07229},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
false | # Dataset Card for Dataset Name
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
Lev Muchnik, lev.muchnik@mail.huji.ac.il
### Dataset Summary
This dataset represents a 2022 snapshot of the Supreme Court of Israel public verdicts and decisions supported by rich metadata. The 5.31GB dataset represents 751,194 documents.
Overall, the dataset contains 2.68 Gb of text.
It can be loaded with the dataset package:
```
import datasets
data = datasets.load_dataset('LevMuchnik/SupremeCourtOfIsrael')
```
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The vast majority of the documents in the database are in Hebrew. A small number of documents are in English.
## Dataset Structure
The dataset is a json lines file with each line corresponding to a single document and containing document identification, text and metadata.
### Data Instances
[More Information Needed]
### Data Fields
The file contains the following fields:
- case_id - running number for cases
- download_time - when the document was downloaded (datetime)
- number_of_case_documents - number of documents in the current case
- file_name - full name of the document file, including relative path
- Id - document id
- CaseId - case id
- VerdictDt - Date of the document (datetime)
- CreatedDate - Date of when the document was inserted into the Supreme Court database
- CaseNum - case number
- CaseDesc - Unique case identifier. This id is used to reference cases within the Israeli legal system
- Pages - number of pages in the original document
- Path - relative path to the document
- CaseName - formal name of the case
- FileName - document file name, without path
- DocName -document file name, without path
- Year - document creation year
- TypeCode - enumeration of document types (see Type field below)
- Type - Document type
- פסק-דין 84339
- החלטה 663099
- צו ביניים 22
- פסקי דין באנגלית 310
- צו על תנאי 200
- צו 2606
- פד"י 302
- תקצירים 316
- Technical - boolean indicator of whether the document is technical or not.
- CodeVolume - ?
- document_hash - 258-bit hashtag of the document name. Used internally to uniquely identify the document
- text - text of the document. Multiple newlines and other document formating elements (paragraphs,lists, etc.) are preserved.
- html_title - document title extracted from the HTML
- VerdictsDt - date of the verdict
- meta_case_nm - formal case name,
- meta_sec_appeal - integer or None
- meta_side_ty - case type, list of strings
- meta_verdict_file_nm - name of the verdict file
- meta_judge - list of names of the cases judges
- meta_mador_nm - name of the court instance (e.g. בג"ץ)
- meta_side_nm - list of the case parties, list of strings
- meta_verdict_dt - date of the verdict
- meta_case_dt - date of the case
- meta_verdict_nbr -
- meta_ProgId - name of the software used to create the document (None, Word, etc)
- meta_is_technical - whether the document is technical, {'false', 'true'}
- meta_judge_nm_last - last names of the judges (list of strings)
- meta_case_nbr - formal number of the case (same as CaseDesc)
- meta_verdict_ty - type of the decision (same as Type)
- meta_lawyer_nm - list of lawyer names, list of strings or None
- meta_judge_nm_first - list of judges' first names, list of strings
- meta_verdict_pages - number of document cases
- meta_inyan_nm - court בג"ץ
- meta_court_nm - court (e.g. בית המשפט העליון )
### Data Splits
The entire dataset is qualified as 'train'.
## Dataset Creation
2023-04-22
### Curation Rationale
[More Information Needed]
### Source Data
https://supreme.court.gov.il/
#### Initial Data Collection and Normalization
The data was colleted by crawling the Israeli Supreme Court website.
#### 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 data contained in this dataset is public.
## 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
Prof. Lev Muchnik, Hebrew University of Jerusalem
Dr. Inbal Yahav Shenberger, Tel Aviv University
### Licensing Information
[More Information Needed]
### Citation Information
Lev Muchnik, Inbal Yahav, Ariel Nevo, Avichay Chriqui, Tim Shektov, 2023, The Israeli Supreme Court Dataset
### Contributions
The authours would like to thank the Israeli Innovation Authority (grants #78560 and #78561) for their support in creating of this dataset. |
false |
# Dataset Card for BEIR Benchmark
## 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/UKPLab/beir
- **Repository:** https://github.com/UKPLab/beir
- **Paper:** https://openreview.net/forum?id=wCu6T5xFjeJ
- **Leaderboard:** https://docs.google.com/spreadsheets/d/1L8aACyPaXrL8iEelJLGqlMqXKPX2oSP_R10pZoy77Ns
- **Point of Contact:** nandan.thakur@uwaterloo.ca
### Dataset Summary
BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:
- Fact-checking: [FEVER](http://fever.ai), [Climate-FEVER](http://climatefever.ai), [SciFact](https://github.com/allenai/scifact)
- Question-Answering: [NQ](https://ai.google.com/research/NaturalQuestions), [HotpotQA](https://hotpotqa.github.io), [FiQA-2018](https://sites.google.com/view/fiqa/)
- Bio-Medical IR: [TREC-COVID](https://ir.nist.gov/covidSubmit/index.html), [BioASQ](http://bioasq.org), [NFCorpus](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)
- News Retrieval: [TREC-NEWS](https://trec.nist.gov/data/news2019.html), [Robust04](https://trec.nist.gov/data/robust/04.guidelines.html)
- Argument Retrieval: [Touche-2020](https://webis.de/events/touche-20/shared-task-1.html), [ArguAna](tp://argumentation.bplaced.net/arguana/data)
- Duplicate Question Retrieval: [Quora](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs), [CqaDupstack](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)
- Citation-Prediction: [SCIDOCS](https://allenai.org/data/scidocs)
- Tweet Retrieval: [Signal-1M](https://research.signal-ai.com/datasets/signal1m-tweetir.html)
- Entity Retrieval: [DBPedia](https://github.com/iai-group/DBpedia-Entity/)
All these datasets have been preprocessed and can be used for your experiments.
```python
```
### Supported Tasks and Leaderboards
The dataset supports a leaderboard that evaluates models against task-specific metrics such as F1 or EM, as well as their ability to retrieve supporting information from Wikipedia.
The current best performing models can be found [here](https://eval.ai/web/challenges/challenge-page/689/leaderboard/).
### Languages
All tasks are in English (`en`).
## Dataset Structure
All BEIR datasets must contain a corpus, queries and qrels (relevance judgments file). They must be in the following format:
- `corpus` file: a `.jsonl` file (jsonlines) that contains a list of dictionaries, each with three fields `_id` with unique document identifier, `title` with document title (optional) and `text` with document paragraph or passage. For example: `{"_id": "doc1", "title": "Albert Einstein", "text": "Albert Einstein was a German-born...."}`
- `queries` file: a `.jsonl` file (jsonlines) that contains a list of dictionaries, each with two fields `_id` with unique query identifier and `text` with query text. For example: `{"_id": "q1", "text": "Who developed the mass-energy equivalence formula?"}`
- `qrels` file: a `.tsv` file (tab-seperated) that contains three columns, i.e. the `query-id`, `corpus-id` and `score` in this order. Keep 1st row as header. For example: `q1 doc1 1`
### Data Instances
A high level example of any beir dataset:
```python
corpus = {
"doc1" : {
"title": "Albert Einstein",
"text": "Albert Einstein was a German-born theoretical physicist. who developed the theory of relativity, \
one of the two pillars of modern physics (alongside quantum mechanics). His work is also known for \
its influence on the philosophy of science. He is best known to the general public for his mass–energy \
equivalence formula E = mc2, which has been dubbed 'the world's most famous equation'. He received the 1921 \
Nobel Prize in Physics 'for his services to theoretical physics, and especially for his discovery of the law \
of the photoelectric effect', a pivotal step in the development of quantum theory."
},
"doc2" : {
"title": "", # Keep title an empty string if not present
"text": "Wheat beer is a top-fermented beer which is brewed with a large proportion of wheat relative to the amount of \
malted barley. The two main varieties are German Weißbier and Belgian witbier; other types include Lambic (made\
with wild yeast), Berliner Weisse (a cloudy, sour beer), and Gose (a sour, salty beer)."
},
}
queries = {
"q1" : "Who developed the mass-energy equivalence formula?",
"q2" : "Which beer is brewed with a large proportion of wheat?"
}
qrels = {
"q1" : {"doc1": 1},
"q2" : {"doc2": 1},
}
```
### Data Fields
Examples from all configurations have the following features:
### Corpus
- `corpus`: a `dict` feature representing the document title and passage text, made up of:
- `_id`: a `string` feature representing the unique document id
- `title`: a `string` feature, denoting the title of the document.
- `text`: a `string` feature, denoting the text of the document.
### Queries
- `queries`: a `dict` feature representing the query, made up of:
- `_id`: a `string` feature representing the unique query id
- `text`: a `string` feature, denoting the text of the query.
### Qrels
- `qrels`: a `dict` feature representing the query document relevance judgements, made up of:
- `_id`: a `string` feature representing the query id
- `_id`: a `string` feature, denoting the document id.
- `score`: a `int32` feature, denoting the relevance judgement between query and document.
### Data Splits
| Dataset | Website| BEIR-Name | Type | Queries | Corpus | Rel D/Q | Down-load | md5 |
| -------- | -----| ---------| --------- | ----------- | ---------| ---------| :----------: | :------:|
| MSMARCO | [Homepage](https://microsoft.github.io/msmarco/)| ``msmarco`` | ``train``<br>``dev``<br>``test``| 6,980 | 8.84M | 1.1 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/msmarco.zip) | ``444067daf65d982533ea17ebd59501e4`` |
| TREC-COVID | [Homepage](https://ir.nist.gov/covidSubmit/index.html)| ``trec-covid``| ``test``| 50| 171K| 493.5 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/trec-covid.zip) | ``ce62140cb23feb9becf6270d0d1fe6d1`` |
| NFCorpus | [Homepage](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/) | ``nfcorpus`` | ``train``<br>``dev``<br>``test``| 323 | 3.6K | 38.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nfcorpus.zip) | ``a89dba18a62ef92f7d323ec890a0d38d`` |
| BioASQ | [Homepage](http://bioasq.org) | ``bioasq``| ``train``<br>``test`` | 500 | 14.91M | 8.05 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#2-bioasq) |
| NQ | [Homepage](https://ai.google.com/research/NaturalQuestions) | ``nq``| ``train``<br>``test``| 3,452 | 2.68M | 1.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nq.zip) | ``d4d3d2e48787a744b6f6e691ff534307`` |
| HotpotQA | [Homepage](https://hotpotqa.github.io) | ``hotpotqa``| ``train``<br>``dev``<br>``test``| 7,405 | 5.23M | 2.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/hotpotqa.zip) | ``f412724f78b0d91183a0e86805e16114`` |
| FiQA-2018 | [Homepage](https://sites.google.com/view/fiqa/) | ``fiqa`` | ``train``<br>``dev``<br>``test``| 648 | 57K | 2.6 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fiqa.zip) | ``17918ed23cd04fb15047f73e6c3bd9d9`` |
| Signal-1M(RT) | [Homepage](https://research.signal-ai.com/datasets/signal1m-tweetir.html)| ``signal1m`` | ``test``| 97 | 2.86M | 19.6 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#4-signal-1m) |
| TREC-NEWS | [Homepage](https://trec.nist.gov/data/news2019.html) | ``trec-news`` | ``test``| 57 | 595K | 19.6 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#1-trec-news) |
| ArguAna | [Homepage](http://argumentation.bplaced.net/arguana/data) | ``arguana``| ``test`` | 1,406 | 8.67K | 1.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/arguana.zip) | ``8ad3e3c2a5867cdced806d6503f29b99`` |
| Touche-2020| [Homepage](https://webis.de/events/touche-20/shared-task-1.html) | ``webis-touche2020``| ``test``| 49 | 382K | 19.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/webis-touche2020.zip) | ``46f650ba5a527fc69e0a6521c5a23563`` |
| CQADupstack| [Homepage](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/) | ``cqadupstack``| ``test``| 13,145 | 457K | 1.4 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/cqadupstack.zip) | ``4e41456d7df8ee7760a7f866133bda78`` |
| Quora| [Homepage](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs) | ``quora``| ``dev``<br>``test``| 10,000 | 523K | 1.6 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/quora.zip) | ``18fb154900ba42a600f84b839c173167`` |
| DBPedia | [Homepage](https://github.com/iai-group/DBpedia-Entity/) | ``dbpedia-entity``| ``dev``<br>``test``| 400 | 4.63M | 38.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/dbpedia-entity.zip) | ``c2a39eb420a3164af735795df012ac2c`` |
| SCIDOCS| [Homepage](https://allenai.org/data/scidocs) | ``scidocs``| ``test``| 1,000 | 25K | 4.9 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scidocs.zip) | ``38121350fc3a4d2f48850f6aff52e4a9`` |
| FEVER | [Homepage](http://fever.ai) | ``fever``| ``train``<br>``dev``<br>``test``| 6,666 | 5.42M | 1.2| [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fever.zip) | ``5a818580227bfb4b35bb6fa46d9b6c03`` |
| Climate-FEVER| [Homepage](http://climatefever.ai) | ``climate-fever``|``test``| 1,535 | 5.42M | 3.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/climate-fever.zip) | ``8b66f0a9126c521bae2bde127b4dc99d`` |
| SciFact| [Homepage](https://github.com/allenai/scifact) | ``scifact``| ``train``<br>``test``| 300 | 5K | 1.1 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scifact.zip) | ``5f7d1de60b170fc8027bb7898e2efca1`` |
| Robust04 | [Homepage](https://trec.nist.gov/data/robust/04.guidelines.html) | ``robust04``| ``test``| 249 | 528K | 69.9 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#3-robust04) |
## 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
[Needs More Information]
### Citation Information
Cite as:
```
@inproceedings{
thakur2021beir,
title={{BEIR}: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models},
author={Nandan Thakur and Nils Reimers and Andreas R{\"u}ckl{\'e} and Abhishek Srivastava and Iryna Gurevych},
booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
year={2021},
url={https://openreview.net/forum?id=wCu6T5xFjeJ}
}
```
### Contributions
Thanks to [@Nthakur20](https://github.com/Nthakur20) for adding this dataset. |
true | # [TRIP - Tiered Reasoning for Intuitive Physics](https://aclanthology.org/2021.findings-emnlp.422/)
Official dataset for [Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding](https://aclanthology.org/2021.findings-emnlp.422/). Shane Storks, Qiaozi Gao, Yichi Zhang, Joyce Chai. EMNLP Findings, 2021.
For our official model and experiment code, please check [GitHub](https://github.com/sled-group/Verifiable-Coherent-NLU).
## Overview
We introduce Tiered Reasoning for Intuitive Physics (TRIP), a novel commonsense reasoning dataset with dense annotations that enable multi-tiered evaluation of machines’ reasoning process.
It includes dense annotations for each story capturing multiple tiers of reasoning beyond the end task. From these annotations, we propose a tiered evaluation, where given a pair of highly similar stories (differing only by one sentence which makes one of the stories implausible), systems must jointly identify (1) the plausible story, (2) a pair of conflicting sentences in the implausible story, and (3) the underlying physical states in those sentences causing the conflict. The goal of TRIP is to enable a systematic evaluation of machine coherence toward the end task prediction of plausibility. In particular, we evaluate whether a high-level plausibility prediction can be verified based on lower-level understanding, for example, physical state changes that would support the prediction.
## Download
```python
from datasets import load_dataset
dataset = load_dataset("sled-umich/TRIP")
```
* [HuggingFace-Dataset](https://huggingface.co/datasets/sled-umich/TRIP)
* [GitHub](https://github.com/sled-group/Verifiable-Coherent-NLU)
## Cite
```bibtex
@misc{storks2021tiered,
title={Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding},
author={Shane Storks and Qiaozi Gao and Yichi Zhang and Joyce Chai},
year={2021},
booktitle={Findings of the Association for Computational Linguistics: EMNLP 2021},
location={Punta Cana, Dominican Republic},
publisher={Association for Computational Linguistics},
}
```
|
false | This is a repreprocessed version of [P3](https://huggingface.co/datasets/bigscience/P3) with any updates that have been made to the P3 datasets since the release of the original P3. It is used for the finetuning of [bloomz-p3](https://huggingface.co/bigscience/bloomz-p3) & [mt0-xxl-p3](https://huggingface.co/bigscience/mt0-xxl-p3). The script is available [here](https://github.com/bigscience-workshop/bigscience/blob/638e66e40395dbfab9fa08a662d43b317fb2eb38/data/p3/prepare_p3.py).
|
true |
# Dataset Card for "LowerCourtInsertionSwissJudgmentPrediction": An implementation of lower court insertion bias analysis for Swiss judgment prediction
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Summary](#dataset-summary)
- [Documents](#documents)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset **str**ucture](#dataset-**str**ucture)
- [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)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Summary
This dataset contains an implementation of lower-court-insertion for the SwissJudgmentPrediction task.
Note that this dataset only provides a test set and should be used in comination with the [Swiss-Judgment-Prediction](https://huggingface.co/datasets/swiss_judgment_prediction) dataset.
### Documents
Lower-Court-Insertion-Swiss-Judgment-Prediction is a subset of the [Swiss-Judgment-Prediction](https://huggingface.co/datasets/swiss_judgment_prediction) dataset.
The Swiss-Judgment-Prediction dataset is a multilingual, diachronic dataset of 85K Swiss Federal Supreme Court (FSCS) cases annotated with the respective binarized judgment outcome (approval/dismissal), the publication year, the legal area and the canton of origin per case. Lower-Court-Insertion-Swiss-Judgment-Prediction extends this dataset by adding lower court insertion.
### Supported Tasks and Leaderboards
LowerCourtInsertionSwissJudgmentPrediction can be used for performing the LowerCourtInsertion in the legal judgment prediction task.
### Languages
Switzerland has four official languages with 3 languages (German, French and Italian) being represented in more than 1000 Swiss Federal Supreme court decisions. The decisions are written by the judges and clerks in the language of the proceedings.
## Dataset structure
### Data Instances
#### Multilingual use of the dataset
When the dataset is used in a multilingual setting selecting the the 'all' flag:
```python
from datasets import load_dataset
dataset = load_dataset('rcds/lower_court_insertion_swiss_judgment_prediction', 'all')
```
#### Monolingual use of the dataset
When the dataset is used in a monolingual setting selecting the ISO language code for one of the 3 supported languages. For example:
```python
from datasets import load_dataset
dataset = load_dataset('rcds/lower-court-insertion_swiss_judgment_prediction', 'de')
```
### Data Fields
The following data fields are provided for documents (test):
id: (**int**) a unique identifier of the for the document<br/>
year: (**int**) the publication year<br/>
label: (**str**) the judgment outcome: dismissal or approval<br/>
language: (**str**) one of (de, fr, it)<br/>
region: (**str**) the region of the lower court<br/>
canton: (**str**) the canton of the lower court<br/>
legal area: (**str**) the legal area of the case<br/>
explainability_label: (**str**) the explainability label assigned to the occluded text: (Lower court, Baseline)<br/>
text: (**str**) the facts of the case w/o the occluded text except for cases w/ explainability label "Baseline" (contain entire facts)<br/>
lower_court: (**str**) the inserted lower_court (for Baseline there is no insertion)<br/>
### Data Splits (Including Swiss Judgment Prediction)
Language | Subset | Number of Rows (Test)
|-----|-----|------|
German| de| __378__
French | fr| __414__
Italian | it| __335__
All | all | __1127__
Language | Subset | Number of Documents (Test)
| ----------- | ----------- | ----------- |
German| de | __38__
French | fr | __36__
Italian | it | __34__
All | all | __108__
## Dataset Creation
### Curation Rationale
The dataset was curated by Niklaus et al. (2021) and Nina Baumgartner.
### Source Data
#### Initial Data Collection and Normalization
The original data are available at the Swiss Federal Supreme Court (https://www.bger.ch) in unprocessed formats (HTML). The documents were downloaded from the Entscheidsuche portal (https://entscheidsuche.ch) in HTML.
#### Who are the source language producers?
Switzerland has four official languages with 3 languages (German, French and Italian) being represented in more than 1000 Swiss Federal Supreme court decisions. The decisions are written by the judges and clerks in the language of the proceedings.
### Annotations
#### Annotation process
The decisions have been annotated with the binarized judgment outcome using parsers and regular expressions. In addition the a subset of the test set (27 cases in German, 24 in French and 23 in Italian spanning over the years 2017 an 20200) was annotated by legal experts with the lower court. These lower court annotations were then use the insert each lower court into each case once (instead of the original lower court). Allowing an analysis of the changes in the models performance for each inserted lower court, giving insight into a possible bias among them. The legal expert annotation were conducted from April 2020 to August 2020.
#### Who are the annotators?
Joel Niklaus and Adrian Jörg annotated the binarized judgment outcomes. Metadata is published by the Swiss Federal Supreme Court (https://www.bger.ch). The group of legal experts consists of Thomas Lüthi (lawyer), Lynn Grau (law student at master's level) and Angela Stefanelli (law student at master's level).
### Personal and Sensitive Information
The dataset contains publicly available court decisions from the Swiss Federal Supreme Court. Personal or sensitive information has been anonymized by the court before publication according to the following guidelines: https://www.bger.ch/home/juridiction/anonymisierungsregeln.html.
## Additional Information
### Dataset Curators
Niklaus et al. (2021) and Nina Baumgartner
### Licensing Information
We release the data under CC-BY-4.0 which complies with the court licensing (https://www.bger.ch/files/live/sites/bger/files/pdf/de/urteilsveroeffentlichung_d.pdf)
© Swiss Federal Supreme Court, 2000-2020
The copyright for the editorial content of this website and the consolidated texts, which is owned by the Swiss Federal Supreme Court, is licensed under the Creative Commons Attribution 4.0 International licence. This means that you can re-use the content provided you acknowledge the source and indicate any changes you have made.
Source: https://www.bger.ch/files/live/sites/bger/files/pdf/de/urteilsveroeffentlichung_d.pdf
### Citation Information
```
@misc{baumgartner_nina_occlusion_2019,
title = {From Occlusion to Transparancy – An Occlusion-Based Explainability Approach for Legal Judgment Prediction in Switzerland},
shorttitle = {From Occlusion to Transparancy},
abstract = {Natural Language Processing ({NLP}) models have been used for more and more complex tasks such as Legal Judgment Prediction ({LJP}). A {LJP} model predicts the outcome of a legal case by utilizing its facts. This increasing deployment of Artificial Intelligence ({AI}) in high-stakes domains such as law and the involvement of sensitive data has increased the need for understanding such systems. We propose a multilingual occlusion-based explainability approach for {LJP} in Switzerland and conduct a study on the bias using Lower Court Insertion ({LCI}). We evaluate our results using different explainability metrics introduced in this thesis and by comparing them to high-quality Legal Expert Annotations using Inter Annotator Agreement. Our findings show that the model has a varying understanding of the semantic meaning and context of the facts section, and struggles to distinguish between legally relevant and irrelevant sentences. We also found that the insertion of a different lower court can have an effect on the prediction, but observed no distinct effects based on legal areas, cantons, or regions. However, we did identify a language disparity with Italian performing worse than the other languages due to representation inequality in the training data, which could lead to potential biases in the prediction in multilingual regions of Switzerland. Our results highlight the challenges and limitations of using {NLP} in the judicial field and the importance of addressing concerns about fairness, transparency, and potential bias in the development and use of {NLP} systems. The use of explainable artificial intelligence ({XAI}) techniques, such as occlusion and {LCI}, can help provide insight into the decision-making processes of {NLP} systems and identify areas for improvement. Finally, we identify areas for future research and development in this field in order to address the remaining limitations and challenges.},
author = {{Baumgartner, Nina}},
year = {2022},
langid = {english}
}
```
### Contributions
Thanks to [@ninabaumgartner](https://github.com/ninabaumgartner) for adding this dataset.
|
false | # Dataset Card for "ms-marco-es-500k"
QA asymmetric Spanish dataset filtered from [multilingual version of MS Marco](https://huggingface.co/datasets/unicamp-dl/mmarco) and sampled on 500k rows.
```python
import datasets
ms_marco_es = datasets.load_dataset('unicamp-dl/mmarco', name='spanish', split='train')
ms_marco_es.select(range(500_000)).push_to_hub("dariolopez/ms-marco-es-500k", token=os.environ['hg_token'])
``` |
true |
# Dataset Card for "many_emotions"
## Dataset Description
- **Homepage:**
### Dataset Summary
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
The data fields are:
- `id`: unique identifier
- `text`: a `string` feature.
- `label`: a classification label, with possible values including `anger` (0), `fear` (1), `joy` (2), `love` (
3), `sadness` (4), `surprise` (5), `neutral` (6).
- `license`: inherited license from source dataset
- `dataset`: source dataset
- `language`: text language
### Data Splits
The dataset has 2 configurations:
- raw: with 5 configuration for each language
- split: with configurations train, validation, test
## Dataset Creation
### Curation Rationale
The raw split contains duplicates.
In the split "split" there may be equal rows but with different label.
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
## Additional Information
### Licensing Information
Each row has its own license which is inherited from the source dataset. |
false |
# Preprocessed SemEval-2010 Benchmark dataset for Keyphrase Generation
## About
SemEval-2010 is a dataset for benchmarking keyphrase extraction and generation models.
The dataset is composed of 244 **full-text** scientific papers collected from the [ACM Digital Library](https://dl.acm.org/).
Keyphrases were annotated by readers and combined with those provided by the authors.
Details about the SemEval-2010 dataset can be found in the original paper [(kim et al., 2010)][kim-2010].
This version of the dataset was produced by [(Boudin et al., 2016)][boudin-2016] and provides four increasingly sophisticated levels of document preprocessing:
* `lvl-1`: default text files provided by the SemEval-2010 organizers.
* `lvl-2`: for each file, we manually retrieved the original PDF file from the ACM Digital Library.
We then extract the enriched textual content of the PDF files using an Optical Character Recognition (OCR) system and perform document logical structure detection using ParsCit v110505.
We use the detected logical structure to remove author-assigned keyphrases and select only relevant elements : title, headers, abstract, introduction, related work, body text and conclusion.
We finally apply a systematic dehyphenation at line breaks.s
* `lvl-3`: we further abridge the input text from level 2 preprocessed documents to the following: title, headers, abstract, introduction, related work, background and conclusion.
* `lvl-4`: we abridge the input text from level 3 preprocessed documents using an unsupervised summarization technique.
We keep the title and abstract and select the most content bearing sentences from the remaining contents.
Titles and abstracts, collected from the [SciCorefCorpus](https://github.com/melsk125/SciCorefCorpus), are also provided.
Details about how they were extracted and cleaned up can be found in [(Chaimongkol et al., 2014)][chaimongkol-2014].
Reference keyphrases are provided in stemmed form (because they were provided like this for the test split in the competition).
They are also categorized under the PRMU (<u>P</u>resent-<u>R</u>eordered-<u>M</u>ixed-<u>U</u>nseen) scheme as proposed in [(Boudin and Gallina, 2021)][boudin-2021].
Text pre-processing (tokenization) is carried out using `spacy` (`en_core_web_sm` model) with a special rule to avoid splitting words with hyphens (e.g. graph-based is kept as one token).
Stemming (Porter's stemmer implementation provided in `nltk`) is applied before reference keyphrases are matched against the source text.
Details about the process can be found in `prmu.py`.
The <u>P</u>resent reference keyphrases are also ordered by their order of apparition in the concatenation of title and text (lvl-1).
## Content and statistics
The dataset is divided into the following two splits:
| Split | # documents | #words | # keyphrases | % Present | % Reordered | % Mixed | % Unseen |
| :--------- |------------:|-------:|-------------:|----------:|------------:|--------:|---------:|
| Train | 144 | 184.6 | 15.44 | 42.16 | 7.36 | 26.85 | 23.63 |
| Test | 100 | 203.1 | 14.66 | 40.11 | 8.34 | 27.12 | 24.43 |
Statistics (#words, PRMU distributions) are computed using the title/abstract and not the full text of scientific papers.
The following data fields are available :
- **id**: unique identifier of the document.
- **title**: title of the document.
- **abstract**: abstract of the document.
- **lvl-1**: content of the document with no text processing.
- **lvl-2**: content of the document retrieved from original PDF files and cleaned up.
- **lvl-3**: content of the document further abridged to relevant sections.
- **lvl-4**: content of the document further abridged using an unsupervised summarization technique.
- **keyphrases**: list of reference keyphrases.
- **prmu**: list of <u>P</u>resent-<u>R</u>eordered-<u>M</u>ixed-<u>U</u>nseen categories for reference keyphrases.
## References
- (Kim et al., 2010) Su Nam Kim, Olena Medelyan, Min-Yen Kan, and Timothy Baldwin. 2010.
[SemEval-2010 Task 5 : Automatic Keyphrase Extraction from Scientific Articles][kim-2010].
In Proceedings of the 5th International Workshop on Semantic Evaluation, pages 21–26, Uppsala, Sweden. Association for Computational Linguistics.
- (Chaimongkol et al., 2014) Panot Chaimongkol, Akiko Aizawa, and Yuka Tateisi. 2014.
[Corpus for Coreference Resolution on Scientific Papers][chaimongkol-2014].
In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3187–3190, Reykjavik, Iceland. European Language Resources Association (ELRA).
- (Boudin et al., 2016) Florian Boudin, Hugo Mougard, and Damien Cram. 2016.
[How Document Pre-processing affects Keyphrase Extraction Performance][boudin-2016].
In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pages 121–128, Osaka, Japan. The COLING 2016 Organizing Committee.
- (Boudin and Gallina, 2021) Florian Boudin and Ygor Gallina. 2021.
[Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness][boudin-2021].
In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4185–4193, Online. Association for Computational Linguistics.
[kim-2010]: https://aclanthology.org/S10-1004/
[chaimongkol-2014]: https://aclanthology.org/L14-1259/
[boudin-2016]: https://aclanthology.org/W16-3917/
[boudin-2021]: https://aclanthology.org/2021.naacl-main.330/
|
false |
# WCEP10 dataset for summarization
Summarization dataset copied from [PRIMERA](https://github.com/allenai/PRIMER)
This dataset is compatible with the [`run_summarization.py`](https://github.com/huggingface/transformers/tree/master/examples/pytorch/summarization) script from Transformers if you add this line to the `summarization_name_mapping` variable:
```python
"ccdv/WCEP-10": ("document", "summary")
```
# Configs
4 possibles configs:
- `roberta` will concatenate documents with "\</s\>" (default)
- `newline` will concatenate documents with "\n"
- `bert` will concatenate documents with "[SEP]"
- `list` will return the list of documents instead of a string
### Data Fields
- `id`: paper id
- `document`: a string/list containing the body of a set of documents
- `summary`: a string containing the abstract of the set
### Data Splits
This dataset has 3 splits: _train_, _validation_, and _test_. \
| Dataset Split | Number of Instances |
| ------------- | --------------------|
| Train | 8158 |
| Validation | 1020 |
| Test | 1022 |
# Cite original article
```
@article{DBLP:journals/corr/abs-2005-10070,
author = {Demian Gholipour Ghalandari and
Chris Hokamp and
Nghia The Pham and
John Glover and
Georgiana Ifrim},
title = {A Large-Scale Multi-Document Summarization Dataset from the Wikipedia
Current Events Portal},
journal = {CoRR},
volume = {abs/2005.10070},
year = {2020},
url = {https://arxiv.org/abs/2005.10070},
eprinttype = {arXiv},
eprint = {2005.10070},
timestamp = {Fri, 22 May 2020 16:21:28 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-10070.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-08499,
author = {Wen Xiao and
Iz Beltagy and
Giuseppe Carenini and
Arman Cohan},
title = {{PRIMER:} Pyramid-based Masked Sentence Pre-training for Multi-document
Summarization},
journal = {CoRR},
volume = {abs/2110.08499},
year = {2021},
url = {https://arxiv.org/abs/2110.08499},
eprinttype = {arXiv},
eprint = {2110.08499},
timestamp = {Fri, 22 Oct 2021 13:33:09 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-08499.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
``` |
false | # range3/cc100-ja
This dataset consists of parquet files from the cc100 dataset with only the Japanese language extracted and sharded.
このデータセットは、cc100データセットの日本語のみを抽出し、シャーディングしたparquetファイルで構成されます。 |
true | |
false |
> There is also an identical dataset for the new libritts-r dataset at [cdminix/libritts-r-aligned](https://huggingface.co/datasets/cdminix/libritts-r-aligned)
# Dataset Card for LibriTTS with Forced Alignments (and Measures)
This dataset downloads LibriTTS and preprocesses it on your machine to create alignments using [montreal forced aligner](https://montreal-forced-aligner.readthedocs.io/en/latest/).
You need to run ``pip install alignments phones`` before using this dataset.
When running this the first time, it can take an hour or two, but subsequent runs will be lightning fast.
## Requirements
- ``pip install alignments phones`` **(required)**
- ``pip install speech-collator`` (optional)
## Example Item
```json
{
'id': '100_122655_000073_000002.wav',
'speaker': '100',
'text': 'the day after, diana and mary quitted it for distant b.',
'start': 0.0,
'end': 3.6500000953674316,
'phones': ['[SILENCE]', 'ð', 'ʌ', '[SILENCE]', 'd', 'eɪ', '[SILENCE]', 'æ', 'f', 't', 'ɜ˞', '[COMMA]', 'd', 'aɪ', 'æ', 'n', 'ʌ', '[SILENCE]', 'æ', 'n', 'd', '[SILENCE]', 'm', 'ɛ', 'ɹ', 'i', '[SILENCE]', 'k', 'w', 'ɪ', 't', 'ɪ', 'd', '[SILENCE]', 'ɪ', 't', '[SILENCE]', 'f', 'ɜ˞', '[SILENCE]', 'd', 'ɪ', 's', 't', 'ʌ', 'n', 't', '[SILENCE]', 'b', 'i', '[FULL STOP]'],
'phone_durations': [5, 2, 4, 0, 5, 13, 0, 16, 7, 5, 20, 2, 6, 9, 15, 4, 2, 0, 11, 3, 5, 0, 3, 8, 9, 8, 0, 13, 3, 5, 3, 6, 4, 0, 8, 5, 0, 9, 5, 0, 7, 5, 6, 7, 4, 5, 10, 0, 3, 35, 9],
'audio': '/dev/shm/metts/train-clean-360-alignments/100/100_122655_000073_000002.wav'
}
```
The phones are IPA phones, and the phone durations are in frames (assuming a hop length of 256, sample rate of 22050 and window length of 1024). These attributes can be changed using the ``hop_length``, ``sample_rate`` and ``window_length`` arguments to ``LibriTTSAlign``.
## Data Collator
This dataset comes with a data collator which can be used to create batches of data for training.
It can be installed using ``pip install speech-collator`` ([MiniXC/speech-collator](https://www.github.com/MiniXC/speech-collator)) and can be used as follows:
```python
import json
from datasets import load_dataset
from speech_collator import SpeechCollator
from torch.utils.data import DataLoader
dataset = load_dataset('cdminix/libritts-aligned', split="train")
speaker2ixd = json.load(open("speaker2idx.json"))
phone2ixd = json.load(open("phone2idx.json"))
collator = SpeechCollator(
speaker2ixd=speaker2idx,
phone2ixd=phone2idx ,
)
dataloader = DataLoader(dataset, collate_fn=collator.collate_fn, batch_size=8)
```
You can either download the ``speaker2idx.json`` and ``phone2idx.json`` files from [here](https://huggingface.co/datasets/cdminix/libritts-aligned/tree/main/data) or create them yourself using the following code:
```python
import json
from datasets import load_dataset
from speech_collator import SpeechCollator, create_speaker2idx, create_phone2idx
dataset = load_dataset("cdminix/libritts-aligned", split="train")
# Create speaker2idx and phone2idx
speaker2idx = create_speaker2idx(dataset, unk_idx=0)
phone2idx = create_phone2idx(dataset, unk_idx=0)
# save to json
with open("speaker2idx.json", "w") as f:
json.dump(speaker2idx, f)
with open("phone2idx.json", "w") as f:
json.dump(phone2idx, f)
```
### Measures
When using ``speech-collator`` you can also use the ``measures`` argument to specify which measures to use. The following example extracts Pitch and Energy on the fly.
```python
import json
from torch.utils.data import DataLoader
from datasets import load_dataset
from speech_collator import SpeechCollator, create_speaker2idx, create_phone2idx
from speech_collator.measures import PitchMeasure, EnergyMeasure
dataset = load_dataset("cdminix/libritts-aligned", split="train")
speaker2idx = json.load(open("data/speaker2idx.json"))
phone2idx = json.load(open("data/phone2idx.json"))
# Create SpeechCollator
speech_collator = SpeechCollator(
speaker2idx=speaker2idx,
phone2idx=phone2idx,
measures=[PitchMeasure(), EnergyMeasure()],
return_keys=["measures"]
)
# Create DataLoader
dataloader = DataLoader(
dataset,
batch_size=8,
collate_fn=speech_collator.collate_fn,
)
```
COMING SOON: Detailed documentation on how to use the measures at [MiniXC/speech-collator](https://www.github.com/MiniXC/speech-collator).
## Splits
This dataset has the following splits:
- ``train``: All the training data, except one sample per speaker which is used for validation.
- ``dev``: The validation data, one sample per speaker.
- ``train.clean.100``: Training set derived from the original materials of the train-clean-100 subset of LibriSpeech.
- ``train.clean.360``: Training set derived from the original materials of the train-clean-360 subset of LibriSpeech.
- ``train.other.500``: Training set derived from the original materials of the train-other-500 subset of LibriSpeech.
- ``dev.clean``: Validation set derived from the original materials of the dev-clean subset of LibriSpeech.
- ``dev.other``: Validation set derived from the original materials of the dev-other subset of LibriSpeech.
- ``test.clean``: Test set derived from the original materials of the test-clean subset of LibriSpeech.
- ``test.other``: Test set derived from the original materials of the test-other subset of LibriSpeech.
## Environment Variables
There are a few environment variable which can be set.
- ``LIBRITTS_VERBOSE``: If set, will print out more information about the dataset creation process.
- ``LIBRITTS_MAX_WORKERS``: The number of workers to use when creating the alignments. Defaults to ``cpu_count()``.
- ``LIBRITTS_PATH``: The path to download LibriTTS to. Defaults to the value of ``HF_DATASETS_CACHE``.
# Citation
When using LibriTTS please cite the following papers:
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://arxiv.org/abs/1904.02882)
- [Montreal Forced Aligner: Trainable text-speech alignment using Kaldi](https://www.researchgate.net/publication/319185277_Montreal_Forced_Aligner_Trainable_Text-Speech_Alignment_Using_Kaldi)
When using the Measures please cite the following paper (ours):
- [Evaluating and reducing the distance between synthetic and real speech distributions](https://arxiv.org/abs/2211.16049) |
false |
You must download the dataset files manually. You can visit [this](https://github.com/jbrownlee/Datasets/releases/tag/Flickr8k) page or run `download.sh` to get files.
After, you can load dataset by referencing the directory:
```py
import datasets
ds = datasets.load_dataset("atasoglu/flickr8k-dataset", data_dir="data")
print(ds)
```
```
DatasetDict({
train: Dataset({
features: ['image_id', 'image_path', 'captions'],
num_rows: 6000
})
test: Dataset({
features: ['image_id', 'image_path', 'captions'],
num_rows: 1000
})
validation: Dataset({
features: ['image_id', 'image_path', 'captions'],
num_rows: 1000
})
})
```
I don't own the copyright of the images. Please [visit](https://forms.illinois.edu/sec/1713398) for more. |
false | #Dataset 9001 |
true |
### Dataset Summary
This dataset is extracted from Fever dataset (https://fever.ai), pre-processed and ready to train and evaluate.
The training objective is a text classification task - given a claim and evidence, predict if evidence is related to claim. |
true |
# Dataset Card for news-data
## 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)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Dataset Curators](#dataset-curators)
### Dataset Summary
The News Dataset is an English-language dataset containing just over 4k unique news articles scrapped from AriseTv- One of the most popular news television in Nigeria.
### Supported Tasks and Leaderboards
It supports news article classification into different categories.
### Languages
English
## Dataset Structure
### Data Instances
'''
{'Title': 'Nigeria: APC Yet to Zone Party Positions Ahead of Convention'
'Excerpt': 'The leadership of the All Progressives Congress (APC), has denied reports that it had zoned some party positions ahead of'
'Category': 'politics'
'labels': 2}
'''
### Data Fields
* Title: a string containing the title of a news title as shown
* Excerpt: a string containing a short extract from the body of the news
* Category: a string that tells the category of an example (string label)
* labels: integer telling the class of an example (label)
### Data Splits
| Dataset Split | Number of instances in split |
| ----------- | ----------- |
| Train | 4,594 |
| Paragraph | 811 |
## Dataset Creation
### Source Data
#### Initial Data Collection and Normalization
The code for the dataset creation at *https://github.com/chimaobi-okite/NLP-Projects-Competitions/blob/main/NewsCategorization/Data/NewsDataScraping.ipynb*. The examples were scrapped from
<https://www.arise.tv/>
### Annotations
#### Annotation process
The annotation is based on the news category in the [arisetv](https://www.arise.tv) website
#### Who are the annotators?
Journalists at arisetv
## Considerations for Using the Data
### Social Impact of Dataset
The purpose of this dataset is to help develop models that can classify news articles into categories.
This task is useful for efficiently presenting information given a large quantity of text. It should be made clear that any summarizations produced by models trained on this dataset are reflective of the language used in the articles, but are in fact automatically generated.
### Discussion of Biases
This data is biased towards news happenings in Nigeria but the model built using it can as well classify news from other parts of the world
with a slight degradation in performance.
### Dataset Curators
The dataset is created by people at arise but was scrapped by [@github-chimaobi-okite](https://github.com/chimaobi-okite/)
|
false |
# Dataset Card for LILA
## 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)
- [Tutorial](#tutorial)
- [Working with Taxonomies](#working-with-taxonomies)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://lila.science/
- **Repository:** N/A
- **Paper:** N/A
- **Leaderboard:** N/A
- **Point of Contact:** [info@lila.science](info@lila.science)
### Dataset Summary
LILA Camera Traps is an aggregate data set of images taken by camera traps, which are devices that automatically (e.g. via motion detection) capture images of wild animals to help ecological research.
This data set is the first time when disparate camera trap data sets have been aggregated into a single training environment with a single [taxonomy](https://lila.science/taxonomy-mapping-for-camera-trap-data-sets/).
This data set consists of only camera trap image data sets, whereas the broader [LILA](lila.science/) website also has other data sets related to biology and conservation, intended as a resource for both machine learning (ML) researchers and those that want to harness ML for this topic.
See below for information about each specific dataset that LILA contains:
<details>
<summary> Caltech Camera Traps </summary>
This data set contains 243,100 images from 140 camera locations in the Southwestern United States, with labels for 21 animal categories (plus empty), primarily at the species level (for example, the most common labels are opossum, raccoon, and coyote), and approximately 66,000 bounding box annotations. Approximately 70% of images are labeled as empty.
More information about this data set is available [here](https://beerys.github.io/CaltechCameraTraps/).
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
For questions about this data set, contact caltechcameratraps@gmail.com.
If you use this data set, please cite the associated manuscript:
```bibtex
@inproceedings{DBLP:conf/eccv/BeeryHP18,
author = {Sara Beery and
Grant Van Horn and
Pietro Perona},
title = {Recognition in Terra Incognita},
booktitle = {Computer Vision - {ECCV} 2018 - 15th European Conference, Munich,
Germany, September 8-14, 2018, Proceedings, Part {XVI}},
pages = {472--489},
year = {2018},
crossref = {DBLP:conf/eccv/2018-16},
url = {https://doi.org/10.1007/978-3-030-01270-0\_28},
doi = {10.1007/978-3-030-01270-0\_28},
timestamp = {Mon, 08 Oct 2018 17:08:07 +0200},
biburl = {https://dblp.org/rec/bib/conf/eccv/BeeryHP18},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
</details>
<details>
<summary> ENA24 </summary>
This data set contains approximately 10,000 camera trap images representing 23 classes from Eastern North America, with bounding boxes on each image. The most common classes are “American Crow”, “American Black Bear”, and “Dog”.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
Please cite this manuscript if you use this data set:
```bibtex
@article{yousif2019dynamic,
title={Dynamic Programming Selection of Object Proposals for Sequence-Level Animal Species Classification in the Wild},
author={Yousif, Hayder and Kays, Roland and He, Zhihai},
journal={IEEE Transactions on Circuits and Systems for Video Technology},
year={2019},
publisher={IEEE}
}
```
For questions about this data set, contact [Hayder Yousif](hyypp5@mail.missouri.edu).
</details>
<details>
<summary> Missouri Camera Traps </summary>
This data set contains approximately 25,000 camera trap images representing 20 species (for example, the most common labels are red deer, mouflon, and white-tailed deer). Images within each sequence share the same species label (even though the animal may not have been recorded in all the images in the sequence). Around 900 bounding boxes are included. These are very challenging sequences with highly cluttered and dynamic scenes. Spatial resolutions of the images vary from 1920 × 1080 to 2048 × 1536. Sequence lengths vary from 3 to more than 300 frames.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
If you use this data set, please cite the associated manuscript:
```bibtex
@article{zhang2016animal,
title={Animal detection from highly cluttered natural scenes using spatiotemporal object region proposals and patch verification},
author={Zhang, Zhi and He, Zhihai and Cao, Guitao and Cao, Wenming},
journal={IEEE Transactions on Multimedia},
volume={18},
number={10},
pages={2079--2092},
year={2016},
publisher={IEEE}
}
```
For questions about this data set, contact [Hayder Yousif](hyypp5@mail.missouri.edu) and [Zhi Zhang](zzbhf@mail.missouri.edu).
</details>
<details>
<summary> North American Camera Trap Images (NACTI) </summary>
This data set contains 3.7M camera trap images from five locations across the United States, with labels for 28 animal categories, primarily at the species level (for example, the most common labels are cattle, boar, and red deer). Approximately 12% of images are labeled as empty. We have also added bounding box annotations to 8892 images (mostly vehicles and birds).
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
Please cite this manuscript if you use this data set:
```bibtex
@article{tabak2019machine,
title={Machine learning to classify animal species in camera trap images: Applications in ecology},
author={Tabak, Michael A and Norouzzadeh, Mohammad S and Wolfson, David W and Sweeney, Steven J and VerCauteren, Kurt C and Snow, Nathan P and Halseth, Joseph M and Di Salvo, Paul A and Lewis, Jesse S and White, Michael D and others},
journal={Methods in Ecology and Evolution},
volume={10},
number={4},
pages={585--590},
year={2019},
publisher={Wiley Online Library}
}
```
For questions about this data set, contact [northamericancameratrapimages@gmail.com](northamericancameratrapimages@gmail.com).
</details>
<details>
<summary> WCS Camera Traps </summary>
This data set contains approximately 1.4M camera trap images representing around 675 species from 12 countries, making it one of the most diverse camera trap data sets available publicly. Data were provided by the [Wildlife Conservation Society](https://www.wcs.org/). The most common classes are tayassu pecari (peccary), meleagris ocellata (ocellated turkey), and bos taurus (cattle). A complete list of classes and associated image counts is available here. Approximately 50% of images are empty. We have also added approximately 375,000 bounding box annotations to approximately 300,000 of those images, which come from sequences covering almost all locations.
Sequences are inferred from timestamps, so may not strictly represent bursts. Images were labeled at a combination of image and sequence level, so – as is the case with most camera trap data sets – empty images may be labeled as non-empty (if an animal was present in one frame of a sequence but not in others). Images containing humans are referred to in metadata, but are not included in the data files. You can find more information about the data set [on the LILA website](https://lila.science/datasets/wcscameratraps).
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Wellington Camera Traps </summary>
This data set contains 270,450 images from 187 camera locations in Wellington, New Zealand. The cameras (Bushnell 119537, 119476, and 119436) recorded sequences of three images when triggered. Each sequence was labelled by citizen scientists and/or professional ecologists from Victoria University of Wellington into 17 classes: 15 animal categories (for example, the most common labels are bird, cat, and hedgehog), empty, and unclassifiable. Approximately 17% of images are labeled as empty. Images within each sequence share the same species label (even though the animal may not have been recorded in all three images).
If you use this data set, please cite the associated manuscript:
```bibtex
@article{anton2018monitoring,
title={Monitoring the mammalian fauna of urban areas using remote cameras and citizen science},
author={Anton, Victor and Hartley, Stephen and Geldenhuis, Andre and Wittmer, Heiko U},
journal={Journal of Urban Ecology},
volume={4},
number={1},
pages={juy002},
year={2018},
publisher={Oxford University Press}
}
```
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
For questions about this data set, contact [Victor Anton](vykanton@gmail.com).
</details>
<details>
<summary> Island Conservation Camera Traps </summary>
This data set contains approximately 123,000 camera trap images from 123 camera locations from 7 islands in 6 countries. Data were provided by Island Conservation during projects conducted to prevent the extinction of threatened species on islands.
The most common classes are rabbit, rat, petrel, iguana, cat, goat, and pig, with both rat and cat represented between multiple island sites representing significantly different ecosystems (tropical forest, dry forest, and temperate forests). Additionally, this data set represents data from locations and ecosystems that, to our knowledge, are not well represented in publicly available datasets including >1,000 images each of iguanas, petrels, and shearwaters. A complete list of classes and associated image counts is available here. Approximately 60% of the images are empty. We have also included approximately 65,000 bounding box annotations for about 50,000 images.
In general cameras were dispersed across each project site to detect the presence of invasive vertebrate species that threaten native island species. Cameras were set to capture bursts of photos for each motion detection event (between three and eight photos) with a set delay between events (10 to 30 seconds) to minimize the number of photos. Images containing humans are referred to in metadata, but are not included in the data files.
For questions about this data set, contact [David Will](david.will@islandconservation.org) at Island Conservation.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
The original data set included a “human” class label; for privacy reasons, we have removed those images from this version of the data set. Those labels are still present in the metadata. If those images are important to your work, contact us; in some cases it will be possible to release those images under an alternative license.
</details>
<details>
<summary> Channel Islands Camera Traps </summary>
This data set contains 246,529 camera trap images from 73 camera locations in the Channel Islands, California. All animals are annotated with bounding boxes. Data were provided by The Nature Conservancy. Animals are classified as rodent1 (82914), fox (48150), bird (11099), skunk (1071), or other (159). 114,949 images (47%) are empty. All images of rats were taken on islands already known to have rat populations.
If you use these data in a publication or report, please use the following citation:
The Nature Conservancy (2021): Channel Islands Camera Traps 1.0. The Nature Conservancy. Dataset.
For questions about this data set, contact [Nathaniel Rindlaub](nathaniel.rindlaub@TNC.ORG) at The Nature Conservancy.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
The original data set included a “human” class label; for privacy reasons, we have removed those images from this version of the data set. Those labels are still present in the metadata.
</details>
<details>
<summary> Idaho Camera Traps </summary>
This data set contains approximately 1.5 million camera trap images from Idaho. Labels are provided for 62 categories, most of which are animal classes (“deer”, “elk”, and “cattle” are the most common animal classes), but labels also include some state indicators (e.g. “snow on lens”, “foggy lens”). Approximately 70.5% of images are labeled as empty. Annotations were assigned to image sequences, rather than individual images, so annotations are meaningful only at the sequence level.
The metadata contains references to images containing humans, but these have been removed from the dataset (along with images containing vehicles and domestic dogs).
Images were provided by the Idaho Department of Fish and Game. No representations or warranties are made regarding the data, including but not limited to warranties of non-infringement or fitness for a particular purpose. Some information shared under this agreement may not have undergone quality assurance procedures and should be considered provisional. Images may not be sold in any format, but may be used for scientific publications. Please acknowledge the Idaho Department of Fish and Game when using images for publication or scientific communication.
</details>
<details>
<summary> Snapshot Serengeti </summary>
This data set contains approximately 2.65M sequences of camera trap images, totaling 7.1M images, from seasons one through eleven of the [Snapshot Serengeti project](https://snapshotserengeti.org/) -- the flagship project of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Serengeti National Park in Tanzania is best known for the massive annual migrations of wildebeest and zebra that drive the cycling of its dynamic ecosystem.
Labels are provided for 61 categories, primarily at the species level (for example, the most common labels are wildebeest, zebra, and Thomson’s gazelle). Approximately 76% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshotserengeti-v-2-0/SnapshotSerengeti_S1-11_v2.1.species_list.csv). We have also added approximately 150,000 bounding box annotations to approximately 78,000 of those images.
The images and species-level labels are described in more detail in the associated manuscript:
```bibtex
@misc{dryad_5pt92,
title = {Data from: Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna},
author = {Swanson, AB and Kosmala, M and Lintott, CJ and Simpson, RJ and Smith, A and Packer, C},
year = {2015},
journal = {Scientific Data},
URL = {https://doi.org/10.5061/dryad.5pt92},
doi = {doi:10.5061/dryad.5pt92},
publisher = {Dryad Digital Repository}
}
```
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Karoo </summary>
This data set contains 14889 sequences of camera trap images, totaling 38074 images, from the [Snapshot Karoo](https://www.zooniverse.org/projects/shuebner729/snapshot-karoo) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Karoo National Park, located in the arid Nama Karoo biome of South Africa, is defined by its endemic vegetation and mountain landscapes. Its unique topographical gradient has led to a surprising amount of biodiversity, with 58 mammals and more than 200 bird species recorded, as well as a multitude of reptilian species.
Labels are provided for 38 categories, primarily at the species level (for example, the most common labels are gemsbokoryx, hartebeestred, and kudu). Approximately 83.02% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/KAR/SnapshotKaroo_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Kgalagadi </summary>
This data set contains 3611 sequences of camera trap images, totaling 10222 images, from the [Snapshot Kgalagadi](https://www.zooniverse.org/projects/shuebner729/snapshot-kgalagadi/) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. The Kgalagadi Transfrontier Park stretches from the Namibian border across South Africa and into Botswana, covering a landscape commonly referred to as the Kalahari – an arid savanna. This region is of great interest to help us understand how animals cope with extreme temperatures at both ends of the scale.
Labels are provided for 31 categories, primarily at the species level (for example, the most common labels are gemsbokoryx, birdother, and ostrich). Approximately 76.14% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/KGA/SnapshotKgalagadi_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Enonkishu </summary>
This data set contains 13301 sequences of camera trap images, totaling 28544 images, from the [Snapshot Enonkishu](https://www.zooniverse.org/projects/aguthmann/snapshot-enonkishu) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Enonkishu Conservancy is located on the northern boundary of the Mara-Serengeti ecosystem in Kenya, and is managed by a consortium of stakeholders and land-owning Maasai families. Their aim is to promote coexistence between wildlife and livestock in order to encourage regenerative grazing and build stability in the Mara conservancies.
Labels are provided for 39 categories, primarily at the species level (for example, the most common labels are impala, warthog, and zebra). Approximately 64.76% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/ENO/SnapshotEnonkishu_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Camdeboo </summary>
This data set contains 12132 sequences of camera trap images, totaling 30227 images, from the [Snapshot Camdeboo](https://www.zooniverse.org/projects/shuebner729/snapshot-camdeboo) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Camdeboo National Park, South Africa is crucial habitat for many birds on a global scale, with greater than fifty endemic and near-endemic species and many migratory species.
Labels are provided for 43 categories, primarily at the species level (for example, the most common labels are kudu, springbok, and ostrich). Approximately 43.74% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/CDB/SnapshotCamdeboo_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Mountain Zebra </summary>
This data set contains 71688 sequences of camera trap images, totaling 73034 images, from the [Snapshot Mountain Zebra](https://www.zooniverse.org/projects/meredithspalmer/snapshot-mountain-zebra/) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Mountain Zebra National Park is located in the Eastern Cape of South Africa in a transitional area between several distinct biomes, which means it is home to many endemic species. As the name suggests, this park contains the largest remnant population of Cape Mountain zebras, ~700 as of 2019 and increasing steadily every year.
Labels are provided for 54 categories, primarily at the species level (for example, the most common labels are zebramountain, kudu, and springbok). Approximately 91.23% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/MTZ/SnapshotMountainZebra_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Kruger </summary>
This data set contains 4747 sequences of camera trap images, totaling 10072 images, from the [Snapshot Kruger](https://www.zooniverse.org/projects/shuebner729/snapshot-kruger) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Kruger National Park, South Africa has been a refuge for wildlife since its establishment in 1898, and it houses one of the most diverse wildlife assemblages remaining in Africa. The Snapshot Safari grid was established in 2018 as part of a research project assessing the impacts of large mammals on plant life as boundary fences were removed and wildlife reoccupied areas of previous extirpation.
Labels are provided for 46 categories, primarily at the species level (for example, the most common labels are impala, elephant, and buffalo). Approximately 61.60% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/KRU/SnapshotKruger_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> SWG Camera Traps </summary>
This data set contains 436,617 sequences of camera trap images from 982 locations in Vietnam and Lao, totaling 2,039,657 images. Labels are provided for 120 categories, primarily at the species level (for example, the most common labels are “Eurasian Wild Pig”, “Large-antlered Muntjac”, and “Unidentified Murid”). Approximately 12.98% of images are labeled as empty. A full list of species and associated image counts is available here. 101,659 bounding boxes are provided on 88,135 images.
This data set is provided by the Saola Working Group; providers include:
- IUCN SSC Asian Wild Cattle Specialist Group’s Saola Working Group (SWG)
- Asian Arks
- Wildlife Conservation Society (Lao)
- WWF Lao
- Integrated Conservation of Biodiversity and Forests project, Lao (ICBF)
- Center for Environment and Rural Development, Vinh University, Vietnam
If you use these data in a publication or report, please use the following citation:
SWG (2021): Northern and Central Annamites Camera Traps 2.0. IUCN SSC Asian Wild Cattle Specialist Group’s Saola Working Group. Dataset.
For questions about this data set, contact saolawg@gmail.com.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Orinoquia Camera Traps </summary>
This data set contains 104,782 images collected from a 50-camera-trap array deployed from January to July 2020 within the private natural reserves El Rey Zamuro (31 km2) and Las Unamas (40 km2), located in the Meta department in the Orinoquía region in central Colombia. We deployed cameras using a stratified random sampling design across forest core area strata. Cameras were spaced 1 km apart from one another, located facing wildlife trails, and deployed with no bait. Images were stored and reviewed by experts using the Wildlife Insights platform.
This data set contains 51 classes, predominantly mammals such as the collared peccary, black agouti, spotted paca, white-lipped peccary, lowland tapir, and giant anteater. Approximately 20% of images are empty.
The main purpose of the study is to understand how humans, wildlife, and domestic animals interact in multi-functional landscapes (e.g., agricultural livestock areas with native forest remnants). However, this data set was also used to review model performance of AI-powered platforms – Wildlife Insights (WI), MegaDetector (MD), and Machine Learning for Wildlife Image Classification (MLWIC2). We provide a demonstration of the use of WI, MD, and MLWIC2 and R code for evaluating model performance of these platforms in the accompanying [GitHub repository](https://github.com/julianavelez1/Processing-Camera-Trap-Data-Using-AI).
If you use these data in a publication or report, please use the following citation:
```bibtex
@article{velez2022choosing,
title={Choosing an Appropriate Platform and Workflow for Processing Camera Trap Data using Artificial Intelligence},
author={V{\'e}lez, Juliana and Castiblanco-Camacho, Paula J and Tabak, Michael A and Chalmers, Carl and Fergus, Paul and Fieberg, John},
journal={arXiv preprint arXiv:2202.02283},
year={2022}
}
```
For questions about this data set, contact [Juliana Velez Gomez](julianavelezgomez@gmail.com).
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
### Supported Tasks and Leaderboards
No leaderboards exist for LILA.
### Languages
The [LILA taxonomy](https://lila.science/taxonomy-mapping-for-camera-trap-data-sets/) is provided in English.
## Dataset Structure
### Data Instances
The data annotations are provided in [COCO Camera Traps](https://github.com/Microsoft/CameraTraps/blob/master/data_management/README.md#coco-cameratraps-format) format.
All of the datasets share a common category taxonomy, which is defined on the [LILA website](https://lila.science/taxonomy-mapping-for-camera-trap-data-sets/).
### Data Fields
Different datasets may have slightly varying fields, which include:
`file_name`: the file name \
`width` and `height`: the dimensions of the image \
`study`: which research study the image was collected as part of \
`location` : the name of the location at which the image was taken \
`annotations`: information about image annotation, which includes the taxonomy information, bounding box/boxes (`bbox`/`bboxes`) if any, as well as any other annotation information. \
`image` : the `path` to download the image and any other information that is available, e.g. its size in `bytes`.
### Data Splits
This dataset does not have a predefined train/test split.
## Dataset Creation
### Curation Rationale
The datasets that constitute LILA have been provided by the organizations, projects and researchers who collected them.
### Source Data
#### Initial data collection and normalization
N/A
#### Who are the source language producers?
N/A
### Annotations
#### Annotation process
Each dataset has been annotated by the members of the project/organization that provided it.
#### Who are the annotators?
The annotations have been provided by domain experts in fields such as biology and ecology.
### Personal and Sensitive Information
Some of the original data sets included a “human” class label; for privacy reasons, these images were removed. Those labels are still present in the metadata. If those images are important to your work, contact the [LILA maintainers](mailto:info@lila.science), since in some cases it will be possible to release those images under an alternative license.
## Considerations for Using the Data
### Social Impact of Dataset
Machine learning depends on labeled data, but accessing such data in biology and conservation is a challenge. Consequently, everyone benefits when labeled data is made available. Biologists and conservation scientists benefit by having data to train on, and free hosting allows teams to multiply the impact of their data (we suggest listing this benefit in grant proposals that fund data collection). ML researchers benefit by having data to experiment with.
### Discussion of Biases
These datasets do not represent global diversity, but are examples of local ecosystems and animals.
### Other Known Limitations
N/A
## Additional Information
### Tutorial
The [tutorial in this Google Colab notebook](https://colab.research.google.com/drive/17gPOIK-ksxPyX6yP9TaKIimlwf9DYe2R?usp=sharing) demonstrates how to work with this dataset, including filtering by species, collating configurations, and downloading images.
### Working with Taxonomies
All the taxonomy categories are saved as ClassLabels, which can be converted to strings as needed. Strings can likewise be converted to integers as needed, to filter the dataset. In the example below we filter the "Caltech Camera Traps" dataset to find all the entries with a "felis catus" as the species for the first annotation.
```python
dataset = load_dataset("society-ethics/lila_camera_traps", "Caltech Camera Traps", split="train")
taxonomy = dataset.features["annotations"].feature["taxonomy"]
# Filters to show only cats
cats = dataset.filter(lambda x: x["annotations"]["taxonomy"][0]["species"] == taxonomy["species"].str2int("felis catus"))
```
The original common names have been saved with their taxonomy mappings in this repository in `common_names_to_tax.json`. These can be used, for example, to map from a taxonomy combination to a common name to help make queries more legible. Note, however, that there is a small number of duplicate common names with different taxonomy values which you will need to disambiguate.
The following example loads the first "sea turtle" in the "Island Conservation Camera Traps" dataset.
```python
LILA_COMMON_NAMES_TO_TAXONOMY = pd.read_json("https://huggingface.co/datasets/society-ethics/lila_camera_traps/raw/main/data/common_names_to_tax.json", lines=True).set_index("common_name")
dataset = load_dataset("society-ethics/lila_camera_traps", "Island Conservation Camera Traps", split="train")
taxonomy = dataset.features["annotations"].feature["taxonomy"]
sea_turtle = LILA_COMMON_NAMES_TO_TAXONOMY.loc["sea turtle"].to_dict()
sea_turtle = {k: taxonomy[k].str2int(v) if v is not None else v for k, v in sea_turtle.items()} # Map to ClassLabel integers
sea_turtle_dataset = ds.filter(lambda x: x["annotations"]["taxonomy"][0] == sea_turtle)
```
The example below selects a random item from the dataset, and then maps from the taxonomy to a common name:
```python
LILA_COMMON_NAMES_TO_TAXONOMY = pd.read_json("https://huggingface.co/datasets/society-ethics/lila_camera_traps/raw/main/data/common_names_to_tax.json", lines=True).set_index("common_name")
dataset = load_dataset("society-ethics/lila_camera_traps", "Caltech Camera Traps", split="train")
taxonomy = dataset.features["annotations"].feature["taxonomy"]
random_entry = dataset.shuffle()[0]
filter_taxonomy = random_entry["annotations"]["taxonomy"][0]
filter_keys = list(map(lambda x: (x[0], taxonomy[x[0]].int2str(x[1])), filter(lambda x: x[1] is not None, list(filter_taxonomy.items()))))
if len(filter_keys) > 0:
print(LILA_COMMON_NAMES_TO_TAXONOMY[np.logical_and.reduce([
LILA_COMMON_NAMES_TO_TAXONOMY[k] == v for k,v in filter_keys
])])
else:
print("No common name found for the item.")
```
### Dataset Curators
LILA BC is maintained by a working group that includes representatives from Ecologize, Zooniverse, the Evolving AI Lab, Snapshot Safari, and Microsoft AI for Earth. Hosting on Microsoft Azure is provided by Microsoft AI for Earth.
### Licensing Information
Many, but not all, LILA data sets were released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/). Check the details of the specific dataset you are using in its section above.
### Citation Information
Citations for each dataset (if they exist) are provided in its section above.
### Contributions
Thanks to [@NimaBoscarino](https://github.com/NimaBoscarino/) for adding this dataset.
|
false |
# CMP Facade Database
We present a dataset of facade images assembled at the Center for Machine Perception, which includes 606 rectified images of facades from various sources, which have been manually annotated. The facades are from different cities around the world and diverse architectural styles.
Documentation
Data origin, format and processing, annotation principles for 12 classes are specified in the report.
- facade
- molding
- cornice
- pillar
- window
- door
- sill
- blind
- balcony
- shop
- deco
- background
Link to original website:
https://cmp.felk.cvut.cz/~tylecr1/facade/
Citation
Please use the following reference to cite the dataset:
```latex
@INPROCEEDINGS{Tylecek13,
author = {Radim Tyle{\v c}ek and Radim {\v S}{\' a}ra},
title = {Spatial Pattern Templates for Recognition of Objects with Regular Structure},
booktitle = {Proc. GCPR},
year = {2013},
address = {Saarbrucken, Germany},
}
``` |
false | # ILPD
The [ILPD dataset](https://archive.ics.uci.edu/ml/datasets/ILPD) from the [UCI ML repository](https://archive.ics.uci.edu/ml/datasets).
# Configurations and tasks
| **Configuration** | **Task** | **Description** |
|-------------------|---------------------------|---------------------------------------|
| liver | Binary classification | Does the patient have liver problems? |
# Usage
```python
from datasets import load_dataset
dataset = load_dataset("mstz/liver")["train"]
``` |
false |
Wizard-LM-Chinese是在MSRA的Wizard-LM数据集上，对指令进行翻译，然后再调用GPT获得答案的数据集
Wizard-LM包含了很多难度超过Alpaca的指令。
中文的问题翻译会有少量指令注入导致翻译失败的情况
中文回答是根据中文问题再进行问询得到的。
我们会陆续将更多数据集发布到hf，包括
- [ ] Coco Caption的中文翻译
- [ ] CoQA的中文翻译
- [ ] CNewSum的Embedding数据
- [ ] 增广的开放QA数据
- [x] WizardLM的中文翻译
如果你也在做这些数据集的筹备，欢迎来联系我们，避免重复花钱。
# 骆驼(Luotuo): 开源中文大语言模型
[https://github.com/LC1332/Luotuo-Chinese-LLM](https://github.com/LC1332/Luotuo-Chinese-LLM)
骆驼(Luotuo)项目是由[冷子昂](https://blairleng.github.io) @ 商汤科技, 陈启源 @ 华中师范大学 以及 李鲁鲁 @ 商汤科技 发起的中文大语言模型开源项目，包含了一系列语言模型。
( 注意: [陈启源](https://qiyuan-chen.github.io/) 正在寻找2024推免导师，欢迎联系 )
骆驼项目**不是**商汤科技的官方产品。
## Citation
Please cite the repo if you use the data or code in this repo.
```
@misc{alpaca,
author={Ziang Leng, Qiyuan Chen and Cheng Li},
title = {Luotuo: An Instruction-following Chinese Language model, LoRA tuning on LLaMA},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/LC1332/Luotuo-Chinese-LLM}},
}
``` |
false | ERROR: type should be string, got "\nhttps://huggingface.co/datasets/RUCAIBox/Story-Generation\n\nRUC AI Box HC Story Generation augmented and converted to alpaca format.\nNo filtering has been done." |
false |
# Dataset Card for sberdevices_golos_10h_crowd
## 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:** [Golos ASR corpus](https://www.openslr.org/114)
- **Repository:** [Golos dataset](https://github.com/sberdevices/golos)
- **Paper:** [Golos: Russian Dataset for Speech Research](https://arxiv.org/pdf/2106.10161.pdf)
- **Leaderboard:** [The 🤗 Speech Bench](https://huggingface.co/spaces/huggingface/hf-speech-bench)
- **Point of Contact:** [Nikolay Karpov](mailto:karpnv@gmail.com)
### Dataset Summary
Sberdevices Golos is a corpus of approximately 1200 hours of 16kHz Russian speech from crowd (reading speech) and farfield (communication with smart devices) domains, prepared by SberDevices Team (Alexander Denisenko, Angelina Kovalenko, Fedor Minkin, and Nikolay Karpov). The data is derived from the crowd-sourcing platform, and has been manually annotated.
Authors divide all dataset into train and test subsets. The training subset includes approximately 1000 hours. For experiments with a limited number of records, authors identified training subsets of shorter length: 100 hours, 10 hours, 1 hour, 10 minutes.
This dataset is a simpler version of the above mentioned Golos:
- it includes the crowd domain only (without any sound from the farfield domain);
- validation split is built on the 1-hour training subset;
- training split corresponds to the 10-hour training subset without sounds from the 1-hour training subset;
- test split is a full original test split.
### Supported Tasks and Leaderboards
- `automatic-speech-recognition`: The dataset can be used to train a model for Automatic Speech Recognition (ASR). The model is presented with an audio file and asked to transcribe the audio file to written text. The most common evaluation metric is the word error rate (WER). The task has an active Hugging Face leaderboard which can be found at https://huggingface.co/spaces/huggingface/hf-speech-bench. The leaderboard ranks models uploaded to the Hub based on their WER.
### Languages
The audio is in Russian.
## Dataset Structure
### Data Instances
A typical data point comprises the audio data, usually called `audio` and its transcription, called `transcription`. Any additional information about the speaker and the passage which contains the transcription is not provided.
```
{'audio': {'path': None,
'array': array([ 3.05175781e-05, 3.05175781e-05, 0.00000000e+00, ...,
-1.09863281e-03, -7.93457031e-04, -1.52587891e-04]), dtype=float64),
'sampling_rate': 16000},
'transcription': 'шестнадцатая часть сезона пять сериала лемони сникет тридцать три несчастья'}
```
### 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]`.
- transcription: the transcription of the audio file.
### Data Splits
This dataset is a simpler version of the original Golos:
- it includes the crowd domain only (without any sound from the farfield domain);
- validation split is built on the 1-hour training subset;
- training split corresponds to the 10-hour training subset without sounds from the 1-hour training subset;
- test split is a full original test split.
| | Train | Validation | Test |
| ----- | ------ | ---------- | ----- |
| examples | 7993 | 793 | 9994 |
| hours | 8.9h | 0.9h | 11.2h |
## 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
All recorded audio files were manually annotated on the crowd-sourcing platform.
#### Who are the annotators?
[Needs More Information]
### Personal and Sensitive Information
The dataset consists of people who have donated their voice. 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
[Needs More Information]
## Additional Information
### Dataset Curators
The dataset was initially created by Alexander Denisenko, Angelina Kovalenko, Fedor Minkin, and Nikolay Karpov.
### Licensing Information
[Public license with attribution and conditions reserved](https://github.com/sberdevices/golos/blob/master/license/en_us.pdf)
### Citation Information
```
@misc{karpov2021golos,
author = {Karpov, Nikolay and Denisenko, Alexander and Minkin, Fedor},
title = {Golos: Russian Dataset for Speech Research},
publisher = {arXiv},
year = {2021},
url = {https://arxiv.org/abs/2106.10161}
}
```
### Contributions
Thanks to [@bond005](https://github.com/bond005) for adding this dataset.
|
false | # Codex Math QA
Solve math_qa using codex-davinci-002 via Python Programming.
[Since OpenAI decided to shut off code-davinci-002 behind Azure](https://mobile.twitter.com/Veqtor/status/1638081493099597824), this dataset aims to share the generation results for code-davinci-002 OpenAI's 176B code generation model.
### Data Splits
| name |train|validation|test|
|-------|----:|---------:|---:|
|main|25065| 4133|2985|
|rational| - | 4151|2985|
1. Basic prompts : only question
```
dataset = load_dataset("theblackcat102/codex-math-qa", "main")
```
**Example :**
```
the average weight of 8 person ' s increases by 1.5 kg when a new person comes in place of one of them weighing 75 kg. what might be the weight of the new person ?
Write a short snippet of python function which solve this problem. No need to explain the answer, let the code output the answer.
```
output
```python
def average_weight(weights):
total_weight = sum(weights)
return total_weight / len(weights)
def new_person_weight(weights):
average_weight = average_weight(weights)
new_person_weight = average_weight + 1.5
return new_person_weight
weights = [75, 80, 85, 90, 95]
print(new_person_weight(weights))
```
2. Prompts with rationale : include the `Rationale` text which should helps the programming planinig
```
dataset = load_dataset("theblackcat102/codex-math-qa", "rational")
```
**Example :**
```
one copy machine can make 20 copies a minute, and a second copy machine makes 10 copies a minute. if the two copiers work together, how long would it take them to make 900 copies ?
Rationale: "total work done by both machines in a minute = 20 + 10 = 30 copies total number of copies required = 900 time = 900 / 30 = 30 mins answer d"
Write a short snippet of python function which solve this problem within 30 lines of code. Add comments in the function block for explaination.
```
output
```python
def copy_machine(copies, copy_speed):
"""
:param copies: number of copies required
:param copy_speed: speed of the copy machine
:return: time in minutes
"""
total_work = sum(copy_speed)
time = copies / total_work
return time
if __name__ == "__main__":
print(copy_machine(900, [20, 10]))
```
### Notes:
The generated results are unvalidated and are as what it is from the codex-davinci-002 outputs. So there's a majority of answers which is incorrect and code with syntax error. However, this is a work for a future study and the aim of this dataset was to provide a source or reference for code based math answering by codex-davinci-002.
## Dataset Creation
Dataset was sourced from [math_qa](https://huggingface.co/datasets/math_qa) and append prompts at the end of section for generating Python solutions for the answer. This is an aim for providing dataset for the work offload seem in galactica
The generation config for code-davinci-02 are as follows:
| name | value|
|-------|----:|
|max_tokens| 2048 |
|temperature| 0.5 |
|top_p| 0.7 |
### Citation Information
```
@inproceedings{amini-etal-2019-mathqa,
title = "{M}ath{QA}: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms",
author = "Amini, Aida and
Gabriel, Saadia and
Lin, Shanchuan and
Koncel-Kedziorski, Rik and
Choi, Yejin and
Hajishirzi, Hannaneh",
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://aclanthology.org/N19-1245",
doi = "10.18653/v1/N19-1245",
pages = "2357--2367",
}
``` |
false |
# VoxCeleb 1
VoxCeleb1 contains over 100,000 utterances for 1,251 celebrities, extracted from videos uploaded to YouTube.
## Identification Split
| | train | validation | test |
| :---: | :---: | :---: | :---: |
| # of speakers | 1251 | 1251 | 1251 |
| # of samples | 138361 | 6904 | 8251 |
## References
- https://www.robots.ox.ac.uk/~vgg/data/voxceleb/vox1.html |
false |
## Dataset Summary
The Massive ABC notation Dataset (MABCD) used to train and evaluate [TunesFormer](https://huggingface.co/sander-wood/tunesformer) is collected from two sources: [The Session](https://thesession.org) and [ABCnotation.com](https://abcnotation.com). The Session is a community website focused on Irish traditional music, while ABCnotation.com is a website that provides a standard for folk and traditional music notation in the form of ASCII text files. Both of them provide a platform for sharing folk and traditional music. The combined dataset consists of 285,449 ABC tunes, with 99\% (282,595) of the tunes used as the training set and the remaining 1\% (2854) used as the evaluation set.
Control codes are symbols that are added to the ABC notation representation to indicate the desired musical form of the generated melodies. We add the following control codes to each ABC tune in the dataset through an automated process to indicate its musical form:
- Number of Bars (NB): controls the number of bars in a section of the melody. For example, users could specify that they want a section to contain 8 bars, and TunesFormer would generate a section that fits within that structure. It counts on the bar symbol ***|***.
- Number of Sections (NS): controls the number of sections in the entire melody. This can be used to create a sense of structure and coherence within the melody, as different sections can be used to create musical themes or motifs. It counts on several symbols that are commonly used in ABC notation and can be used to represent section boundaries: ***\[|***, ***||***, ***|\]***, ***|:***, ***::***, and ***:|***.
- Edit Distance Similarity (EDS): controls the similarity level between the current section and a previous section in the melody.
To ensure consistency and standardization among the ABC tunes in the dataset, we first converted them all into MusicXML format and then re-converted them back into ABC notation. In order to focus solely on the musical content, we removed any natural language elements (such as titles, composers, and lyrics) and unnecessary information (such as reference numbers and sources).
ABC notation can be converted to sheet music or audio using [this website](https://ldzhangyx.github.io/abc/), or [this software](https://sourceforge.net/projects/easyabc/).
## Copyright Disclaimer
The dataset is provided solely for research purposes and is not intended for commercial use. While most of the tunes in the dataset are freely shared, some may be protected by copyright. It is the responsibility of the user to determine the copyright status of each tune and obtain any necessary permissions before using the data.
If you are the copyright owner of any tune included in the MABCD and have concerns about its inclusion, please contact us at shangda@mail.ccom.edu.cn to have it removed.
## Special Thanks
We would like to extend a special thanks to abcnotation.com and thesession.org for their contributions to the development and promotion of ABC notation, as well as their contributions to the field of music information retrieval. Their platforms have provided invaluable resources for the traditional and folk music community, and have made it possible for researchers like us to create and study large datasets like the Massive ABC notation Dataset. |
false |
# Dataset Card for MeQSum
## 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:**
- **Repository:** https://github.com/abachaa/MeQSum
- **Paper:** [On the Summarization of Consumer Health Questions](https://aclanthology.org/P19-1215)
- **Leaderboard:**
- **Point of Contact:** [Asma Ben Abacha](mailto:asma.benabacha@nih.gov)
### Dataset Summary
MeQSum corpus is a dataset for medical question summarization. It contains 1,000 summarized consumer health questions.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English (`en`).
## Dataset Structure
### Data Instances
```
{
"CHQ": "SUBJECT: who and where to get cetirizine - D\\nMESSAGE: I need\\/want to know who manufscturs Cetirizine. My Walmart is looking for a new supply and are not getting the recent",
"Summary": "Who manufactures cetirizine?",
"File": "1-131188152.xml.txt"
}
```
### Data Fields
- `CHQ` (str): Consumer health question.
- `Summary` (str): Question summarization, i.e., condensed question expressing the minimum information required to find correct answers to the original question.
- `File` (str): Filename.
### Data Splits
The dataset consists of a single `train` split containing 1,000 examples.
## 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
If you use the MeQSum corpus, please cite:
```
@inproceedings{ben-abacha-demner-fushman-2019-summarization,
title = "On the Summarization of Consumer Health Questions",
author = "Ben Abacha, Asma and
Demner-Fushman, Dina",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1215",
doi = "10.18653/v1/P19-1215",
pages = "2228--2234",
abstract = "Question understanding is one of the main challenges in question answering. In real world applications, users often submit natural language questions that are longer than needed and include peripheral information that increases the complexity of the question, leading to substantially more false positives in answer retrieval. In this paper, we study neural abstractive models for medical question summarization. We introduce the MeQSum corpus of 1,000 summarized consumer health questions. We explore data augmentation methods and evaluate state-of-the-art neural abstractive models on this new task. In particular, we show that semantic augmentation from question datasets improves the overall performance, and that pointer-generator networks outperform sequence-to-sequence attentional models on this task, with a ROUGE-1 score of 44.16{\%}. We also present a detailed error analysis and discuss directions for improvement that are specific to question summarization.",
}
```
### Contributions
Thanks to [@albertvillanova](https://huggingface.co/albertvillanova) for adding this dataset. |
false |
# IVA Swift GitHub Code Dataset
## Dataset Description
This is the raw IVA Swift dataset extracted from GitHub.
It contains uncurated Swift files gathered with the purpose to train a code generation model.
The dataset consists of 753693 swift code files from GitHub totaling ~700MB of data.
The dataset was created from the public GitHub dataset on Google BiqQuery.
### How to use it
To download the full dataset:
```python
from datasets import load_dataset
dataset = load_dataset('mvasiliniuc/iva-swift-codeint', split='train')
```
```python
from datasets import load_dataset
dataset = load_dataset('mvasiliniuc/iva-swift-codeint', split='train')
print(dataset[77723])
#OUTPUT:
{
"repo_name":"simpleandpretty/decider-ios",
"path":"MessagesExtension/MediaResources.swift",
"copies":"1",
"size":"1232",
"content":"import Foundation\nimport UIKit\n\nclass MediaResources {\n\n static func mediaURL(forGameOption option:FightMove) -> URL {\n let bundle = Bundle.main\n guard\n let mediaURL = bundle.url(forResource: option.rawValue, withExtension: \"mp4\")\n ...",
"license":"gpl-3.0"
}
```
## Data Structure
### Data Fields
|Field|Type|Description|
|---|---|---|
|repo_name|string|name of the GitHub repository|
|path|string|path of the file in GitHub repository|
|copies|string|number of occurrences in dataset|
|code|string|content of source file|
|size|string|size of the source file in bytes|
|license|string|license of GitHub repository|
### Instance
```json
{
"repo_name":"simpleandpretty/decider-ios",
"path":"MessagesExtension/MediaResources.swift",
"copies":"1",
"size":"1232",
"content":"import Foundation\nimport UIKit\n\nclass MediaResources {\n\n static func mediaURL(forGameOption option:FightMove) -> URL {\n let bundle = Bundle.main\n guard\n let mediaURL = bundle.url(forResource: option.rawValue, withExtension: \"mp4\")\n ...",
"license":"gpl-3.0"
}
```
## Languages
The dataset contains only Swift files.
```json
{
"Swift": [".swift"]
}
```
## Licenses
Each entry in the dataset contains the associated license. The following is a list of licenses involved and their occurrences.
```json
{
"agpl-3.0": 2775,
"apache-2.0": 180178,
"artistic-2.0": 314,
"bsd-2-clause": 5342,
"bsd-3-clause": 11429,
"cc0-1.0": 2718,
"epl-1.0": 980,
"gpl-2.0": 15751,
"gpl-3.0": 33074,
"isc": 1647,
"lgpl-2.1": 1741,
"lgpl-3.0": 6150,
"mit": 476518,
"mpl-2.0": 11799,
"unlicense": 3277
}
```
## Dataset Statistics
```json
{
"Total size": "~712 MB",
"Number of files": 753693,
"Number of files under 500 bytes": 129827,
"Average file size in bytes": 4245,
}
```
## Dataset Creation
The dataset was created using Google Query for Github:
https://cloud.google.com/blog/topics/public-datasets/github-on-bigquery-analyze-all-the-open-source-code
The following steps were pursued for data
gathering:
1. Creation of a dataset and a table in Google Big Query Project.
2. Creation of a bucket in Google Cloud Storage.
3. Creation of a query in Google Big Query Project.
4. Running the query with the setting to output the results in the dataset and table
created at step one.
5. Exporting the resulting dataset into the bucket created in step 2. Export format of JSON with gzip compression.
The result of these steps leads to the following results:
* 2.7 TB Processed,
* number of extracted rows/Swift files was 464,215
* total logical bytes 1.46 GB.
* The result amounts to 7 json.gz files in a total of 700 MB
The SQL Query used is:
```sql
SELECT
f.repo_name, f.path, c.copies, c.size, c.content, l.license
FROM
(select f.*, row_number() over (partition by id order by path desc) as seqnum from `bigquery-public-data.github_repos.files` AS f) f
JOIN
`bigquery-public-data.github_repos.contents` AS c
ON
f.id = c.id AND seqnum=1
JOIN
`bigquery-public-data.github_repos.licenses` AS l
ON
f.repo_name = l.repo_name
WHERE
NOT c.binary AND ((f.path LIKE '%.swift') AND (c.size BETWEEN 0 AND 1048575))
```
## Data Splits
The dataset only contains a train split.
Using the curated version of this dataset, a split was made into multiple repositories:
* Clean Version: https://huggingface.co/datasets/mvasiliniuc/iva-swift-codeint-clean
* Clean Version Train: https://huggingface.co/datasets/mvasiliniuc/iva-swift-codeint-clean-train
* Clean Version Valid: https://huggingface.co/datasets/mvasiliniuc/iva-swift-codeint-clean-valid
# Considerations for Using the Data
The dataset comprises source code from various repositories, potentially containing harmful or biased code,
along with sensitive information such as passwords or usernames.
# Additional Information
## Dataset Curators
[mircea.dev@icloud.com](mircea.dev@icloud.com)
## Licensing Information
* The license of this open-source dataset is: other.
* The dataset is gathered from open-source repositories on [GitHub using BigQuery](https://cloud.google.com/blog/topics/public-datasets/github-on-bigquery-analyze-all-the-open-source-code).
* Find the license of each entry in the dataset in the corresponding license column.
## Citation Information
```json
@misc {mircea_vasiliniuc_2023,
author = { {Mircea Vasiliniuc} },
title = { iva-swift-codeint (Revision c09ebf8) },
year = 2023,
url = { https://huggingface.co/datasets/mvasiliniuc/iva-swift-codeint },
doi = { 10.57967/hf/0778 },
publisher = { Hugging Face }
}
``` |
true |
# Dataset Card for ReRelEM
## Dataset Description
- **Paper:** [Relation detection between named entities: report of a shared task](https://aclanthology.org/W09-2421.pdf)
- **Point of Contact:** [Hugo Gonçalo Oliveira](hroliv@dei.uc.pt)
### Dataset Summary
The ReRelEM dataset is designed for the detection and classification of relations between named entities in Portuguese text. It contains 2226 training, 701 validation, and 805 test instances. Each instance contains two sentences with two entities enclosed by the tags [E1] and [E2]. The dataset provides a fourfold relationship classification: identity, included-in, located-in, and other (which is detailed into twenty different relations).
It's important to note that, although we maintained more than 99% of the original instances, this is not a full representation of the original ReRelEM dataset.
The dataset was split into train, validation, and test sets, after which 21 instances with relation types not included in the training set were dropped from the test set. Furthermore, 7 instances from the original dataset that had formatting errors and could not be resolved into post-processed records were also dropped.
### Supported Tasks and Leaderboards
- Relation extraction: The primary task of this dataset is to classify relations between named entities.
### Languages
- Portuguese
## Dataset Structure
### Data Instances
An example data instance from the dataset:
```json
{
"docid": "cver",
"sentence1": "O PRESIDENTE Sarkozy abriu a Conferência de Dadores realizada em Paris com uma frase grandiloquente sobre a necessidade urgente de criar um Estado palestiniano no fim de 2008 . O Presidente ou é mentiroso ou finge-se ignorante, ou as duas coisas. Depois do falhanço esperado da cimeira de Annapolis , um modo de [E2]Condoleezza Rice[/E2] salvar a face e de a Administração | Administração americana e a Europa continuarem a fingir que estão interessadas em resolver o conflito israelo-palestiniano e de lavarem as mãos de tudo o resto, Sarkozy não pode ignorar que o momento para pronunciamentos débeis é o menos adequado. Tony Blair , depois de ter minado todo o processo de paz do Médio Oriente ao ordenar a invasão do Iraque de braço dado com [E1]Bush[/E1] , continua a emitir piedades deste género, e diz que está na altura de resolver o problema e que ele pode ser resolvido. Blair não sabe o que diz.",
"sentence2": "nan",
"label": "relacao_profissional",
"same_text": true
}
```
### Data Fields
- `docid`: Document ID of both sentences (sentence1 and sentence2)
- `sentence1`: The first sentence with an entity span enclosed by the tags [E1] and [/E1]
- `sentence2`: The second sentence with an entity span enclosed by the tags [E2] and [/E2]
- `label`: The type of relation between the entities
- `same_text`: True if both entity spans appear in the same sentence. If True, `sentence2` will be empty.
### Data Splits
| | train | validation | test |
|--------|-------|------------|------|
| Instances | 2226 | 701 | 805 |
The dataset was divided in a manner that ensured sentences from the same document did not appear in more than one split.
### Citation Information
```bibtex
@inproceedings{freitas2009relation,
title={Relation detection between named entities: report of a shared task},
author={Freitas, Cl{\\'a}udia and Santos, Diana and Mota, Cristina and Oliveira, Hugo Gon{\\c{c}}alo and Carvalho, Paula},
booktitle={Proceedings of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions (SEW-2009)},
pages={129--137},
year={2009}
}
```
### Contributions
Thanks to [@ruanchaves](https://github.com/ruanchaves) for adding this dataset. |
false |
# Dataset Card for BEIR Benchmark
## 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/UKPLab/beir
- **Repository:** https://github.com/UKPLab/beir
- **Paper:** https://openreview.net/forum?id=wCu6T5xFjeJ
- **Leaderboard:** https://docs.google.com/spreadsheets/d/1L8aACyPaXrL8iEelJLGqlMqXKPX2oSP_R10pZoy77Ns
- **Point of Contact:** nandan.thakur@uwaterloo.ca
### Dataset Summary
BEIR is a heterogeneous benchmark that has been built from 18 diverse datasets representing 9 information retrieval tasks:
- Fact-checking: [FEVER](http://fever.ai), [Climate-FEVER](http://climatefever.ai), [SciFact](https://github.com/allenai/scifact)
- Question-Answering: [NQ](https://ai.google.com/research/NaturalQuestions), [HotpotQA](https://hotpotqa.github.io), [FiQA-2018](https://sites.google.com/view/fiqa/)
- Bio-Medical IR: [TREC-COVID](https://ir.nist.gov/covidSubmit/index.html), [BioASQ](http://bioasq.org), [NFCorpus](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)
- News Retrieval: [TREC-NEWS](https://trec.nist.gov/data/news2019.html), [Robust04](https://trec.nist.gov/data/robust/04.guidelines.html)
- Argument Retrieval: [Touche-2020](https://webis.de/events/touche-20/shared-task-1.html), [ArguAna](tp://argumentation.bplaced.net/arguana/data)
- Duplicate Question Retrieval: [Quora](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs), [CqaDupstack](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)
- Citation-Prediction: [SCIDOCS](https://allenai.org/data/scidocs)
- Tweet Retrieval: [Signal-1M](https://research.signal-ai.com/datasets/signal1m-tweetir.html)
- Entity Retrieval: [DBPedia](https://github.com/iai-group/DBpedia-Entity/)
All these datasets have been preprocessed and can be used for your experiments.
```python
```
### Supported Tasks and Leaderboards
The dataset supports a leaderboard that evaluates models against task-specific metrics such as F1 or EM, as well as their ability to retrieve supporting information from Wikipedia.
The current best performing models can be found [here](https://eval.ai/web/challenges/challenge-page/689/leaderboard/).
### Languages
All tasks are in English (`en`).
## Dataset Structure
All BEIR datasets must contain a corpus, queries and qrels (relevance judgments file). They must be in the following format:
- `corpus` file: a `.jsonl` file (jsonlines) that contains a list of dictionaries, each with three fields `_id` with unique document identifier, `title` with document title (optional) and `text` with document paragraph or passage. For example: `{"_id": "doc1", "title": "Albert Einstein", "text": "Albert Einstein was a German-born...."}`
- `queries` file: a `.jsonl` file (jsonlines) that contains a list of dictionaries, each with two fields `_id` with unique query identifier and `text` with query text. For example: `{"_id": "q1", "text": "Who developed the mass-energy equivalence formula?"}`
- `qrels` file: a `.tsv` file (tab-seperated) that contains three columns, i.e. the `query-id`, `corpus-id` and `score` in this order. Keep 1st row as header. For example: `q1 doc1 1`
### Data Instances
A high level example of any beir dataset:
```python
corpus = {
"doc1" : {
"title": "Albert Einstein",
"text": "Albert Einstein was a German-born theoretical physicist. who developed the theory of relativity, \
one of the two pillars of modern physics (alongside quantum mechanics). His work is also known for \
its influence on the philosophy of science. He is best known to the general public for his mass–energy \
equivalence formula E = mc2, which has been dubbed 'the world's most famous equation'. He received the 1921 \
Nobel Prize in Physics 'for his services to theoretical physics, and especially for his discovery of the law \
of the photoelectric effect', a pivotal step in the development of quantum theory."
},
"doc2" : {
"title": "", # Keep title an empty string if not present
"text": "Wheat beer is a top-fermented beer which is brewed with a large proportion of wheat relative to the amount of \
malted barley. The two main varieties are German Weißbier and Belgian witbier; other types include Lambic (made\
with wild yeast), Berliner Weisse (a cloudy, sour beer), and Gose (a sour, salty beer)."
},
}
queries = {
"q1" : "Who developed the mass-energy equivalence formula?",
"q2" : "Which beer is brewed with a large proportion of wheat?"
}
qrels = {
"q1" : {"doc1": 1},
"q2" : {"doc2": 1},
}
```
### Data Fields
Examples from all configurations have the following features:
### Corpus
- `corpus`: a `dict` feature representing the document title and passage text, made up of:
- `_id`: a `string` feature representing the unique document id
- `title`: a `string` feature, denoting the title of the document.
- `text`: a `string` feature, denoting the text of the document.
### Queries
- `queries`: a `dict` feature representing the query, made up of:
- `_id`: a `string` feature representing the unique query id
- `text`: a `string` feature, denoting the text of the query.
### Qrels
- `qrels`: a `dict` feature representing the query document relevance judgements, made up of:
- `_id`: a `string` feature representing the query id
- `_id`: a `string` feature, denoting the document id.
- `score`: a `int32` feature, denoting the relevance judgement between query and document.
### Data Splits
| Dataset | Website| BEIR-Name | Type | Queries | Corpus | Rel D/Q | Down-load | md5 |
| -------- | -----| ---------| --------- | ----------- | ---------| ---------| :----------: | :------:|
| MSMARCO | [Homepage](https://microsoft.github.io/msmarco/)| ``msmarco`` | ``train``<br>``dev``<br>``test``| 6,980 | 8.84M | 1.1 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/msmarco.zip) | ``444067daf65d982533ea17ebd59501e4`` |
| TREC-COVID | [Homepage](https://ir.nist.gov/covidSubmit/index.html)| ``trec-covid``| ``test``| 50| 171K| 493.5 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/trec-covid.zip) | ``ce62140cb23feb9becf6270d0d1fe6d1`` |
| NFCorpus | [Homepage](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/) | ``nfcorpus`` | ``train``<br>``dev``<br>``test``| 323 | 3.6K | 38.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nfcorpus.zip) | ``a89dba18a62ef92f7d323ec890a0d38d`` |
| BioASQ | [Homepage](http://bioasq.org) | ``bioasq``| ``train``<br>``test`` | 500 | 14.91M | 8.05 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#2-bioasq) |
| NQ | [Homepage](https://ai.google.com/research/NaturalQuestions) | ``nq``| ``train``<br>``test``| 3,452 | 2.68M | 1.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nq.zip) | ``d4d3d2e48787a744b6f6e691ff534307`` |
| HotpotQA | [Homepage](https://hotpotqa.github.io) | ``hotpotqa``| ``train``<br>``dev``<br>``test``| 7,405 | 5.23M | 2.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/hotpotqa.zip) | ``f412724f78b0d91183a0e86805e16114`` |
| FiQA-2018 | [Homepage](https://sites.google.com/view/fiqa/) | ``fiqa`` | ``train``<br>``dev``<br>``test``| 648 | 57K | 2.6 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fiqa.zip) | ``17918ed23cd04fb15047f73e6c3bd9d9`` |
| Signal-1M(RT) | [Homepage](https://research.signal-ai.com/datasets/signal1m-tweetir.html)| ``signal1m`` | ``test``| 97 | 2.86M | 19.6 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#4-signal-1m) |
| TREC-NEWS | [Homepage](https://trec.nist.gov/data/news2019.html) | ``trec-news`` | ``test``| 57 | 595K | 19.6 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#1-trec-news) |
| ArguAna | [Homepage](http://argumentation.bplaced.net/arguana/data) | ``arguana``| ``test`` | 1,406 | 8.67K | 1.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/arguana.zip) | ``8ad3e3c2a5867cdced806d6503f29b99`` |
| Touche-2020| [Homepage](https://webis.de/events/touche-20/shared-task-1.html) | ``webis-touche2020``| ``test``| 49 | 382K | 19.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/webis-touche2020.zip) | ``46f650ba5a527fc69e0a6521c5a23563`` |
| CQADupstack| [Homepage](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/) | ``cqadupstack``| ``test``| 13,145 | 457K | 1.4 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/cqadupstack.zip) | ``4e41456d7df8ee7760a7f866133bda78`` |
| Quora| [Homepage](https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs) | ``quora``| ``dev``<br>``test``| 10,000 | 523K | 1.6 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/quora.zip) | ``18fb154900ba42a600f84b839c173167`` |
| DBPedia | [Homepage](https://github.com/iai-group/DBpedia-Entity/) | ``dbpedia-entity``| ``dev``<br>``test``| 400 | 4.63M | 38.2 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/dbpedia-entity.zip) | ``c2a39eb420a3164af735795df012ac2c`` |
| SCIDOCS| [Homepage](https://allenai.org/data/scidocs) | ``scidocs``| ``test``| 1,000 | 25K | 4.9 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scidocs.zip) | ``38121350fc3a4d2f48850f6aff52e4a9`` |
| FEVER | [Homepage](http://fever.ai) | ``fever``| ``train``<br>``dev``<br>``test``| 6,666 | 5.42M | 1.2| [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/fever.zip) | ``5a818580227bfb4b35bb6fa46d9b6c03`` |
| Climate-FEVER| [Homepage](http://climatefever.ai) | ``climate-fever``|``test``| 1,535 | 5.42M | 3.0 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/climate-fever.zip) | ``8b66f0a9126c521bae2bde127b4dc99d`` |
| SciFact| [Homepage](https://github.com/allenai/scifact) | ``scifact``| ``train``<br>``test``| 300 | 5K | 1.1 | [Link](https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/scifact.zip) | ``5f7d1de60b170fc8027bb7898e2efca1`` |
| Robust04 | [Homepage](https://trec.nist.gov/data/robust/04.guidelines.html) | ``robust04``| ``test``| 249 | 528K | 69.9 | No | [How to Reproduce?](https://github.com/UKPLab/beir/blob/main/examples/dataset#3-robust04) |
## 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
[Needs More Information]
### Citation Information
Cite as:
```
@inproceedings{
thakur2021beir,
title={{BEIR}: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models},
author={Nandan Thakur and Nils Reimers and Andreas R{\"u}ckl{\'e} and Abhishek Srivastava and Iryna Gurevych},
booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
year={2021},
url={https://openreview.net/forum?id=wCu6T5xFjeJ}
}
```
### Contributions
Thanks to [@Nthakur20](https://github.com/Nthakur20) for adding this dataset. |
false | # Dataset Card for "stackoverflow_python_preprocessed"
This is a preprocessed version of the [stackoverflow_python] dataset.
Questions and answers were filtered to only include questions with more than 100 votes and answers with more than 5 votes.
The dataset has been converted from HTML to plain text and only includes the title, question, and answer columns.
## Additional Information
### License
All Stack Overflow user contributions are licensed under CC-BY-SA 3.0 with attribution required.
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) |
false |
# Dataset Card for LearningQ-qg
## Dataset Description
- **Repository:** [GitHub](https://github.com/AngusGLChen/LearningQ#readme)
- **Paper:** [LearningQ: A Large-scale Dataset for Educational Question Generation](https://ojs.aaai.org/index.php/ICWSM/article/view/14987/14837)
- **Point of Contact:** angus.glchen@gmail.com
### Dataset Summary
This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[English]
## 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
[More Information Needed] |
false |
# Dataset Card for "LegalLAMA"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Dataset Specifications](#supported-tasks-and-leaderboards)
## Dataset Description
- **Homepage:** https://github.com/coastalcph/lexlms
- **Repository:** https://github.com/coastalcph/lexlms
- **Paper:** https://arxiv.org/abs/2305.07507
- **Point of Contact:** [Ilias Chalkidis](mailto:ilias.chalkidis@di.ku.dk)
### Dataset Summary
LegalLAMA is a diverse probing benchmark suite comprising 8 sub-tasks that aims to assess the acquaintance of legal knowledge that PLMs acquired in pre-training.
### Dataset Specifications
| Corpus | Corpus alias | Examples | Avg. Tokens | Labels |
|--------------------------------------|----------------------|-----------|-------------|--------|
| Criminal Code Sections (Canada) | `canadian_sections` | 321 | 72 | 144 |
| Legal Terminology (EU) | `cjeu_term` | 2,127 | 164 | 23 |
| Contractual Section Titles (US) | `contract_sections` | 1,527 | 85 | 20 |
| Contract Types (US) | `contract_types` | 1,089 | 150 | 15 |
| ECHR Articles (CoE) | `ecthr_articles` | 5,072 | 69 | 13 |
| Legal Terminology (CoE) | `ecthr_terms` | 6,803 | 97 | 250 |
| Crime Charges (US) | `us_crimes` | 4,518 | 118 | 59 |
| Legal Terminology (US) | `us_terms` | 5,829 | 308 | 7 |
### Citation
[*Ilias Chalkidis\*, Nicolas Garneau\*, Catalina E.C. Goanta, Daniel Martin Katz, and Anders Søgaard.*
*LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development.*
*2022. In the Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics. Toronto, Canada.*](https://arxiv.org/abs/2305.07507)
```
@inproceedings{chalkidis-garneau-etal-2023-lexlms,
title = {{LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development}},
author = "Chalkidis*, Ilias and
Garneau*, Nicolas and
Goanta, Catalina and
Katz, Daniel Martin and
Søgaard, Anders",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics",
month = june,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/2305.07507",
}
``` |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.