text-classification bool 2 classes | text stringlengths 0 664k |
|---|---|
false |
# Dataset Card for MultiLegalPile: A Large-Scale Multilingual Corpus for the Legal Domain
## 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:** [Joel Niklaus](mailto:joel.niklaus.2@bfh.ch)
### Dataset Summary
The Multi_Legal_Pile is a large-scale multilingual legal dataset suited for pretraining language models.
It spans over 24 languages and five legal text types.
### Supported Tasks and Leaderboards
The dataset supports the tasks of fill-mask.
### Languages
The following languages are supported: bg, cs, da, de, el, en, es, et, fi, fr, ga, hr, hu, it, lt, lv, mt, nl, pl, pt,
ro, sk, sl, sv
## Dataset Structure
It is structured in the following format:
type -> language -> jurisdiction.jsonl.xz
type is one of the following:
- caselaw
- contracts
- legislation
- other
- mc4_legal
`mc4_legal` is a subset of the other type but is listed separately so it can be easily excluded since it is less
permissively licensed than the other types.
Use the dataset like this:
```python
from datasets import load_dataset
config = 'en_contracts' # {language}_{type}
dataset = load_dataset('joelito/Multi_Legal_Pile', config, split='train', streaming=True)
```
'config' is a combination of language and text_type, e.g. 'en_contracts' or 'de_caselaw'.
To load all the languages or all the text_types, use 'all' instead of the language or text_type (e.g., '
all_legislation').
### Data Instances
The file format is jsonl.xz and there is one split available ("train").
The complete dataset (689GB) consists of four large subsets:
- Native Multi Legal Pile (112GB)
- Eurlex Resources (179GB)
- Legal MC4 (106GB)
- Pile of Law (292GB)
#### Native Multilingual Legal Pile data
| | Language | Text Type | Jurisdiction | Source | Size (MB) | Words | Documents | Words/Document | URL | License |
|---:|:-----------|:------------|:---------------|:-----------------------------------|------------:|------------:|------------:|-----------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------|
| 0 | bg | legislation | Bulgaria | MARCELL | 8015 | 308946116 | 82777 | 3732 | https://elrc-share.eu/repository/browse/marcell-bulgarian-legislative-subcorpus-v2/946267fe8d8711eb9c1a00155d026706d2c9267e5cdf4d75b5f02168f01906c6/ | [CC0-1.0](https://elrc-share.eu/static/metashare/licences/CC0-1.0.pdf) |
| 1 | cs | caselaw | Czechia | CzCDC Constitutional Court | 11151 | 574336489 | 296652 | 1936 | https://lindat.mff.cuni.cz/repository/xmlui/handle/11372/LRT-3052 | [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) |
| 2 | cs | caselaw | Czechia | CzCDC Supreme Administrative Court | 11151 | 574336489 | 296652 | 1936 | https://lindat.mff.cuni.cz/repository/xmlui/handle/11372/LRT-3052 | [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) |
| 3 | cs | caselaw | Czechia | CzCDC Supreme Court | 11151 | 574336489 | 296652 | 1936 | https://lindat.mff.cuni.cz/repository/xmlui/handle/11372/LRT-3052 | [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) |
| 4 | da | caselaw | Denmark | DDSC | 3469 | 210730560 | 89702 | 2349 | https://huggingface.co/DDSC | [CC BY 4.0 and other, depending on the dataset](https://creativecommons.org/licenses/by-nc/4.0/) |
| 5 | da | legislation | Denmark | DDSC | 10736 | 653153146 | 265868 | 2456 | https://huggingface.co/DDSC | [CC BY 4.0 and other, depending on the dataset](https://creativecommons.org/licenses/by-nc/4.0/) |
| 6 | de | caselaw | Germany | openlegaldata | 31527 | 1785439383 | 596800 | 2991 | https://de.openlegaldata.io/ | [ODbL-1.0](https://opendatacommons.org/licenses/odbl/1-0/) |
| 7 | de | caselaw | Switzerland | entscheidsuche | 31527 | 1785439383 | 596800 | 2991 | https://entscheidsuche.ch/ | [See description](https://entscheidsuche.ch/dataUsage) |
| 8 | de | legislation | Germany | openlegaldata | 8934 | 512840663 | 276034 | 1857 | https://de.openlegaldata.io/ | [ODbL-1.0](https://opendatacommons.org/licenses/odbl/1-0/) |
| 9 | de | legislation | Switzerland | lexfind | 8934 | 512840663 | 276034 | 1857 | https://www.lexfind.ch/fe/de/search | No information provided |
| 10 | fr | caselaw | Switzerland | entscheidsuche | 18313 | 1170335690 | 435569 | 2686 | https://entscheidsuche.ch/ | [See description](https://entscheidsuche.ch/dataUsage) |
| 11 | fr | caselaw | Belgium | jurportal | 18313 | 1170335690 | 435569 | 2686 | https://juportal.be/home/welkom | [See description](https://juportal.be/home/disclaimer) |
| 12 | fr | caselaw | France | CASS | 18313 | 1170335690 | 435569 | 2686 | https://echanges.dila.gouv.fr/OPENDATA/CASS/ | [Open Licence 2.0](https://echanges.dila.gouv.fr/OPENDATA/CASS/DILA_CASS_Presentation_20170824.pdf) |
| 13 | fr | caselaw | Luxembourg | judoc | 18313 | 1170335690 | 435569 | 2686 | https://justice.public.lu/fr.html | [See description](https://justice.public.lu/fr/support/aspects-legaux/conditions-generales.html) |
| 14 | it | caselaw | Switzerland | entscheidsuche | 6483 | 406520336 | 156630 | 2595 | https://entscheidsuche.ch/ | [See description](https://entscheidsuche.ch/dataUsage) |
| 15 | en | legislation | Switzerland | lexfind | 36587 | 2537696894 | 657805 | 3857 | https://www.lexfind.ch/fe/de/search | No information provided |
| 16 | en | legislation | UK | uk-lex | 36587 | 2537696894 | 657805 | 3857 | https://zenodo.org/record/6355465 | [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/legalcode) |
| 17 | fr | legislation | Switzerland | lexfind | 9297 | 600170792 | 243313 | 2466 | https://www.lexfind.ch/fe/fr/search | No information provided |
| 18 | fr | legislation | Belgium | ejustice | 9297 | 600170792 | 243313 | 2466 | https://www.ejustice.just.fgov.be/cgi/welcome.pl | No information provided |
| 19 | it | legislation | Switzerland | lexfind | 8332 | 542579039 | 227968 | 2380 | https://www.lexfind.ch/fe/it/search | No information provided |
| 20 | nl | legislation | Belgium | ejustice | 8484 | 550788527 | 232204 | 2372 | https://www.ejustice.just.fgov.be/cgi/welcome.pl | No information provided |
| 21 | hu | legislation | Hungary | MARCELL | 5744 | 264572303 | 86862 | 3045 | https://elrc-share.eu/repository/browse/marcell-hungarian-legislative-subcorpus-v2/a87295ec8d6511eb9c1a00155d0267065f7e56dc7db34ce5aaae0b48a329daaa/ | [CC0-1.0](https://elrc-share.eu/static/metashare/licences/CC0-1.0.pdf) |
| 22 | pl | legislation | Poland | MARCELL | 5459 | 299334705 | 89264 | 3353 | https://elrc-share.eu/repository/browse/marcell-polish-legislative-subcorpus-v2/dd14fa1c8d6811eb9c1a00155d026706c4718ddc9c6e4a92a88923816ca8b219/ | [CC0-1.0](https://elrc-share.eu/static/metashare/licences/CC0-1.0.pdf) |
| 23 | pt | caselaw | Brazil | RulingBR | 196919 | 12611760973 | 17251236 | 731 | https://github.com/diego-feijo/rulingbr | No information provided |
| 24 | pt | caselaw | Brazil | CRETA | 196919 | 12611760973 | 17251236 | 731 | https://www.kaggle.com/datasets/eliasjacob/brcad5?resource=download&select=language_modeling_texts.parquet | [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) |
| 25 | pt | caselaw | Brazil | CJPG | 196919 | 12611760973 | 17251236 | 731 | https://esaj.tjsp.jus.br/cjsg/consultaCompleta.do?f=1 | No information provided |
| 26 | ro | legislation | Romania | MARCELL | 10464 | 559092153 | 215694 | 2592 | https://elrc-share.eu/repository/browse/marcell-romanian-legislative-subcorpus-v2/2da548428b9d11eb9c1a00155d026706ce94a6b59ffc4b0e9fb5cd9cebe6889e/ | [CC0-1.0](https://elrc-share.eu/static/metashare/licences/CC0-1.0.pdf) |
| 27 | sk | legislation | Slovakia | MARCELL | 5208 | 280182047 | 76760 | 3650 | https://elrc-share.eu/repository/browse/marcell-slovak-legislative-subcorpus-v2/6bdee1d68c8311eb9c1a00155d0267063398d3f1a3af40e1b728468dcbd6efdd/ | [CC0-1.0](https://elrc-share.eu/static/metashare/licences/CC0-1.0.pdf) |
| 28 | sl | legislation | Slovenia | MARCELL | 6057 | 365513763 | 88651 | 4123 | https://elrc-share.eu/repository/browse/marcell-slovenian-legislative-subcorpus-v2/e2a779868d4611eb9c1a00155d026706983c845a30d741b78e051faf91828b0d/ | [CC-BY-4.0](https://elrc-share.eu/static/metashare/licences/CC-BY-4.0.pdf)
| total | all | all | all | 1297609 | xxx | 81214262514 | 57305071 | 1417 | |
#### Eurlex Resources
See [Eurlex Resources](https://huggingface.co/datasets/joelito/eurlex_resources#data-instances) for more information.
#### Legal-MC4
See [Legal-MC4](https://huggingface.co/datasets/joelito/legal-mc4#data-instances) for more information.
#### Pile-of-Law
See [Pile-of-Law](https://huggingface.co/datasets/pile-of-law/pile-of-law#data-instances) for more information.
| Language | Type | Jurisdiction | Source | Size (MB) | Tokens | Documents | Tokens/Document | Part of Multi_Legal_Pile |
|:-----------|:------------|:---------------|:-------------------------------------|------------:|------------:|------------:|------------------:|:---------------------------|
| en | all | all | all | 503712 | 50547777921 | 9872444 | 5120 | yes |
| en | caselaw | EU | echr | 298 | 28374996 | 8480 | 3346 | yes |
| en | caselaw | Canada | canadian_decisions | 486 | 45438083 | 11343 | 4005 | yes |
| en | caselaw | US | dol_ecab | 942 | 99113541 | 28211 | 3513 | no |
| en | caselaw | US | scotus_oral_arguments | 1092 | 108228951 | 7996 | 13535 | no |
| en | caselaw | US | tax_rulings | 1704 | 166915887 | 54064 | 3087 | no |
| en | caselaw | US | nlrb_decisions | 2652 | 294471818 | 32080 | 9179 | no |
| en | caselaw | US | scotus_filings | 4018 | 593870413 | 63775 | 9311 | yes |
| en | caselaw | US | bva_opinions | 35238 | 4084140080 | 839523 | 4864 | no |
| en | caselaw | US | courtlistener_docket_entry_documents | 139006 | 12713614864 | 1983436 | 6409 | yes |
| en | caselaw | US | courtlistener_opinions | 158110 | 15899704961 | 4518445 | 3518 | yes |
| en | contracts | -- | tos | 4 | 391890 | 50 | 7837 | no |
| en | contracts | US | cfpb_creditcard_contracts | 188 | 25984824 | 2638 | 9850 | yes |
| en | contracts | US | edgar | 28698 | 2936402810 | 987926 | 2972 | yes |
| en | contracts | US | atticus_contracts | 78300 | 7997013703 | 650833 | 12287 | yes |
| en | legislation | US | fre | 2 | 173325 | 68 | 2548 | no |
| en | legislation | US | frcp | 4 | 427614 | 92 | 4647 | no |
| en | legislation | US | eoir | 62 | 6109737 | 2229 | 2741 | no |
| en | legislation | -- | constitutions | 66 | 5984865 | 187 | 32004 | yes |
| en | legislation | US | federal_register | 424 | 39854787 | 5414 | 7361 | yes |
| en | legislation | US | uscode | 716 | 78466325 | 58 | 1352867 | yes |
| en | legislation | EU | euro_parl | 808 | 71344326 | 9672 | 7376 | no |
| en | legislation | US | cfr | 1788 | 160849007 | 243 | 661930 | yes |
| en | legislation | US | us_bills | 3394 | 320723838 | 112483 | 2851 | yes |
| en | legislation | EU | eurlex | 3504 | 401324829 | 142036 | 2825 | no |
| en | legislation | US | state_codes | 18066 | 1858333235 | 217 | 8563747 | yes |
| en | other | -- | bar_exam_outlines | 4 | 346924 | 59 | 5880 | no |
| en | other | US | ftc_advisory_opinions | 4 | 509025 | 145 | 3510 | no |
| en | other | US | olc_memos | 98 | 12764635 | 1384 | 9223 | yes |
| en | other | -- | cc_casebooks | 258 | 24857378 | 73 | 340512 | no |
| en | other | -- | un_debates | 360 | 31152497 | 8481 | 3673 | no |
| en | other | -- | r_legaladvice | 798 | 72605386 | 146671 | 495 | no |
| en | other | US | founding_docs | 1118 | 100390231 | 183664 | 546 | no |
| en | other | US | oig | 5056 | 566782244 | 38954 | 14550 | yes |
| en | other | US | congressional_hearings | 16448 | 1801110892 | 31514 | 57152 | no |
### 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
```
TODO add citation
```
### Contributions
Thanks to [@JoelNiklaus](https://github.com/joelniklaus) for adding this dataset.
|
false | This is a repreprocessed version of the [FLAN dataset](https://arxiv.org/abs/2109.01652) with any updates that have been made to the FLAN datasets since the release of the original FLAN. The script is available [here](https://github.com/Muennighoff/FLAN).
Tasks:
```
{'aeslc_10templates',
'ag_news_subset_10templates',
'anli_r1_10templates',
'anli_r2_10templates',
'anli_r3_10templates',
'arc_challenge_10templates',
'arc_easy_10templates',
'bool_q_10templates',
'cb_10templates',
'cnn_dailymail_10templates',
'cola_10templates',
'common_gen_10templates',
'copa_10templates',
'coqa_10templates',
'cosmos_qa_10templates',
'dart_10templates',
'definite_pronoun_resolution_10templates',
'drop_10templates',
'e2e_nlg_10templates',
'fix_punct_10templates',
'gigaword_10templates',
'glue_mrpc_10templates',
'glue_qqp_10templates',
'hellaswag_10templates',
'imdb_reviews_10templates',
'math_dataset_10templates',
'mnli_matched_10templates',
'mnli_mismatched_10templates',
'multi_news_10templates',
'multirc_10templates',
'natural_questions_10templates',
'openbookqa_10templates',
'opinion_abstracts_idebate_10templates',
'opinion_abstracts_rotten_tomatoes_10templates',
'para_crawl_enes_10templates',
'paws_wiki_10templates',
'piqa_10templates',
'qnli_10templates',
'quac_10templates',
'record_10templates',
'rte_10templates',
'samsum_10templates',
'sentiment140_10templates',
'snli_10templates',
'squad_v1_10templates',
'squad_v2_10templates',
'sst2_10templates',
'story_cloze_10templates',
'stsb_10templates',
'trec_10templates',
'trivia_qa_10templates',
'true_case_10templates',
'web_nlg_en_10templates',
'wic_10templates',
'wiki_lingua_english_en_10templates',
'wmt14_enfr_10templates',
'wmt16_translate_csen_10templates',
'wmt16_translate_deen_10templates',
'wmt16_translate_fien_10templates',
'wmt16_translate_roen_10templates',
'wmt16_translate_ruen_10templates',
'wmt16_translate_tren_10templates',
'wnli_10templates',
'word_segment_10templates',
'wsc_10templates',
'yelp_polarity_reviews_10templates'}
``` |
false |
# Dataset Card for CUAD
## 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:** [Contract Understanding Atticus Dataset](https://www.atticusprojectai.org/cuad)
- **Repository:** [Contract Understanding Atticus Dataset](https://github.com/TheAtticusProject/cuad/)
- **Paper:** [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://arxiv.org/abs/2103.06268)
- **Point of Contact:** [Atticus Project Team](info@atticusprojectai.org)
### Dataset Summary
Contract Understanding Atticus Dataset (CUAD) v1 is a corpus of more than 13,000 labels in 510 commercial legal contracts that have been manually labeled to identify 41 categories of important clauses that lawyers look for when reviewing contracts in connection with corporate transactions.
CUAD is curated and maintained by The Atticus Project, Inc. to support NLP research and development in legal contract review. Analysis of CUAD can be found at https://arxiv.org/abs/2103.06268. Code for replicating the results and the trained model can be found at https://github.com/TheAtticusProject/cuad.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset contains samples in English only.
## Dataset Structure
### Data Instances
An example of 'train' looks as follows.
```
This example was too long and was cropped:
{
"answers": {
"answer_start": [44],
"text": ['DISTRIBUTOR AGREEMENT']
},
"context": 'EXHIBIT 10.6\n\n DISTRIBUTOR AGREEMENT\n\n THIS DISTRIBUTOR AGREEMENT (the "Agreement") is made by and between Electric City Corp., a Delaware corporation ("Company") and Electric City of Illinois LLC ("Distributor") this 7th day of September, 1999...',
"id": "LIMEENERGYCO_09_09_1999-EX-10-DISTRIBUTOR AGREEMENT__Document Name_0",
"question": "Highlight the parts (if any) of this contract related to "Document Name" that should be reviewed by a lawyer. Details: The name of the contract",
"title": "LIMEENERGYCO_09_09_1999-EX-10-DISTRIBUTOR AGREEMENT"
}
```
### Data Fields
- `id`: a `string` feature.
- `title`: a `string` feature.
- `context`: a `string` feature.
- `question`: a `string` feature.
- `answers`: a dictionary feature containing:
- `text`: a `string` feature.
- `answer_start`: a `int32` feature.
### Data Splits
This dataset is split into train/test set. Number of samples in each set is given below:
| | Train | Test |
| ----- | ------ | ---- |
| CUAD | 22450 | 4182 |
## Dataset Creation
### Curation Rationale
A highly valuable specialized task without a public large-scale dataset is contract review, which costs humans substantial time, money, and attention. Many law firms spend approximately 50% of their time reviewing contracts (CEB, 2017). Due to the specialized training necessary to understand and interpret contracts, the billing rates for lawyers at large law firms are typically around $500-$900 per hour in the US. As a result, many transactions cost companies hundreds of thousands of dollars just so that lawyers can verify that there are no problematic obligations or requirements included in the contracts. Contract review can be a source of drudgery and, in comparison to other legal tasks, is widely considered to be especially boring.
Contract review costs also affect consumers. Since contract review costs are so prohibitive, contract review is not often performed outside corporate transactions. Small companies and individuals consequently often sign contracts without even reading them, which can result in predatory behavior that harms consumers. Automating contract review by openly releasing high-quality data and fine-tuned models can increase access to legal support for small businesses and individuals, so that legal support is not exclusively available to wealthy companies.
To reduce the disparate societal costs of contract review, and to study how well NLP models generalize to specialized domains, the authors introduced a new large-scale dataset for contract review. As part of The Atticus Project, a non-profit organization of legal experts, CUAD is introduced, the Contract Understanding Atticus Dataset. This dataset was created with a year-long effort pushed forward by dozens of law student annotators, lawyers, and machine learning researchers. The dataset includes more than 500 contracts and more than 13,000 expert annotations that span 41 label categories. For each of 41 different labels, models must learn to highlight the portions of a contract most salient to that label. This makes the task a matter of finding needles in a haystack.
### Source Data
#### Initial Data Collection and Normalization
The CUAD includes commercial contracts selected from 25 different types of contracts based on the contract names as shown below. Within each type, the creators randomly selected contracts based on the names of the filing companies across the alphabet.
Type of Contracts: # of Docs
Affiliate Agreement: 10
Agency Agreement: 13
Collaboration/Cooperation Agreement: 26
Co-Branding Agreement: 22
Consulting Agreement: 11
Development Agreement: 29
Distributor Agreement: 32
Endorsement Agreement: 24
Franchise Agreement: 15
Hosting Agreement: 20
IP Agreement: 17
Joint Venture Agreemen: 23
License Agreement: 33
Maintenance Agreement: 34
Manufacturing Agreement: 17
Marketing Agreement: 17
Non-Compete/No-Solicit/Non-Disparagement Agreement: 3
Outsourcing Agreement: 18
Promotion Agreement: 12
Reseller Agreement: 12
Service Agreement: 28
Sponsorship Agreement: 31
Supply Agreement: 18
Strategic Alliance Agreement: 32
Transportation Agreement: 13
TOTAL: 510
#### Who are the source language producers?
The contracts were sourced from EDGAR, the Electronic Data Gathering, Analysis, and Retrieval system used at the U.S. Securities and Exchange Commission (SEC). Publicly traded companies in the United States are required to file certain contracts under the SEC rules. Access to these contracts is available to the public for free at https://www.sec.gov/edgar. Please read the Datasheet at https://www.atticusprojectai.org/ for information on the intended use and limitations of the CUAD.
### Annotations
#### Annotation process
The labeling process included multiple steps to ensure accuracy:
1. Law Student Training: law students attended training sessions on each of the categories that included a summary, video instructions by experienced attorneys, multiple quizzes and workshops. Students were then required to label sample contracts in eBrevia, an online contract review tool. The initial training took approximately 70-100 hours.
2. Law Student Label: law students conducted manual contract review and labeling in eBrevia.
3. Key Word Search: law students conducted keyword search in eBrevia to capture additional categories that have been missed during the “Student Label” step.
4. Category-by-Category Report Review: law students exported the labeled clauses into reports, review each clause category-by-category and highlight clauses that they believe are mislabeled.
5. Attorney Review: experienced attorneys reviewed the category-by-category report with students comments, provided comments and addressed student questions. When applicable, attorneys discussed such results with the students and reached consensus. Students made changes in eBrevia accordingly.
6. eBrevia Extras Review. Attorneys and students used eBrevia to generate a list of “extras”, which are clauses that eBrevia AI tool identified as responsive to a category but not labeled by human annotators. Attorneys and students reviewed all of the “extras” and added the correct ones. The process is repeated until all or substantially all of the “extras” are incorrect labels.
7. Final Report: The final report was exported into a CSV file. Volunteers manually added the “Yes/No” answer column to categories that do not contain an answer.
#### Who are the annotators?
Answered in above section.
### Personal and Sensitive Information
Some clauses in the files are redacted because the party submitting these contracts redacted them to protect confidentiality. Such redaction may show up as asterisks (\*\*\*) or underscores (\_\_\_) or blank spaces. The dataset and the answers reflect such redactions. For example, the answer for “January \_\_ 2020” would be “1/[]/2020”).
For any categories that require an answer of “Yes/No”, annotators include full sentences as text context in a contract. To maintain consistency and minimize inter-annotator disagreement, annotators select text for the full sentence, under the instruction of “from period to period”.
For the other categories, annotators selected segments of the text in the contract that are responsive to each such category. One category in a contract may include multiple labels. For example, “Parties” may include 4-10 separate text strings that are not continuous in a contract. The answer is presented in the unified format separated by semicolons of “Party A Inc. (“Party A”); Party B Corp. (“Party B”)”.
Some sentences in the files include confidential legends that are not part of the contracts. An example of such confidential legend is as follows:
THIS EXHIBIT HAS BEEN REDACTED AND IS THE SUBJECT OF A CONFIDENTIAL TREATMENT REQUEST. REDACTED MATERIAL IS MARKED WITH [* * *] AND HAS BEEN FILED SEPARATELY WITH THE SECURITIES AND EXCHANGE COMMISSION.
Some sentences in the files contain irrelevant information such as footers or page numbers. Some sentences may not be relevant to the corresponding category. Some sentences may correspond to a different category. Because many legal clauses are very long and contain various sub-parts, sometimes only a sub-part of a sentence is responsive to a category.
To address the foregoing limitations, annotators manually deleted the portion that is not responsive, replacing it with the symbol "<omitted>" to indicate that the two text segments do not appear immediately next to each other in the contracts. For example, if a “Termination for Convenience” clause starts with “Each Party may terminate this Agreement if” followed by three subparts “(a), (b) and (c)”, but only subpart (c) is responsive to this category, the authors manually deleted subparts (a) and (b) and replaced them with the symbol "<omitted>”. Another example is for “Effective Date”, the contract includes a sentence “This Agreement is effective as of the date written above” that appears after the date “January 1, 2010”. The annotation is as follows: “January 1, 2010 <omitted> This Agreement is effective as of the date written above.”
Because the contracts were converted from PDF into TXT files, the converted TXT files may not stay true to the format of the original PDF files. For example, some contracts contain inconsistent spacing between words, sentences and paragraphs. Table format is not maintained in the TXT files.
## 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
Attorney Advisors
Wei Chen, John Brockland, Kevin Chen, Jacky Fink, Spencer P. Goodson, Justin Haan, Alex Haskell, Kari Krusmark, Jenny Lin, Jonas Marson, Benjamin Petersen, Alexander Kwonji Rosenberg, William R. Sawyers, Brittany Schmeltz, Max Scott, Zhu Zhu
Law Student Leaders
John Batoha, Daisy Beckner, Lovina Consunji, Gina Diaz, Chris Gronseth, Calvin Hannagan, Joseph Kroon, Sheetal Sharma Saran
Law Student Contributors
Scott Aronin, Bryan Burgoon, Jigar Desai, Imani Haynes, Jeongsoo Kim, Margaret Lynch, Allison Melville, Felix Mendez-Burgos, Nicole Mirkazemi, David Myers, Emily Rissberger, Behrang Seraj, Sarahginy Valcin
Technical Advisors & Contributors
Dan Hendrycks, Collin Burns, Spencer Ball, Anya Chen
### Licensing Information
CUAD is licensed under the Creative Commons Attribution 4.0 (CC BY 4.0) license and free to the public for commercial and non-commercial use.
The creators make no representations or warranties regarding the license status of the underlying contracts, which are publicly available and downloadable from EDGAR.
Privacy Policy & Disclaimers
The categories or the contracts included in the dataset are not comprehensive or representative. The authors encourage the public to help improve them by sending them your comments and suggestions to info@atticusprojectai.org. Comments and suggestions will be reviewed by The Atticus Project at its discretion and will be included in future versions of Atticus categories once approved.
The use of CUAD is subject to their privacy policy https://www.atticusprojectai.org/privacy-policy and disclaimer https://www.atticusprojectai.org/disclaimer.
### Citation Information
```
@article{hendrycks2021cuad,
title={CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review},
author={Dan Hendrycks and Collin Burns and Anya Chen and Spencer Ball},
journal={arXiv preprint arXiv:2103.06268},
year={2021}
}
```
### Contributions
Thanks to [@bhavitvyamalik](https://github.com/bhavitvyamalik) for adding this dataset. |
false |
# Dataset Card for Gazeta
## 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://github.com/IlyaGusev/gazeta
- **Paper:** [Dataset for Automatic Summarization of Russian News](https://arxiv.org/abs/2006.11063)
- **Leaderboard:** https://paperswithcode.com/sota/text-summarization-on-gazeta
- **Point of Contact:** [Ilya Gusev](ilya.gusev@phystech.edu)
### Dataset Summary
Dataset for automatic summarization of Russian news. News and their summaries are from the Gazeta website. Summaries were parsed as the content of an HTML tag with “description” property. Additional selection of good summaries was performed. There are two versions of this dataset.
### Supported Tasks and Leaderboards
Leaderboard on Papers With Code: [text-summarization-on-gazeta](https://paperswithcode.com/sota/text-summarization-on-gazeta).
Please use the original [evaluation script](https://github.com/IlyaGusev/summarus/blob/master/evaluate.py) with the same parameters. Example:
```
python3 evaluate.py --predicted-path predictions.txt --gold-path targets.txt --language ru --tokenize-after --lower
```
### Languages
The dataset is in Russian.
### Usage
Loading version 1.0:
```python
from datasets import load_dataset
dataset = load_dataset('IlyaGusev/gazeta', revision="v1.0")
```
Loading version 2.0:
```python
from datasets import load_dataset
dataset = load_dataset('IlyaGusev/gazeta', revision="v2.0")
```
### Other datasets
Other Russian summarization datasets:
* Russian part of [XL-Sum](https://huggingface.co/datasets/csebuetnlp/xlsum), parsed from www.bbc.com/russian, 77803 samples
* Russian part of [MLSUM](https://huggingface.co/datasets/mlsum), parsed from www.mk.ru, 27063 samples
## Dataset Structure
### Data Instances
For each instance, there is a string for the article, a string for the summary, and a string for the url. Additionally, a string for the title and a date are provided.
```
{
'date': '2019-10-01 15:14:05',
'url': 'https://www.gazeta.ru/tech/2019/10/01/12698923/whatsapp_pls.shtml',
'title': 'На последнем издыхании: у кого отключится WhatsApp',
'summary': 'Мессенджер WhatsApp перестанет работать на ряде смартфонов — речь идет о гаджетах на базе операционных систем Android 2.3.7 и iOS 8, которые считаются устаревшими. В компании отмечают, что сервис на этих устройствах может отключиться в любой момент, поэтому будет целесообразно сменить устройство либо обновить ОС.',
'text': 'На официальном сайте мессенджера WhatsApp появилось сообщение о том, что с 1 февраля 2020 года сервис прекратит свою работу на некоторых устаревших смартфонах. Речь идет об устройствах, работающих на базе операционных систем Android 2.3.7 и iOS 8. При этом руководство WhatsApp предупреждает, что даже до обозначенного выше дедлайна функционал мессенджера на этих ОС может быть ограничен. «В связи с тем, что мы не планируем обновлять данные операционные системы, некоторые функции могут перестать работать на них в любое время», — говорится в пресс-релизе компании. Чтобы сохранить возможность пользоваться мессенджером без проблем, следует обновить версию прошивки или приобрести новое, более современное устройство. Сообщается, что на старых версиях операционных систем уже не получится завести новый аккаунт WhatsApp или верифицировать уже существующий. При этом в WhatsApp порекомендовали пользоваться устройствами с Android 4.0.3 и более поздними версиями, а также iOS 9 и более поздними версиями. Ранее стало известно о том, что с 31 декабря 2019 года WhatsApp прекращает поддержку устройств на базе операционной системы Windows Phone, от разработки которой пришлось отказаться. Впрочем, если верить статистике , эти меры вряд ли затронут большое количество пользователей. По состоянию на май 2019 года лишь 0,3% всех владельцев Android все еще пользуются ОС версий 2.3.3–2.3.7. Что же касается iOS, то версия под номером «10» или старше установлена на 5% устройств Apple. Как уже упоминалось выше, выпуск новых гаджетов на Windows Phone и вовсе прекращен ее создателем. В середине сентября экс-сотрудник АНБ Эдвард Сноуден раскритиковал WhatsApp за несовершенную систему защиты, порекомендовав политикам пользоваться другими средствами связи. Журналист французской радиостанции France Inter отметил, что президент Франции Эмманюэль Макрон для связи использует Telegram, а премьер-министр страны Эдуар Филипп — WhatsApp. Сноуден назвал такое решение «большой ошибкой», учитывая серьезные посты, которые занимают Макрон и Филипп. По словам Сноудена, эти сервисы безопаснее обычных SMS-сообщений, но все еще «чрезвычайно опасны, если вы премьер-министр». Больше всего претензий у информатора к WhatsApp, который стал частью активов корпорации Facebook в 2014 году. Эдвард Сноуден отметил, что после приобретения мессенджера Facebook «слой за слоем» снимает различные уровни защиты сервиса, чтобы при необходимости читать переписку своих пользователей. Ранее с критикой в адрес WhatsApp выступил и глава Telegram Павел Дуров. По словам предпринимателя, после устранения одной «дыры» в мессенджере тут же появляются новые. «Все выявленные проблемы позволяют вести слежку, выглядят и функционируют как бэкдоры», — заявил Дуров. При этом Дуров подчеркнул, что WhatsApp мог быть вынужден установить бэкдоры по указанию ФБР. В июне руководство WhatsApp заявило о том, что их сервис готов судиться с юзерами за нарушение правил пользования. В список нарушений входит использование программы «не в личных целях» и применение автоматической рассылки сообщений. По данным пресс-службы WhatsApp, уже сейчас обнаружены и заморожены «миллионы аккаунтов», пойманных на «злоупотреблении». «Наша платформа изначально создавалась, чтобы помогать людям общаться с их друзьями и любимыми... Используя информацию приложения, мы нашли и заблокировали миллионы злоупотребляющих аккаунтов от использования нашей сети», – заявили в WhatsApp. В частности, нарушение происходит, если компания публично заявляет о возможности использовать WhatsApp, нарушая при этом правила пользования мессенджером. «Ничто в этом объявлении не ограничивает право WhatsApp от применения своих условий с использованием технологий. Классификаторы на основе machine learning нам в этом помогают, и мы продолжим их использовать», – добавили в команде приложения.',
}
```
Some dataset statistics are below:
| Feature | Mean Token Count | Mean Sentence Count |
|:---------|:---------|--------------------------------------------------|
| Text | 767 | 37 |
| Summary | 50 | 3 |
### Data Splits
| Dataset Split | v1, Number of Instances in Split | v2, Number of Instances in Split |
|:---------|:---------|:---------|
| Train | 52,400 | 60,964 |
| Validation | 5,265 | 6,369 |
| Test | 5,770 | 6,793 |
## Dataset Creation
### Curation Rationale
When the first version of the dataset was collected, there were no other datasets for Russian text summarization. Even now, it is one of the few datasets for this task.
### Source Data
#### Initial Data Collection and Normalization
* The source of data is the [Gazeta](https://www.gazeta.ru/) website.
* Parsing scripts are [here](https://github.com/IlyaGusev/gazeta/tree/master/parser).
* Cleaning and normalization Colab notebook is [here](https://colab.research.google.com/drive/1Ed_chVrslp_7vJNS3PmRC0_ZJrRQYv0C)
#### Who are the source language producers?
Texts and summaries were written by journalists at [Gazeta](https://www.gazeta.ru/).
### Annotations
#### Annotation process
[N/A]
#### Who are the annotators?
[N/A]
### Personal and Sensitive Information
The dataset is not anonymized, so individuals' names can be found in the dataset. Information about the original author is not included in the dataset.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
It is a dataset from a single source. Thus it has a constrained text style and event perspective.
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The data was collected by Ilya Gusev.
### Licensing Information
Legal basis for distribution of the dataset: https://www.gazeta.ru/credits.shtml, paragraph 2.1.2. All rights belong to "www.gazeta.ru". Usage of this dataset is possible only for personal purposes on a non-commercial basis.
### Citation Information
```bibtex
@InProceedings{10.1007/978-3-030-59082-6_9,
author="Gusev, Ilya",
editor="Filchenkov, Andrey and Kauttonen, Janne and Pivovarova, Lidia",
title="Dataset for Automatic Summarization of Russian News",
booktitle="Artificial Intelligence and Natural Language",
year="2020",
publisher="Springer International Publishing",
address="Cham",
pages="122--134",
isbn="978-3-030-59082-6"
}
```
### Contributions
[N/A] |
false |
# Dataset Card for Natural Questions
## 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://ai.google.com/research/NaturalQuestions/dataset](https://ai.google.com/research/NaturalQuestions/dataset)
- **Repository:** [https://github.com/google-research-datasets/natural-questions](https://github.com/google-research-datasets/natural-questions)
- **Paper:** [https://research.google/pubs/pub47761/](https://research.google/pubs/pub47761/)
- **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:** 45.07 GB
- **Size of the generated dataset:** 99.80 GB
- **Total amount of disk used:** 144.87 GB
### Dataset Summary
The NQ corpus contains questions from real users, and it requires QA systems to
read and comprehend an entire Wikipedia article that may or may not contain the
answer to the question. The inclusion of real user questions, and the
requirement that solutions should read an entire page to find the answer, cause
NQ to be a more realistic and challenging task than prior QA datasets.
### Supported Tasks and Leaderboards
[https://ai.google.com/research/NaturalQuestions](https://ai.google.com/research/NaturalQuestions)
### Languages
en
## Dataset Structure
### Data Instances
- **Size of downloaded dataset files:** 45.07 GB
- **Size of the generated dataset:** 99.80 GB
- **Total amount of disk used:** 144.87 GB
An example of 'train' looks as follows. This is a toy example.
```
{
"id": "797803103760793766",
"document": {
"title": "Google",
"url": "http://www.wikipedia.org/Google",
"html": "<html><body><h1>Google Inc.</h1><p>Google was founded in 1998 By:<ul><li>Larry</li><li>Sergey</li></ul></p></body></html>",
"tokens":[
{"token": "<h1>", "start_byte": 12, "end_byte": 16, "is_html": True},
{"token": "Google", "start_byte": 16, "end_byte": 22, "is_html": False},
{"token": "inc", "start_byte": 23, "end_byte": 26, "is_html": False},
{"token": ".", "start_byte": 26, "end_byte": 27, "is_html": False},
{"token": "</h1>", "start_byte": 27, "end_byte": 32, "is_html": True},
{"token": "<p>", "start_byte": 32, "end_byte": 35, "is_html": True},
{"token": "Google", "start_byte": 35, "end_byte": 41, "is_html": False},
{"token": "was", "start_byte": 42, "end_byte": 45, "is_html": False},
{"token": "founded", "start_byte": 46, "end_byte": 53, "is_html": False},
{"token": "in", "start_byte": 54, "end_byte": 56, "is_html": False},
{"token": "1998", "start_byte": 57, "end_byte": 61, "is_html": False},
{"token": "by", "start_byte": 62, "end_byte": 64, "is_html": False},
{"token": ":", "start_byte": 64, "end_byte": 65, "is_html": False},
{"token": "<ul>", "start_byte": 65, "end_byte": 69, "is_html": True},
{"token": "<li>", "start_byte": 69, "end_byte": 73, "is_html": True},
{"token": "Larry", "start_byte": 73, "end_byte": 78, "is_html": False},
{"token": "</li>", "start_byte": 78, "end_byte": 83, "is_html": True},
{"token": "<li>", "start_byte": 83, "end_byte": 87, "is_html": True},
{"token": "Sergey", "start_byte": 87, "end_byte": 92, "is_html": False},
{"token": "</li>", "start_byte": 92, "end_byte": 97, "is_html": True},
{"token": "</ul>", "start_byte": 97, "end_byte": 102, "is_html": True},
{"token": "</p>", "start_byte": 102, "end_byte": 106, "is_html": True}
],
},
"question" :{
"text": "who founded google",
"tokens": ["who", "founded", "google"]
},
"long_answer_candidates": [
{"start_byte": 32, "end_byte": 106, "start_token": 5, "end_token": 22, "top_level": True},
{"start_byte": 65, "end_byte": 102, "start_token": 13, "end_token": 21, "top_level": False},
{"start_byte": 69, "end_byte": 83, "start_token": 14, "end_token": 17, "top_level": False},
{"start_byte": 83, "end_byte": 92, "start_token": 17, "end_token": 20 , "top_level": False}
],
"annotations": [{
"id": "6782080525527814293",
"long_answer": {"start_byte": 32, "end_byte": 106, "start_token": 5, "end_token": 22, "candidate_index": 0},
"short_answers": [
{"start_byte": 73, "end_byte": 78, "start_token": 15, "end_token": 16, "text": "Larry"},
{"start_byte": 87, "end_byte": 92, "start_token": 18, "end_token": 19, "text": "Sergey"}
],
"yes_no_answer": -1
}]
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `id`: a `string` feature.
- `document` a dictionary feature containing:
- `title`: a `string` feature.
- `url`: a `string` feature.
- `html`: a `string` feature.
- `tokens`: a dictionary feature containing:
- `token`: a `string` feature.
- `is_html`: a `bool` feature.
- `start_byte`: a `int64` feature.
- `end_byte`: a `int64` feature.
- `question`: a dictionary feature containing:
- `text`: a `string` feature.
- `tokens`: a `list` of `string` features.
- `long_answer_candidates`: a dictionary feature containing:
- `start_token`: a `int64` feature.
- `end_token`: a `int64` feature.
- `start_byte`: a `int64` feature.
- `end_byte`: a `int64` feature.
- `top_level`: a `bool` feature.
- `annotations`: a dictionary feature containing:
- `id`: a `string` feature.
- `long_answers`: a dictionary feature containing:
- `start_token`: a `int64` feature.
- `end_token`: a `int64` feature.
- `start_byte`: a `int64` feature.
- `end_byte`: a `int64` feature.
- `candidate_index`: a `int64` feature.
- `short_answers`: a dictionary feature containing:
- `start_token`: a `int64` feature.
- `end_token`: a `int64` feature.
- `start_byte`: a `int64` feature.
- `end_byte`: a `int64` feature.
- `text`: a `string` feature.
- `yes_no_answer`: a classification label, with possible values including `NO` (0), `YES` (1).
### Data Splits
| name | train | validation |
|---------|-------:|-----------:|
| default | 307373 | 7830 |
| dev | N/A | 7830 |
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[Creative Commons Attribution-ShareAlike 3.0 Unported](https://creativecommons.org/licenses/by-sa/3.0/).
### Citation Information
```
@article{47761,
title = {Natural Questions: a Benchmark for Question Answering Research},
author = {Tom Kwiatkowski and Jennimaria Palomaki and Olivia Redfield and Michael Collins and Ankur Parikh and Chris Alberti and Danielle Epstein and Illia Polosukhin and Matthew Kelcey and Jacob Devlin and Kenton Lee and Kristina N. Toutanova and Llion Jones and Ming-Wei Chang and Andrew Dai and Jakob Uszkoreit and Quoc Le and Slav Petrov},
year = {2019},
journal = {Transactions of the Association of Computational Linguistics}
}
```
### Contributions
Thanks to [@thomwolf](https://github.com/thomwolf), [@lhoestq](https://github.com/lhoestq) for adding this dataset. |
false |
> This dataset is identical to **[cdminix/libritts-aligned](https://huggingface.co/datasets/cdminix/libritts-aligned)** except it uses the newly released LibriTTS-R corpus. Please cite **[Y. Koizumi, et al., "LibriTTS-R: Restoration of a Large-Scale Multi-Speaker TTS Corpus", Interspeech 2023](https://google.github.io/df-conformer/librittsr/)**
*When using this dataset to download LibriTTS-R, make sure you agree to the terms on https://www.openslr.org*
# Dataset Card for LibriTTS-R with Forced Alignments (and Measures)
This dataset downloads LibriTTS-R 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)
*Note: version >=0.0.15 of alignments is required for this corpus*
## 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-R please cite the following papers:
- [LibriTTS-R: Restoration of a Large-Scale Multi-Speaker TTS Corpus](https://google.github.io/df-conformer/librittsr/)
- [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 |
# Dataset Card for [Dataset Name]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [SPECIES](https://species.jensenlab.org/)
- **Repository:**
- **Paper:** https://doi.org/10.1371/journal.pone.0065390
- **Leaderboard:**
- **Point of Contact:** [Lars Juhl Jensen](mailto:lars.juhl.jensen@cpr.ku.dk)
### Dataset Summary
S800 Corpus: a novel abstract-based manually annotated corpus. S800 comprises 800 PubMed abstracts in which organism mentions were identified and mapped to the corresponding NCBI Taxonomy identifiers.
To increase the corpus taxonomic mention diversity the S800 abstracts were collected by selecting 100 abstracts from the following 8 categories: bacteriology, botany, entomology, medicine, mycology, protistology, virology and zoology. S800 has been annotated with a focus at the species level; however, higher taxa mentions (such as genera, families and orders) have also been considered.
The Species-800 dataset was pre-processed and split based on the dataset of Pyysalo (https://github.com/spyysalo/s800).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English (`en`).
## Dataset Structure
### Data Instances
```
{'id': '0',
'tokens': ['Methanoregula',
'formicica',
'sp',
'.',
'nov',
'.',
',',
'a',
'methane',
'-',
'producing',
'archaeon',
'isolated',
'from',
'methanogenic',
'sludge',
'.'],
'ner_tags': [1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]}
```
### Data Fields
- `id`: Sentence identifier.
- `tokens`: Array of tokens composing a sentence.
- `ner_tags`: Array of tags, where `0` indicates no species mentioned, `1` signals the first token of a species and `2` the subsequent tokens of the species.
### 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
The species-level S800 corpus is subject to Medline restrictions.
### Citation Information
Original data:
```
@article{pafilis2013species,
title={The SPECIES and ORGANISMS resources for fast and accurate identification of taxonomic names in text},
author={Pafilis, Evangelos and Frankild, Sune P and Fanini, Lucia and Faulwetter, Sarah and Pavloudi, Christina and Vasileiadou, Aikaterini and Arvanitidis, Christos and Jensen, Lars Juhl},
journal={PloS one},
volume={8},
number={6},
pages={e65390},
year={2013},
publisher={Public Library of Science}
}
```
Source data of this dataset:
```
@article{10.1093/bioinformatics/btz682,
author = {Lee, Jinhyuk and Yoon, Wonjin and Kim, Sungdong and Kim, Donghyeon and Kim, Sunkyu and So, Chan Ho and Kang, Jaewoo},
title = "{BioBERT: a pre-trained biomedical language representation model for biomedical text mining}",
journal = {Bioinformatics},
volume = {36},
number = {4},
pages = {1234-1240},
year = {2019},
month = {09},
issn = {1367-4803},
doi = {10.1093/bioinformatics/btz682},
url = {https://doi.org/10.1093/bioinformatics/btz682},
eprint = {https://academic.oup.com/bioinformatics/article-pdf/36/4/1234/48983216/bioinformatics\_36\_4\_1234.pdf},
}
```
and
```
https://github.com/spyysalo/s800
```
### Contributions
Thanks to [@edugp](https://github.com/edugp) for adding this dataset. |
false |
# Dataset Card for ASCEND
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Usage](#usage)
- [Dataset Structure](#dataset-structure)
- [Data Splits](#data-instances)
- [Additional Information](#additional-information)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** [Needs More Information]
- **Repository:** [Needs More Information]
- **Paper:** https://arxiv.org/abs/2112.06223
- **Leaderboard:** [Needs More Information]
- **Point of Contact:** [Needs More Information]
### Dataset Summary
ASCEND (A Spontaneous Chinese-English Dataset) introduces a high-quality resource of spontaneous multi-turn conversational dialogue Chinese-English code-switching corpus collected in Hong Kong. ASCEND consists of 10.62 hours of spontaneous speech with a total of ~12.3K utterances. The corpus is split into 3 sets: training, validation, and test with a ratio of 8:1:1 while maintaining a balanced gender proportion on each set.
### Supported Tasks and Leaderboards
Code-switching
### Languages
Chinese and English
## Usage
To obtain the full dataset (complete with train, validation, and test set), simply run this:
```
import datasets
dataset = datasets.load_dataset("CAiRE/ASCEND")
```
## Dataset Structure
A typical data point comprises the path to the audio file, the loaded audio array, and its transcription. Additional fields include datapoint id, duration, language, speaker id, session id, and topic.
```
{
'id': '00644',
'path': '.cache/huggingface/datasets/downloads/extracted/f0b33b5266cd9452ee310eef3577cf7adb7f29aa54dbff74b9a8ee406a55d614/waves/ses2_spk3_L13101_189.900_5.490.wav',
'audio': {
'path': '.cache/huggingface/datasets/downloads/extracted/f0b33b5266cd9452ee310eef3577cf7adb7f29aa54dbff74b9a8ee406a55d614/waves/ses2_spk3_L13101_189.900_5.490.wav',
'array': array([-6.1035156e-05, -1.8310547e-04, 3.0517578e-05, ...,
0.0000000e+00, -3.0517578e-05, 0.0000000e+00
], dtype = float32),
'sampling_rate': 16000
},
'transcription': '因为你不可能邀你的female friends去说走我们去play basketball',
'duration': 5.489999771118164,
'language': 'mixed',
'original_speaker_id': 3,
'session_id': 2,
'topic': 'sports'
}
```
### Data Splits
Number of utterances: 9,869 train, 1,130 validation, and 1,315 test.
## Additional Information
For comprehensive explanations, please check [our paper](https://arxiv.org/pdf/2112.06223.pdf).
### Licensing Information
Creative Common Attribution Share-Alike 4.0 International (CC-BY-SA 4.0)
### Citation Information
If you use our dataset, please cite us:
```
@inproceedings{lovenia2022ascend,
title={ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation},
author={Lovenia, Holy and Cahyawijaya, Samuel and Winata, Genta Indra and Xu, Peng and Yan, Xu and Liu, Zihan and Frieske, Rita and Yu, Tiezheng and Dai, Wenliang and Barezi, Elham J and others},
booktitle={Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
year={2022}
``` |
false |
The YouTube transcriptions dataset contains technical tutorials (currently from [James Briggs](https://www.youtube.com/c/jamesbriggs), [Daniel Bourke](https://www.youtube.com/channel/UCr8O8l5cCX85Oem1d18EezQ), and [AI Coffee Break](https://www.youtube.com/c/aicoffeebreak)) transcribed using [OpenAI's Whisper](https://huggingface.co/openai/whisper-large) (large). Each row represents roughly a sentence-length chunk of text alongside the video URL and timestamp.
Note that each item in the dataset contains just a short chunk of text. For most use cases you will likely need to merge multiple rows to create more substantial chunks of text, if you need to do that, this code snippet will help:
```python
from datasets import load_dataset
# first download the dataset
data = load_dataset(
'jamescalam/youtube-transcriptions',
split='train'
)
new_data = [] # this will store adjusted data
window = 6 # number of sentences to combine
stride = 3 # number of sentences to 'stride' over, used to create overlap
for i in range(0, len(data), stride):
i_end = min(len(data)-1, i+window)
if data[i]['title'] != data[i_end]['title']:
# in this case we skip this entry as we have start/end of two videos
continue
# create larger text chunk
text = ' '.join(data[i:i_end]['text'])
# add to adjusted data list
new_data.append({
'start': data[i]['start'],
'end': data[i_end]['end'],
'title': data[i]['title'],
'text': text,
'id': data[i]['id'],
'url': data[i]['url'],
'published': data[i]['published']
})
``` |
false |
# Dataset Card for WIT
## 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:** [WIT homepage](https://github.com/google-research-datasets/wit)
- **Paper:** [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning
](https://arxiv.org/abs/2103.01913)
- **Leaderboard:** [WIT leaderboard](https://paperswithcode.com/sota/text-image-retrieval-on-wit) and [WIT Kaggle competition](https://www.kaggle.com/competitions/wikipedia-image-caption/leaderboard)
- **Point of Contact:** [Miriam Redi](mailto:miriam@wikimedia.org)
### Dataset Summary
Wikimedia's version of the Wikipedia-based Image Text (WIT) Dataset, a large multimodal multilingual dataset.
From the [official blog post](https://techblog.wikimedia.org/2021/09/09/the-wikipedia-image-caption-matching-challenge-and-a-huge-release-of-image-data-for-research/):
> The core training data is taken from the Wikipedia Image-Text (WIT) Dataset, a large curated set of more than 37 million image-text associations extracted from Wikipedia articles in 108 languages that was recently released by Google Research.
>
> The WIT dataset offers extremely valuable data about the pieces of text associated with Wikipedia images. However, due to licensing and data volume issues, the Google dataset only provides the image name and corresponding URL for download and not the raw image files.
>
> Getting easy access to the image files is crucial for participants to successfully develop competitive models. Therefore, today, the Wikimedia Research team is releasing its first large image dataset. It contains more than six million image files from Wikipedia articles in 100+ languages, which correspond to almost [1] all captioned images in the WIT dataset. Image files are provided at a 300-px resolution, a size that is suitable for most of the learning frameworks used to classify and analyze images.
> [1] We are publishing all images having a non-null “reference description” in the WIT dataset. For privacy reasons, we are not publishing images where a person is the primary subject, i.e., where a person’s face covers more than 10% of the image surface. To identify faces and their bounding boxes, we use the RetinaFace detector. In addition, to avoid the inclusion of inappropriate images or images that violate copyright constraints, we have removed all images that are candidate for deletion on Commons from the dataset.
**Note**: Compared to [Google's version](https://huggingface.co/datasets/google/wit), which has contents of one Wikipedia page per data sample, this version groups contents of all Wikipedia pages available in different languages for the image in one single data sample to avoid duplication of image bytes.
### Supported Tasks and Leaderboards
- `image-captioning`: This dataset can be used to train a model for image captioning where the goal is to predict a caption given the image.
- `text-retrieval`: The goal in this task is to build a model that retrieves the text (`caption_title_and_reference_description`) closest to an image. The leaderboard for this task can be found [here](https://paperswithcode.com/sota/text-image-retrieval-on-wit). This task also has a competition on [Kaggle](https://www.kaggle.com/c/wikipedia-image-caption).
In these tasks, any combination of the `caption_reference_description`, `caption_attribution_description` and `caption_alt_text_description` fields can be used as the input text/caption.
### Languages
The dataset contains examples from all Wikipedia languages.
## Dataset Structure
### Data Instances
Each instance is an image, its representation in bytes, a pre-computed embedding, and the set of captions attached to the image in Wikipedia.
```
{
'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=300x225 at 0x7F88F3876358>,
'image_url': 'https://upload.wikimedia.org/wikipedia/commons/8/8b/Scolopendra_gigantea.jpg',
'embedding': [1.4784087, 2.8710432, 0.0, 0.51603067, ..., 10.266883, 0.51142216, 0.0, 2.3464653],
'metadata_url': 'http://commons.wikimedia.org/wiki/File:Scolopendra_gigantea.jpg',
'original_height': 3000,
'original_width': 4000,
'mime_type': 'image/jpeg',
'caption_attribution_description': 'English: Puerto Rican Giant Centipede, Scolopendra gigantea; Vieques, Puerto Rico Slovenčina: Stonožka obrovská, Scolopendra gigantea; Vieques, Portoriko',
'wit_features': {
'language': ['ro', 'vi', 'sk', ..., 'nl', 'th', 'lv'],
'page_url': ['https://ro.wikipedia.org/wiki/Scolopendra_gigantea', 'https://vi.wikipedia.org/wiki/Scolopendra_gigantea', 'https://sk.wikipedia.org/wiki/Scolopendra_gigantea', ..., 'https://nl.wikipedia.org/wiki/Scolopendra_gigantea', 'https://th.wikipedia.org/wiki/%E0%B8%95%E0%B8%B0%E0%B8%82%E0%B8%B2%E0%B8%9A%E0%B8%A2%E0%B8%B1%E0%B8%81%E0%B8%A9%E0%B9%8C%E0%B8%82%E0%B8%B2%E0%B9%80%E0%B8%AB%E0%B8%A5%E0%B8%B7%E0%B8%AD%E0%B8%87%E0%B9%80%E0%B8%9B%E0%B8%A3%E0%B8%B9', 'https://lv.wikipedia.org/wiki/Skolopendru_dzimta'],
'attribution_passes_lang_id': [True, True, True, ..., True, True, True],
'caption_alt_text_description': [None, None, None, ..., 'Scolopendra gigantea', None, 'Milzu skolopendra (Scolopendra gigantea)'],
'caption_reference_description': [None, None, None, ..., None, None, 'Milzu skolopendra (Scolopendra gigantea)'],
'caption_title_and_reference_description': [None, 'Scolopendra gigantea [SEP] ', None, ..., 'Scolopendra gigantea [SEP] ', None, 'Skolopendru dzimta [SEP] Milzu skolopendra (Scolopendra gigantea)'],
'context_page_description': ['Scolopendra gigantea este un miriapod din clasa Chilopoda, fiind cel mai mare reprezentant al genului Scolopendra. Adultul poate atinge o lungime de 26 cm, uneori depășind 30 cm. Această specie habitează în regiunile de nord și de vest a Americii de Sud, pe insulele Trinidad, insulele Virgine, Jamaica Hispaniola ș.a. Localnicii denumesc scolopendra chilopodul gigant galben și chilopodul gigant amazonian.', 'Scolopendra gigantea là đại diện lớn nhất của chi Scolopendra nói riêng và cả lớp rết nói chung, thường đạt độ dài 26 cm và có thể vượt quá 30 cm. Sinh sống ở khu vực phía bắc và tây của Nam Mỹ và các đảo Trinidad, Puerto Rico, Saint Thomas, U.S. Virgin Islands, Jamaica, và Hispaniola.', 'Scolopendra gigantea, starší slovenský nazov: štípavica veľká, je živočích z rodu Scolopendra, s veľkosťou do 30 cm.', ..., 'Scolopendra gigantea is een tijgerduizendpoot uit Zuid-Amerika. De soort jaagt onder andere op grote geleedpotigen, amfibieën, reptielen en kleine zoogdieren. Het is voor zover bekend de grootste niet uitgestorven duizendpoot ter wereld.', 'ตะขาบยักษ์ขาเหลืองเปรู หรือ ตะขาบยักษ์อเมซอน เป็นตะขาบชนิดที่มีขนาดใหญ่ที่สุดในสกุล Scolopendra โดยปกติเมื่อโตเต็มที่จะยาว 26 เซนติเมตร แต่บางครั้งก็สามารถโตได้ถึง 30 เซนติเมตร ตะขาบชนิดนี้อาศัยอยู่ทางแถบเหนือและตะวันตกของทวีปอเมริกาใต้ และตามเกาะแก่งของประเทศตรินิแดดและจาไมกา เป็นสัตว์กินเนื้อ โดยกินจิ้งจก, กบ, นก, หนู และแม้แต่ค้างคาวเป็นอาหาร และขึ้นชื่อในเรื่องความดุร้าย', 'Skolpendru dzimta pieder pie simtkāju kārtas. Ap 400 dzimtas sugas sastopamas visā pasaulē, īpaši subtropu un tropu apgabalos. Mitinās augsnē, nobirušās lapās, plaisās, spraugās.'],
'context_section_description': [None, 'Scolopendra gigantea (còn được gọi là Rết chân vàng khổng lồ Peru và Rết khổng lồ Amazon) là đại diện lớn nhất của chi Scolopendra nói riêng và cả lớp rết nói chung, thường đạt độ dài 26\xa0cm (10\xa0in) và có thể vượt quá 30\xa0cm (12\xa0in). Sinh sống ở khu vực phía bắc và tây của Nam Mỹ và các đảo Trinidad, Puerto Rico, Saint Thomas, U.S. Virgin Islands, Jamaica, và Hispaniola.', None, ..., 'Scolopendra gigantea is een tijgerduizendpoot uit Zuid-Amerika. De soort jaagt onder andere op grote geleedpotigen, amfibieën, reptielen en kleine zoogdieren. Het is voor zover bekend de grootste niet uitgestorven duizendpoot ter wereld.', None, 'Skolpendru dzimta (Scolopendridae) pieder pie simtkāju kārtas. Ap 400 dzimtas sugas sastopamas visā pasaulē, īpaši subtropu un tropu apgabalos. Mitinās augsnē, nobirušās lapās, plaisās, spraugās.'],
'hierarchical_section_title': ['Scolopendra gigantea', 'Scolopendra gigantea', 'Scolopendra gigantea', ..., 'Scolopendra gigantea', 'ตะขาบยักษ์ขาเหลืองเปรู', 'Skolopendru dzimta'],
'is_main_image': [True, True, True, ..., True, True, True],
'page_title': ['Scolopendra gigantea', 'Scolopendra gigantea', 'Scolopendra gigantea', ..., 'Scolopendra gigantea', 'ตะขาบยักษ์ขาเหลืองเปรู', 'Skolopendru dzimta'],
'section_title': [None, None, None, ..., None, None, None]
}
}
```
**Note**: The dataset is stored in Parquet for better performance. This dataset was generated from the original files using [this script](wit_base/blob/main/scripts/wit.py). Additionally, 120 examples from the original files have incorrectly formatted one or more of the following fields: `original_height`, `original_width`, `mime_type` and `caption_attribution_description`. The fixed versions of these examples that were used in the generation script can be found [here](wit_base/blob/main/scripts/corrected_examples.py).
### Data Fields
- `image`: A `PIL.Image.Image` object containing the image resized to a width of 300-px while preserving its aspect ratio. Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `"image"` column, *i.e.* `dataset[0]["image"]` should **always** be preferred over `dataset["image"][0]`.
- `image_url`: URL to wikipedia image
- `embedding`: Precomputed image embedding. Each image is described with a 2048-dimensional signature extracted from the second-to-last layer of a [ResNet-50](https://arxiv.org/abs/1512.03385) neural network trained with [Imagenet](https://www.image-net.org/) data. These embeddings contain rich information about the image content and layout, in a compact form
- `metadata_url`: URL to wikimedia page containing the image and the metadata
- `original_height`: Original image height before resizing
- `original_width`: Original image width before resizing
- `mime_type`: Mime type associated to the image
- `caption_attribution_description`: This is the text found on the Wikimedia page of the image. This text is common to all occurrences of that image across all Wikipedias.
- `wit_features`: Sequence of captions for the image with language, page URL, information about the page, caption text, etc.
- `language`: Language code depicting wikipedia language of the page
- `page_url`: URL to wikipedia page
- `attribution_passes_lang_id`: Compared `language` field with the attribution language (written in the prefix of the attribution description.
- `caption_alt_text_description`: This is the “alt” text associated with the image. While not visible in general, it is commonly used for accessibility / screen readers
- `caption_reference_description`: This is the caption that is visible on the wikipedia page directly below the image.
- `caption_title_and_reference_description`: Concatenation of `page_title` and `caption_reference_description`.
- `context_page_description`: Corresponds to the short description of the page. It provides a concise explanation of the scope of the page.
- `context_section_description`: Text within the image's section
- `hierarchical_section_title`: Hierarchical section's title
- `is_main_image`: Flag determining if the image is the first image of the page. Usually displayed on the top-right part of the page when using web browsers.
- `page_changed_recently`: [More Information Needed]
- `page_title`: Wikipedia page's title
- `section_title`: Section's title
<p align='center'>
<img width='75%' src='https://production-media.paperswithcode.com/datasets/Screenshot_2021-03-04_at_14.26.02.png' alt="Half Dome" /> </br>
<b>Figure: WIT annotation example. </b>
</p>
Details on the field content can be found directly in the [paper, figure 5 and table 12.](https://arxiv.org/abs/2103.01913)
### Data Splits
All data is held in `train` split, with a total of 6477255 examples.
## Dataset Creation
### Curation Rationale
From the [official blog post](https://techblog.wikimedia.org/2021/09/09/the-wikipedia-image-caption-matching-challenge-and-a-huge-release-of-image-data-for-research/):
> The WIT dataset offers extremely valuable data about the pieces of text associated with Wikipedia images.
> Getting easy access to the image files is crucial for participants to successfully develop competitive models.
> With this large release of visual data, we aim to help the competition participants—as well as researchers and practitioners who are interested in working with Wikipedia images—find and download the large number of image files associated with the challenge, in a compact form.
### Source Data
#### Initial Data Collection and Normalization
From the [paper, section 3.1](https://arxiv.org/abs/2103.01913):
> We started with all Wikipedia content pages (i.e., ignoring other
pages that have discussions, comments and such). These number about ~124M pages across 279 languages.
#### Who are the source language producers?
Text was extracted from Wikipedia.
### Annotations
#### Annotation process
WIT was constructed using an automatic process. However it was human-validated.
From the [paper, section 3.7](https://arxiv.org/abs/2103.01913):
> To further verify the quality of the WIT dataset we performed a
study using (crowd-sourced) human annotators. As seen in Fig. 3,
we asked raters to answer 3 questions. Given an image and the page
title, raters first evaluate the quality of the attribution description
and reference description in the first two questions (order randomized). The third question understands the contextual quality of these
text descriptions given the page description and caption. Each response is on a 3-point scale: "Yes" if the text perfectly describes
the image, "Maybe" if it is sufficiently explanatory and "No" if it is
irrelevant or the image is inappropriate.
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
From the [official blog post](https://techblog.wikimedia.org/2021/09/09/the-wikipedia-image-caption-matching-challenge-and-a-huge-release-of-image-data-for-research/#FN1):
> For privacy reasons, we are not publishing images where a person is the primary subject, i.e., where a person’s face covers more than 10% of the image surface. To identify faces and their bounding boxes, we use the [RetinaFace](https://arxiv.org/abs/1905.00641) detector. In addition, to avoid the inclusion of inappropriate images or images that violate copyright constraints, we have removed all images that are [candidate for deletion](https://commons.wikimedia.org/wiki/Commons:Deletion_requests) on Commons from the dataset.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
From the [paper, section 3.4](https://arxiv.org/abs/2103.01913):
> Lastly we found that certain image-text pairs occurred very
frequently. These were often generic images that did not have
much to do with the main article page. Common examples
included flags, logos, maps, insignia and such. To prevent
biasing the data, we heavily under-sampled all such images
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Miriam Redi, Fabian Kaelin and Tiziano Piccardi.
### Licensing Information
[CC BY-SA 4.0 international license](https://creativecommons.org/licenses/by-sa/4.0/)
### Citation Information
```bibtex
@article{srinivasan2021wit,
title={WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning},
author={Srinivasan, Krishna and Raman, Karthik and Chen, Jiecao and Bendersky, Michael and Najork, Marc},
journal={arXiv preprint arXiv:2103.01913},
year={2021}
}
```
### Contributions
Thanks to [@nateraw](https://github.com/nateraw), [yjernite](https://github.com/yjernite) and [mariosasko](https://github.com/mariosasko) for adding this dataset. |
false |
# Dataset Card for YahooAnswersQa
## 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:** [Add homepage URL here if available (unless it's a GitHub repository)]()
- **Repository:** [If the dataset is hosted on github or has a github homepage, add URL here]()
- **Paper:** [If the dataset was introduced by a paper or there was a paper written describing the dataset, add URL here (landing page for Arxiv paper preferred)]()
- **Leaderboard:** [If the dataset supports an active leaderboard, add link here]()
- **Point of Contact:** [If known, name and email of at least one person the reader can contact for questions about the dataset.]()
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset. |
false | |
false |
# Dataset Card for EMEA
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://opus.nlpl.eu/EMEA.php
- **Repository:** None
- **Paper:** http://www.lrec-conf.org/proceedings/lrec2012/pdf/463_Paper.pdf
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [More Information Needed]
### Dataset Summary
To load a language pair which isn't part of the config, all you need to do is specify the language code as pairs.
You can find the valid pairs in Homepage section of Dataset Description: http://opus.nlpl.eu/EMEA.php
E.g.
`dataset = load_dataset("emea", lang1="en", lang2="nl")`
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
Here is an example of the `en-nl` configuration:
```
{'id': '4',
'translation': {'en': 'EPAR summary for the public',
'nl': 'EPAR-samenvatting voor het publiek'}}
```
### Data Fields
The data fields are:
- id: id of the sentence pair
- translation: a dictionary of the form {lang1: text_in_lang1, lang2: text_in_lang2}
### Data Splits
Sizes of some language pairs:
| name |train|
|----------|----:|
|bg-el|1044065|
|cs-et|1053164|
|de-mt|1000532|
|fr-sk|1062753|
|es-lt|1051370|
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```bibtex
@InProceedings{TIEDEMANN12.463,
author = {J{\"o}rg Tiedemann},
title = {Parallel Data, Tools and Interfaces in OPUS},
booktitle = {Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)},
year = {2012},
month = {may},
date = {23-25},
address = {Istanbul, Turkey},
editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Mehmet Ugur Dogan and Bente Maegaard and Joseph Mariani and Jan Odijk and Stelios Piperidis},
publisher = {European Language Resources Association (ELRA)},
isbn = {978-2-9517408-7-7},
language = {english}
}
```
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false |
# Dataset Card for "simple-wiki"
## 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://cs.pomona.edu/~dkauchak/simplification/](https://cs.pomona.edu/~dkauchak/simplification/)
- **Repository:** [More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
- **Paper:** [https://aclanthology.org/P11-2117/](https://aclanthology.org/P11-2117/)
- **Point of Contact:** [David Kauchak](dkauchak@cs.pomona.edu)
### Dataset Summary
This dataset contains pairs of equivalent sentences obtained from Wikipedia.
### Supported Tasks
- [Sentence Transformers](https://huggingface.co/sentence-transformers) training; useful for semantic search and sentence similarity.
### Languages
- English.
## Dataset Structure
Each example in the dataset contains pairs of equivalent sentences and is formatted as a dictionary with the key "set" and a list with the sentences as "value".
```
{"set": [sentence_1, sentence_2]}
{"set": [sentence_1, sentence_2]}
...
{"set": [sentence_1, sentence_2]}
```
This dataset is useful for training Sentence Transformers models. Refer to the following post on how to train models using similar sentences.
### Usage Example
Install the 🤗 Datasets library with `pip install datasets` and load the dataset from the Hub with:
```python
from datasets import load_dataset
dataset = load_dataset("embedding-data/simple-wiki")
```
The dataset is loaded as a `DatasetDict` and has the format:
```python
DatasetDict({
train: Dataset({
features: ['set'],
num_rows: 102225
})
})
```
Review an example `i` with:
```python
dataset["train"][i]["set"]
```
### Curation Rationale
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
#### Who are the source language producers?
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
### Annotations
#### Annotation process
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
#### Who are the annotators?
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
### Personal and Sensitive Information
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
### Discussion of Biases
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
### Other Known Limitations
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
## Additional Information
### Dataset Curators
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
### Licensing Information
[More Information Needed](https://cs.pomona.edu/~dkauchak/simplification/)
### Contributions
|
false |
# Dataset Card for Teyvat BLIP captions
Dataset used to train [Teyvat characters text to image model](https://github.com/hpcaitech/ColossalAI/tree/main/examples/images/diffusion).
BLIP generated captions for characters images from [genshin-impact fandom wiki](https://genshin-impact.fandom.com/wiki/Character#Playable_Characters)and [biligame wiki for genshin impact](https://wiki.biligame.com/ys/%E8%A7%92%E8%89%B2).
For each row the dataset contains `image` and `text` keys. `image` is a varying size PIL png, and `text` is the accompanying text caption. Only a train split is provided.
The `text` include the tag `Teyvat`, `Name`,`Element`, `Weapon`, `Region`, `Model type`, and `Description`, the `Description` is captioned with the [pre-trained BLIP model](https://github.com/salesforce/BLIP).
## Examples
<img src = "https://huggingface.co/datasets/Fazzie/Teyvat/resolve/main/data/Ganyu_001.png" title = "Ganyu_001.png" style="max-width: 20%;" >
> Teyvat, Name:Ganyu, Element:Cryo, Weapon:Bow, Region:Liyue, Model type:Medium Female, Description:an anime character with blue hair and blue eyes
<img src = "https://huggingface.co/datasets/Fazzie/Teyvat/resolve/main/data/Ganyu_002.png" title = "Ganyu_002.png" style="max-width: 20%;" >
> Teyvat, Name:Ganyu, Element:Cryo, Weapon:Bow, Region:Liyue, Model type:Medium Female, Description:an anime character with blue hair and blue eyes
<img src = "https://huggingface.co/datasets/Fazzie/Teyvat/resolve/main/data/Keqing_003.png" title = "Keqing_003.png" style="max-width: 20%;" >
> Teyvat, Name:Keqing, Element:Electro, Weapon:Sword, Region:Liyue, Model type:Medium Female, Description:a anime girl with long white hair and blue eyes
<img src = "https://huggingface.co/datasets/Fazzie/Teyvat/resolve/main/data/Keqing_004.png" title = "Keqing_004.png" style="max-width: 20%;" >
> Teyvat, Name:Keqing, Element:Electro, Weapon:Sword, Region:Liyue, Model type:Medium Female, Description:an anime character wearing a purple dress and cat ears |
true |
# Dataset Card for Headline Grouping (HLGD)
## 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/tingofurro/headline_grouping](https://github.com/tingofurro/headline_grouping)
- **Repository:** [https://github.com/tingofurro/headline_grouping](https://github.com/tingofurro/headline_grouping)
- **Paper:** [https://people.eecs.berkeley.edu/~phillab/pdfs/NAACL2021_HLG.pdf](https://people.eecs.berkeley.edu/~phillab/pdfs/NAACL2021_HLG.pdf)
- **Leaderboard:** N/A
- **Point of Contact:** phillab (at) berkeley (dot) edu
### Dataset Summary
HLGD is a binary classification dataset consisting of 20,056 labeled news headlines pairs indicating whether the two headlines describe the same underlying world event or not. The dataset comes with an existing split between `train`, `validation` and `test` (60-20-20).
### Supported Tasks and Leaderboards
The paper (NAACL2021) introducing HLGD proposes three challenges making use of various amounts of data:
- Challenge 1: Headline-only. Models must make predictions using only the text of both headlines.
- Challenge 2: Headline + Time. Models must make predictions using the headline and publication date of the two headlines.
- Challenge 3: Headline + Time + Other. Models can make predictions using the headline, publication date as well as any other relevant meta-data that can be obtained through the URL attached to the headline (full article content, authors, news source, etc.)
### Languages
Dataset is in english.
## Dataset Structure
### Data Instances
A typical dataset consists of a timeline_id, two headlines (A/B), each associated with a URL, and a date. Finally, a label indicates whether the two headlines describe the same underlying event (1) or not (0). Below is an example from the training set:
```
{'timeline_id': 4,
'headline_a': 'France fines Google nearly $57 million for first major violation of new European privacy regime',
'headline_b': "France hits Google with record EUR50mn fine over 'forced consent' data collection",
'date_a': '2019-01-21',
'date_b': '2019-01-21',
'url_a': 'https://www.chicagotribune.com/business/ct-biz-france-fines-google-privacy-20190121-story.html',
'url_b': 'https://www.rt.com/news/449369-france-hits-google-with-record-fine/',
'label': 1}
```
### Data Fields
- `timeline_id`: Represents the id of the timeline that the headline pair belongs to (values 0 to 9). The dev set is composed of timelines 0 and 5, and the test set timelines 7 and 8
- `headline_a`, `headline_b`: Raw text for the headline pair being compared
- `date_a`, `date_b`: Publication date of the respective headlines, in the `YYYY-MM-DD` format
- `url_a`, `url_b`: Original URL of the respective headlines. Can be used to retrieve additional meta-data on the headline.
- `label`: 1 if the two headlines are part of the the same headline group and describe the same underlying event, 0 otherwise.
### Data Splits
| | Train | Dev | Test |
| --------------------------- | ------- | ------ | ----- |
| Number of examples | 15,492 | 2,069 | 2,495 |
## Dataset Creation
### Curation Rationale
The task of grouping headlines from diverse news sources discussing a same underlying event is important to enable interfaces that can present the diversity of coverage of unfolding news events. Many news aggregators (such as Google or Yahoo news) present several sources for a given event, with an objective to highlight coverage diversity.
Automatic grouping of news headlines and articles remains challenging as headlines are short, heavily-stylized texts.
The HeadLine Grouping Dataset introduces the first benchmark to evaluate NLU model's ability to group headlines according to the underlying event they describe.
### Source Data
#### Initial Data Collection and Normalization
The data was obtained by collecting 10 news timelines from the NewsLens project by selecting timelines diversified in topic each contained between 80 and 300 news articles.
#### Who are the source language producers?
The source language producers are journalists or members of the newsroom of 34 news organizations listed in the paper.
### Annotations
#### Annotation process
Each timeline was annotated for group IDs by 5 independent annotators. The 5 annotations were merged into a single annotation named the global groups.
The global group IDs are then used to generate all pairs of headlines within timelines with binary labels: 1 if two headlines are part of the same global group, and 0 otherwise. A heuristic is used to remove negative examples to obtain a final dataset that has class imbalance of 1 positive example to 5 negative examples.
#### Who are the annotators?
Annotators were authors of the papers and 8 crowd-workers on the Upwork platform. The crowd-workers were native English speakers with experience either in proof-reading or data-entry.
### Personal and Sensitive Information
Annotators identity has been anonymized. Due to the public nature of news headline, it is not expected that the headlines will contain personal sensitive information.
## Considerations for Using the Data
### Social Impact of Dataset
The purpose of this dataset is to facilitate applications that present diverse news coverage.
By simplifying the process of developing models that can group headlines that describe a common event, we hope the community can build applications that show news readers diverse sources covering similar events.
We note however that the annotations were performed in majority by crowd-workers and that even though inter-annotator agreement was high, it was not perfect. Bias of the annotators therefore remains in the dataset.
### Discussion of Biases
There are several sources of bias in the dataset:
- Annotator bias: 10 annotators participated in the creation of the dataset. Their opinions and perspectives influenced the creation of the dataset.
- Subject matter bias: HLGD consists of headlines from 10 news timelines from diverse topics (space, tech, politics, etc.). This choice has an impact on the types of positive and negative examples that appear in the dataset.
- Source selection bias: 33 English-language news sources are represented in the dataset. This selection of news sources has an effect on the content in the timeline, and the overall dataset.
- Time-range of the timelines: the timelines selected range from 2010 to 2020, which has an influence on the language and style of news headlines.
### Other Known Limitations
For the task of Headline Grouping, inter-annotator agreement is high (0.814) but not perfect. Some decisions for headline grouping are subjective and depend on interpretation of the reader.
## Additional Information
### Dataset Curators
The dataset was initially created by Philippe Laban, Lucas Bandarkar and Marti Hearst at UC Berkeley.
### Licensing Information
The licensing status of the dataset depends on the legal status of news headlines. It is commonly held that News Headlines fall under "fair-use" ([American Bar blog post](https://www.americanbar.org/groups/gpsolo/publications/gp_solo/2011/september/fair_use_news_reviews/))
The dataset only distributes headlines, a URL and a publication date. Users of the dataset can then retrieve additional information (such as the body content, author, etc.) directly by querying the URL.
### Citation Information
```
@inproceedings{Laban2021NewsHG,
title={News Headline Grouping as a Challenging NLU Task},
author={Laban, Philippe and Bandarkar, Lucas and Hearst, Marti A},
booktitle={NAACL 2021},
publisher = {Association for Computational Linguistics},
year={2021}
}
```
### Contributions
Thanks to [@tingofurro](https://github.com/<tingofurro>) for adding this dataset. |
false |
# Dataset Card for Clean Italian mC4 🇮🇹
## Table of Contents
- [Dataset Card for Clean](#dataset-card-for-mc4)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Preprocessing](#preprocessing)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [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
- **Original Homepage:** [HF Hub](https://huggingface.co/datasets/allenai/c4)
- **Paper:** [ArXiv](https://arxiv.org/abs/1910.10683)
### Dataset Summary
A thoroughly cleaned version of the Italian split of the multilingual colossal, cleaned version of Common Crawl's web crawl corpus (mC4). Based on the [Common Crawl dataset](https://commoncrawl.org). The original version was prepared by [AllenAI](https://allenai.org/), hosted at the address [https://huggingface.co/datasets/allenai/c4](https://huggingface.co/datasets/allenai/c4), with subsequent preprocessing performed by [Gabriele Sarti](https://gsarti.com) following a standard procedure for all dataset shards.
### Preprocessing
The preprocessing of the dataset follows the procedure used by Yeb Havinga for training the model [`t5-base-dutch`](https://huggingface.co/flax-community/t5-base-dutch) on a portion of the cleaned Dutch split of mC4. The original code, that was adapted for Italian in this case, is available on [GitLab](https://gitlab.com/yhavinga/c4nlpreproc). In summary, the preprocessing procedure includes:
- Removing documents containing words from a selection of the [Italian and English List of Dirty Naught Obscene and Otherwise Bad Words](https://github.com/LDNOOBW/List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words).
- Removing sentences containing:
- Less than 3 words.
- A word longer than 1000 characters.
- An end symbol not matching end-of-sentence punctuation.
- Strings associated to javascript code (e.g. `{`), lorem ipsum, policy information in Italian or English.
- Removing documents (after sentence filtering):
- Containing less than 5 sentences.
- Containing less than 500 or more than 50'000 characters.
- Not identified as prevalently Italian by the `LangDetect` package.
Using parallel processing with 96 CPU cores on a TPUv3 via Google Cloud to perform the complete clean of all the original Italian shards of mC4 (1024 of ~220Mb train, 8 of ~24Mb validation) required roughly 10 hours due to the demanding steps of sentence tokenization and language detection. The total size of compressed `.json.gz` files is roughly halved after the procedure.
## Dataset Structure
### Data Instances
An example from the dataset:
```
{
'timestamp': '2020-02-22T22:24:31Z',
'url': 'https://altreconomia.it/una-rotonda-sul-pane/',
'text': 'Per raggiungere il campo attraversiamo la striscia d’asfalto che porta verso la provinciale numero 13. Mettiamo a rischio la nostra incolumità in un territorio di auto e camion. Sullo sfondo, i profili della Grigna e del Resegone. Più vicini, quelli del solito ipermercato di provincia, e delle villette a schiera che avanzano tra le coltivazioni. È lo sprawling, l’avanzata del cemento.\\nDa questo lato dalla strada, invece, è ancora regno contadino. Almeno per ora. Torniamo a Caponago (Mb), Brianza pura, dove ha avuto i natali il progetto “Spiga e madia”. Ne parlammo su Ae nel gennaio 2009: in un territorio “spaesato”, il Comitato “verso il Distretto di economia solidale della Brianza” (Desbri) e la “Retina” dei gruppi di acquisto locali danno vita a un progetto di produzione di frumento, molitura, panificazione e distribuzione in un raggio di 20 chilometri. Si comincia da zero, nel 2007, senza alcun di finanziamento, quando una famiglia del [...]. Il giochino vale almeno 3 miliardi di euro all’anno. La misura, introdotta in via straordinaria con la finanziaria 2005, è stata prorogata anche con l’ultimo decreto “milleproroghe”.'
}
```
### Data Fields
The data contains the following fields:
- `url`: url of the source as a string
- `text`: text content as a string
- `timestamp`: timestamp of extraction as a string
### Data Splits
To build mC4, the original authors used [CLD3](https://github.com/google/cld3) to identify over 100 languages. For Italian, the whole corpus of scraped text was divided in `1032` jsonl files, `1024` for training following the naming style `c4-it.tfrecord-0XXXX-of-01024.json.gz` and 8 for validation following the naming style `c4-it-validation.tfrecord-0000X-of-00008.json.gz`. The full set of preprocessed files takes roughly 215GB of disk space to download with Git LFS.
For ease of use under different storage capacities, the following incremental splits are available (sizes are estimates). **Important**: The sizes in GB represent the estimated weight for :
|split |train size (docs, words, download + preproc disk space)|validation size|
|:-----|------------------------------------------------------:|--------------:|
|tiny | 10M docs, 4B words (9 GB + 27 GB) | 12k docs |
|small | 20M docs, 8B words (18 GB + 54 GB) | 24k docs |
|medium| 50M docs, 20B words (47 GB + 135 GB) | 48k docs |
|large | 75M docs, 30B words (71 GB + 203 GB) | 72k docs |
|full | 103M docs, 41B words (109 GB + 279 GB) | 96k docs |
You can load any subset like this:
```python
from datasets import load_dataset
mc4_it_tiny = load_dataset("gsarti/clean_mc4_it", "tiny")
```
Since splits are quite large, you may want to traverse them using the streaming mode available starting from 🤗 Datasets v1.9.0:
```python
from datasets import load_dataset
mc4_it_full_stream = load_dataset("gsarti/clean_mc4_it", "full", split='train', streaming=True)
print(next(iter(mc4_it_full_stream))) # Prints the example presented above
```
## Dataset Creation
Refer to the original paper for more considerations regarding the choice of sources and the scraping process for creating `mC4`.
## Considerations for Using the Data
### Social Impact of Dataset
With more than 200GB of cleaned Italian text and more than 41B estimated words, this is by far the largest available corpus for the Italian language. The second largest dataset available is [OSCAR](https://oscar-corpus.com/), which is only 69GB in size for its deduplicated variant. Using this corpus for training language models with adequate computational resources will allow researchers to reach parity with the performances observed for the English language. This can in turn have important repercussions for the development of commercial language technology applications for the Italian language.
### Discussion of Biases
Despit the cleaning procedure aimed at removing vulgarity and profanity, it must be considered that model trained on this scraped corpus will inevitably reflect biases present in blog articles and comments on the Internet. This makes the corpus especially interesting in the context of studying data biases and how to limit their impacts.
## Additional Information
### Dataset Curators
Authors at AllenAI are the original curators for the `mc4` corpus. For inquiries or requests regarding the Italian cleaned portion contained in this repository, please contact me at [gabriele.sarti996@gmail.com](mailto:gabriele.sarti996@gmail.com)
### Licensing Information
AllenAI are releasing this dataset under the terms of ODC-BY. By using this, you are also bound by the Common Crawl terms of use in respect of the content contained in the dataset.
### Citation Information
If you use this dataset in your work, please cite us and the original mC4 authors as:
```
@article{sarti-nissim-2022-it5,
title={IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation},
author={Sarti, Gabriele and Nissim, Malvina},
journal={ArXiv preprint 2203.03759},
url={https://arxiv.org/abs/2203.03759},
year={2022},
month={mar}
}
@inproceedings{xue-etal-2021-mt5,
title = "m{T}5: A Massively Multilingual Pre-trained Text-to-Text Transformer",
author = "Xue, Linting and
Constant, Noah and
Roberts, Adam and
Kale, Mihir and
Al-Rfou, Rami and
Siddhant, Aditya and
Barua, Aditya and
Raffel, Colin",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.41",
doi = "10.18653/v1/2021.naacl-main.41",
pages = "483--498",
}
```
### Contributions
Thanks to [@dirkgr](https://github.com/dirkgr) and [@lhoestq](https://github.com/lhoestq) for adding this dataset.
|
false |
# Dataset Card for [Dataset Name]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [bprec homepage](https://clarin-pl.eu/dspace/handle/11321/736)
- **Repository:** [bprec repository](https://gitlab.clarin-pl.eu/team-semantics/semrel-extraction)
- **Paper:** [bprec paper](https://www.aclweb.org/anthology/2020.lrec-1.233.pdf)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
Brand-Product Relation Extraction Corpora in Polish
### Supported Tasks and Leaderboards
NER, Entity linking
### Languages
Polish
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
- id: int identifier of a text
- text: string text, for example a consumer comment on the social media
- ner: extracted entities and their relationship
- source and target: a pair of entities identified in the text
- from: int value representing starting character of the entity
- text: string value with the entity text
- to: int value representing end character of the entity
- type: one of pre-identified entity types:
- PRODUCT_NAME
- PRODUCT_NAME_IMP
- PRODUCT_NO_BRAND
- BRAND_NAME
- BRAND_NAME_IMP
- VERSION
- PRODUCT_ADJ
- BRAND_ADJ
- LOCATION
- LOCATION_IMP
### Data Splits
No train/validation/test split provided. Current dataset configurations point to 4 domain categories for the texts:
- tele
- electro
- cosmetics
- banking
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```
@inproceedings{inproceedings,
author = {Janz, Arkadiusz and Kopociński, Łukasz and Piasecki, Maciej and Pluwak, Agnieszka},
year = {2020},
month = {05},
pages = {},
title = {Brand-Product Relation Extraction Using Heterogeneous Vector Space Representations}
}
```
### Contributions
Thanks to [@kldarek](https://github.com/kldarek) for adding this dataset. |
false |
# Dataset Card for php
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://opus.nlpl.eu/PHP.php
- **Repository:** None
- **Paper:** http://www.lrec-conf.org/proceedings/lrec2012/pdf/463_Paper.pdf
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [More Information Needed]
### Dataset Summary
To load a language pair which isn't part of the config, all you need to do is specify the language code as pairs.
You can find the valid pairs in Homepage section of Dataset Description: http://opus.nlpl.eu/PHP.php
E.g.
`dataset = load_dataset("php", lang1="it", lang2="pl")`
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
Here are some examples of questions and facts:
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false |
# Dataset Card for tanzil
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://opus.nlpl.eu/Tanzil.php
- **Repository:** None
- **Paper:** http://www.lrec-conf.org/proceedings/lrec2012/pdf/463_Paper.pdf
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [More Information Needed]
### Dataset Summary
To load a language pair which isn't part of the config, all you need to do is specify the language code as pairs.
You can find the valid pairs in Homepage section of Dataset Description: http://opus.nlpl.eu/Tanzil.php
E.g.
`dataset = load_dataset("tanzil", lang1="en", lang2="ru")`
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
Here are some examples of questions and facts:
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
true |
# Dataset Card for sd-nlp
## Table of Contents
- [Dataset Card for [Dataset Name]](#dataset-card-for-dataset-name)
- [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://sourcedata.embo.org
- **Repository:** https://github.com/source-data/soda-roberta
- **Paper:**
- **Leaderboard:**
- **Point of Contact:** thomas.lemberger@embo.org
### Dataset Summary
This dataset is based on the content of the SourceData (https://sourcedata.embo.org) database, which contains manually annotated figure legends written in English and extracted from scientific papers in the domain of cell and molecular biology (Liechti et al, Nature Methods, 2017, https://doi.org/10.1038/nmeth.4471).
The dataset is pre-tokenized with the `roberta-base` tokenizer.
Additional details at https://github.com/source-data/soda-roberta
### Supported Tasks and Leaderboards
Tags are provided as [IOB2-style tags](https://en.wikipedia.org/wiki/Inside%E2%80%93outside%E2%80%93beginning_(tagging)).
`PANELIZATION`: figure captions (or figure legends) are usually composed of segments that each refer to one of several 'panels' of the full figure. Panels tend to represent results obtained with a coherent method and depicts data points that can be meaningfully compared to each other. `PANELIZATION` provide the start (B-PANEL_START) of these segments and allow to train for recogntion of the boundary between consecutive panel lengends.
`NER`: biological and chemical entities are labeled. Specifically the following entities are tagged:
- `SMALL_MOLECULE`: small molecules
- `GENEPROD`: gene products (genes and proteins)
- `SUBCELLULAR`: subcellular components
- `CELL`: cell types and cell lines.
- `TISSUE`: tissues and organs
- `ORGANISM`: species
- `EXP_ASSAY`: experimental assays
`ROLES`: the role of entities with regard to the causal hypotheses tested in the reported results. The tags are:
- `CONTROLLED_VAR`: entities that are associated with experimental variables and that subjected to controlled and targeted perturbations.
- `MEASURED_VAR`: entities that are associated with the variables measured and the object of the measurements.
`BORING`: entities are marked with the tag `BORING` when they are more of descriptive value and not directly associated with causal hypotheses ('boring' is not an ideal choice of word, but it is short...). Typically, these entities are so-called 'reporter' geneproducts, entities used as common baseline across samples, or specify the context of the experiment (cellular system, species, etc...).
### Languages
The text in the dataset is English.
## Dataset Structure
### Data Instances
```json
{
"tokens": [
"<s>", "Figure", "\u01205", ".", "\u0120Figure", "\u01205", ".", "A", "\u0120ER", "p", "57", "fl", "ox", "/", "fl", "ox", "\u0120mice", "\u0120were", "\u0120crossed", "\u0120with", "\u0120Nest", "in", "\u0120Cre", "\u0120trans", "genic", "\u0120mice", "\u0120to", "\u0120generate", "\u0120nervous", "\u0120system", "\u0120specific", "\u0120ER", "p", "57", "\u0120deficient", "\u0120animals", ".", "\u0120The", "\u0120levels", "\u0120of", "\u0120ER", "p", "57", "\u0120protein", "\u0120in", "\u0120the", "\u0120spinal", "\u0120cord", "\u0120were", "\u0120monitored", "\u0120by", "\u0120Western", "\u0120blot", ".", "\u0120ER", "p", "57", "WT", "\u0120(", "n", "=", "4", "),", "\u0120ER", "p", "57", "N", "es", "+", "/-", "\u0120(", "n", "=", "5", ")", "\u0120and", "\u0120ER", "p", "57", "N", "es", "-", "/-", "\u0120(", "n", "=", "4", ")", "\u0120mice", ".", "\u0120H", "SP", "90", "\u0120levels", "\u0120were", "\u0120determined", "\u0120as", "\u0120a", "\u0120loading", "\u0120control", ".", "\u0120Right", "\u0120panel", ":", "\u0120Quant", "ification", "\u0120of", "\u0120ER", "p", "57", "\u0120levels", "\u0120was", "\u0120performed", "\u0120relative", "\u0120to", "\u0120H", "sp", "90", "\u0120levels", ".", "\u0120B", "\u0120Body", "\u0120weight", "\u0120measurements", "\u0120were", "\u0120performed", "\u0120for", "\u0120indicated", "\u0120time", "\u0120points", "\u0120in", "\u0120ER", "p", "57", "WT", "\u0120(", "n", "=", "50", "),", "\u0120ER", "p", "57", "N", "es", "+", "/-", "\u0120(", "n", "=", "32", ")", "\u0120and", "\u0120ER", "p", "57", "N", "es", "-", "/-", "\u0120(", "n", "=", "19", ")", "\u0120mice", ".", "\u0120C", "\u0120Rot", "ar", "od", "\u0120performance", "\u0120was", "\u0120performed", "\u0120ER", "p", "57", "WT", "\u0120(", "n", "=", "20", "),", "\u0120ER", "p", "57", "N", "es", "+", "/-", "\u0120(", "n", "=", "15", ")", "\u0120and", "\u0120ER", "p", "57", "N", "es", "-", "/-", "\u0120(", "n", "=", "8", ")", "\u0120mice", ".", "\u0120D", "\u0120H", "anging", "\u0120test", "\u0120performance", "\u0120was", "\u0120assessed", "\u0120in", "\u0120ER", "p", "57", "WT", "\u0120(", "n", "=", "41", "),", "\u0120ER", "p", "57", "N", "es", "+", "/-", "\u0120(", "n", "=", "32", ")", "\u0120and", "\u0120ER", "p", "57", "N", "es", "-", "/-", "\u0120(", "n", "=", "12", ")", "\u0120mice", ".", "\u0120E", "\u0120Kaplan", "-", "Me", "ier", "\u0120survival", "\u0120curve", "\u0120for", "\u0120ER", "p", "57", "N", "es", "-", "/-", "\u0120mice", "\u0120(", "N", "\u0120=", "\u012019", ")", "\u0120that", "\u0120prematurely", "\u0120died", "\u0120or", "\u0120had", "\u0120to", "\u0120be", "\u0120sacrificed", "\u0120because", "\u0120of", "\u0120health", "\u0120reasons", "\u0120between", "\u0120the", "\u0120ages", "\u012022", "\u0120and", "\u012073", "\u0120days", ".", "\u0120Mean", "\u0120survival", "\u0120of", "\u0120this", "\u0120sub", "group", "\u0120of", "\u0120animals", "\u0120was", "\u012057", "\u0120days", ".", "\u0120ER", "p", "57", "WT", "\u0120(", "n", "=", "50", ")", "\u0120and", "\u0120ER", "p", "57", "N", "es", "+", "/-", "\u0120(", "n", "=", "32", ")", "\u0120mice", "\u0120are", "\u0120shown", "\u0120as", "\u0120a", "\u0120reference", ".", "\u0120F", "\u0120Hist", "ological", "\u0120analysis", "\u0120of", "\u0120Ne", "u", "N", "\u0120and", "\u0120GF", "AP", "\u0120st", "aining", "\u0120was", "\u0120performed", "\u0120in", "\u0120spinal", "\u0120cord", "\u0120tissue", "\u0120from", "\u0120ER", "p", "57", "WT", "\u0120and", "\u0120ER", "p", "57", "N", "es", "-", "/-", "\u0120mice", "\u0120in", "\u0120three", "\u0120animals", "\u0120per", "\u0120group", "\u0120using", "\u0120indirect", "\u0120immun", "of", "lu", "orescence", ".", "\u0120The", "\u0120nucleus", "\u0120was", "\u0120stained", "\u0120with", "\u0120H", "oe", "ch", "st", ".", "\u0120Representative", "\u0120images", "\u0120from", "\u0120one", "\u0120mouse", "\u0120per", "\u0120group", "\u0120are", "\u0120shown", ".", "\u0120Scale", "\u0120bar", ":", "\u012050", "\u0120\u00ce\u00bc", "m", ".", "\u0120G", "\u0120St", "ere", "ological", "\u0120analysis", "\u0120of", "\u0120the", "\u0120spinal", "\u0120cord", "\u0120from", "\u0120ER", "p", "57", "WT", "\u0120(", "n", "\u0120=", "\u01204", "),", "\u0120ER", "p", "57", "N", "es", "+", "/-", "\u0120(", "n", "\u0120=", "\u01204", ")", "\u0120and", "\u0120ER", "p", "57", "N", "es", "-", "/-", "\u0120(", "n", "\u0120=", "\u01204", ")", "\u0120mice", ".", "\u0120Alternate", "\u0120series", "\u0120of", "\u0120sections", "\u0120from", "\u0120the", "\u0120spinal", "\u0120cord", "\u0120of", "\u0120the", "\u0120mice", "\u0120were", "\u0120either", "\u0120stained", "\u0120for", "\u0120N", "iss", "l", "\u0120(", "top", "\u0120row", "\u0120images", ")", "\u0120or", "\u0120processed", "\u0120for", "\u0120immun", "oh", "ist", "ochemistry", "\u0120for", "\u0120the", "\u0120ch", "olin", "ergic", "\u0120cell", "\u0120marker", "\u0120Ch", "oline", "\u0120Ac", "et", "yl", "\u0120Transfer", "ase", "\u0120(", "Ch", "AT", ",", "\u0120bottom", "\u0120row", "\u0120images", ").", "\u0120The", "\u0120nucle", "oli", "\u0120of", "\u0120the", "</s>"
],
"input_ids": [
0, 40683, 195, 4, 17965, 195, 4, 250, 13895, 642, 4390, 4825, 4325, 73, 4825, 4325, 15540, 58, 7344, 19, 12786, 179, 12022, 6214, 44131, 15540, 7, 5368, 7464, 467, 2167, 13895, 642, 4390, 38396, 3122, 4, 20, 1389, 9, 13895, 642, 4390, 8276, 11, 5, 21431, 13051, 58, 14316, 30, 2027, 39144, 4, 13895, 642, 4390, 25982, 36, 282, 5214, 306, 238, 13895, 642, 4390, 487, 293, 2744, 40398, 36, 282, 5214, 245, 43, 8, 13895, 642, 4390, 487, 293, 12, 40398, 36, 282, 5214, 306, 43, 15540, 4, 289, 4186, 3248, 1389, 58, 3030, 25, 10, 16761, 797, 4, 5143, 2798, 35, 28256, 5000, 9, 13895, 642, 4390, 1389, 21, 3744, 5407, 7, 289, 4182, 3248, 1389, 4, 163, 13048, 2408, 19851, 58, 3744, 13, 4658, 86, 332, 11, 13895, 642, 4390, 25982, 36, 282, 5214, 1096, 238, 13895, 642, 4390, 487, 293, 2744, 40398, 36, 282, 5214, 2881, 43, 8, 13895, 642, 4390, 487, 293, 12, 40398, 36, 282, 5214, 1646, 43, 15540, 4, 230, 9104, 271, 1630, 819, 21, 3744, 13895, 642, 4390, 25982, 36, 282, 5214, 844, 238, 13895, 642, 4390, 487, 293, 2744, 40398, 36, 282, 5214, 996, 43, 8, 13895, 642, 4390, 487, 293, 12, 40398, 36, 282, 5214, 398, 43, 15540, 4, 211, 289, 23786, 1296, 819, 21, 11852, 11, 13895, 642, 4390, 25982, 36, 282, 5214, 4006, 238, 13895, 642, 4390, 487, 293, 2744, 40398, 36, 282, 5214, 2881, 43, 8, 13895, 642, 4390, 487, 293, 12, 40398, 36, 282, 5214, 1092, 43, 15540, 4, 381, 25353, 12, 5096, 906, 7967, 9158, 13, 13895, 642, 4390, 487, 293, 12, 40398, 15540, 36, 487, 5457, 753, 43, 14, 30088, 962, 50, 56, 7, 28, 26936, 142, 9, 474, 2188, 227, 5, 4864, 820, 8, 6521, 360, 4, 30750, 7967, 9, 42, 2849, 13839, 9, 3122, 21, 4981, 360, 4, 13895, 642, 4390, 25982, 36, 282, 5214, 1096, 43, 8, 13895, 642, 4390, 487, 293, 2744, 40398, 36, 282, 5214, 2881, 43, 15540, 32, 2343, 25, 10, 5135, 4, 274, 31862, 9779, 1966, 9, 3864, 257, 487, 8, 32727, 591, 1690, 8173, 21, 3744, 11, 21431, 13051, 11576, 31, 13895, 642, 4390, 25982, 8, 13895, 642, 4390, 487, 293, 12, 40398, 15540, 11, 130, 3122, 228, 333, 634, 18677, 13998, 1116, 6487, 45094, 4, 20, 38531, 21, 31789, 19, 289, 3540, 611, 620, 4, 10308, 3156, 31, 65, 18292, 228, 333, 32, 2343, 4, 33256, 2003, 35, 654, 46911, 119, 4, 272, 312, 2816, 9779, 1966, 9, 5, 21431, 13051, 31, 13895, 642, 4390, 25982, 36, 282, 5457, 204, 238, 13895, 642, 4390, 487, 293, 2744, 40398, 36, 282, 5457, 204, 43, 8, 13895, 642, 4390, 487, 293, 12, 40398, 36, 282, 5457, 204, 43, 15540, 4, 43510, 651, 9, 9042, 31, 5, 21431, 13051, 9, 5, 15540, 58, 1169, 31789, 13, 234, 3006, 462, 36, 8766, 3236, 3156, 43, 50, 12069, 13, 13998, 2678, 661, 39917, 13, 5, 1855, 21716, 44858, 3551, 17540, 732, 18675, 6208, 594, 4360, 18853, 3175, 36, 4771, 2571, 6, 2576, 3236, 3156, 322, 20, 38898, 6483, 9, 5, 2
],
"label_ids": {
"entity_types": [
"O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "B-GENEPROD", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "B-TISSUE", "I-TISSUE", "O", "O", "O", "B-EXP_ASSAY", "I-EXP_ASSAY", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-ORGANISM", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "B-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "B-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "O", "O", "B-EXP_ASSAY", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-EXP_ASSAY", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "O", "O", "O", "B-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "B-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "B-TISSUE", "I-TISSUE", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "O", "O", "B-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "O", "O", "B-SUBCELLULAR", "O", "O", "O", "B-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "O", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "O", "O", "B-TISSUE", "I-TISSUE", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "O", "O", "O", "B-TISSUE", "I-TISSUE", "O", "O", "B-ORGANISM", "O", "O", "O", "O", "B-SUBCELLULAR", "I-SUBCELLULAR", "I-SUBCELLULAR", "O", "O", "O", "O", "O", "O", "O", "O", "B-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "I-EXP_ASSAY", "O", "O", "O", "O", "O", "O", "O", "B-GENEPROD", "I-GENEPROD", "I-GENEPROD", "I-GENEPROD", "I-GENEPROD", "I-GENEPROD", "I-GENEPROD", "O", "B-GENEPROD", "I-GENEPROD", "O", "O", "O", "O", "O", "O", "B-SUBCELLULAR", "I-SUBCELLULAR", "O", "O", "O"
],
"geneprod_roles": [
"O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-MEASURED_VAR", "I-MEASURED_VAR", "I-MEASURED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-MEASURED_VAR", "I-MEASURED_VAR", "I-MEASURED_VAR", "O", "B-MEASURED_VAR", "I-MEASURED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-CONTROLLED_VAR", "I-CONTROLLED_VAR", "I-CONTROLLED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-MEASURED_VAR", "I-MEASURED_VAR", "I-MEASURED_VAR", "I-MEASURED_VAR", "I-MEASURED_VAR", "I-MEASURED_VAR", "I-MEASURED_VAR", "O", "B-MEASURED_VAR", "I-MEASURED_VAR", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O"
],
"boring": [
"O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "O", "O", "O", "B-BORING", "I-BORING", "B-BORING", "O", "O", "B-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "I-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "O", "B-BORING", "I-BORING", "I-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "I-BORING", "I-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "I-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "I-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "O", "O", "O", "O", "O", "O", "O", "B-BORING", "I-BORING", "O", "O", "B-BORING", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O"
],
"panel_start": [
"O", "O", "O", "O", "O", "O", "O", "B-PANEL_START", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-PANEL_START", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-PANEL_START", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-PANEL_START", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-PANEL_START", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "B-PANEL_START", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O", "O"
]
}
}
```
### Data Fields
- `input_ids`: token id in `roberta-base` tokenizers' vocabulary provided as a`list` of `int`
- `label_ids`:
- `entity_types`: `list` of `strings` for the IOB2 tags for entity type; possible value in `["O", "I-SMALL_MOLECULE", "B-SMALL_MOLECULE", "I-GENEPROD", "B-GENEPROD", "I-SUBCELLULAR", "B-SUBCELLULAR", "I-CELL", "B-CELL", "I-TISSUE", "B-TISSUE", "I-ORGANISM", "B-ORGANISM", "I-EXP_ASSAY", "B-EXP_ASSAY"]`
- `geneprod_roles`: `list` of `strings` for the IOB2 tags for experimental roles; values in `["O", "I-CONTROLLED_VAR", "B-CONTROLLED_VAR", "I-MEASURED_VAR", "B-MEASURED_VAR"]`
- `boring`: `list` of `strings` for IOB2 tags for entities unrelated to causal design; values in `["O", "I-BORING", "B-BORING"]`
- `panel_start`: `list` of `strings` for IOB2 tags `["O", "B-PANEL_START"]`
### Data Splits
- train:
- features: ['input_ids', 'labels', 'tag_mask'],
- num_rows: 48_771
- test:
- features: ['input_ids', 'labels', 'tag_mask'],
- num_rows: 13_801
- validation:
- features: ['input_ids', 'labels', 'tag_mask'],
- num_rows: 7_178
## Dataset Creation
### Curation Rationale
The dataset was built to train models for the automatic extraction of a knowledge graph based from the scientific literature. The dataset can be used to train models for text segmentation, named entity recognition and semantic role labeling.
### Source Data
#### Initial Data Collection and Normalization
Figure legends were annotated according to the SourceData framework described in Liechti et al 2017 (Nature Methods, 2017, https://doi.org/10.1038/nmeth.4471). The curation tool at https://curation.sourcedata.io was used to segment figure legends into panel legends, tag enities, assign experiemental roles and normalize with standard identifiers (not available in this dataset). The source data was downloaded from the SourceData API (https://api.sourcedata.io) on 21 Jan 2021.
#### Who are the source language producers?
The examples are extracted from the figure legends from scientific papers in cell and molecular biology.
### Annotations
#### Annotation process
The annotations were produced manually with expert curators from the SourceData project (https://sourcedata.embo.org)
#### Who are the annotators?
Curators of the SourceData project.
### Personal and Sensitive Information
None known.
## Considerations for Using the Data
### Social Impact of Dataset
Not applicable.
### Discussion of Biases
The examples are heavily biased towards cell and molecular biology and are enriched in examples from papers published in EMBO Press journals (https://embopress.org)
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Thomas Lemberger, EMBO.
### Licensing Information
CC BY 4.0
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@tlemberger](https://github.com/tlemberger>) for adding this dataset.
|
false |
# Dataset Card for QedAmara
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://opus.nlpl.eu/QED.php
- **Repository:** None
- **Paper:** https://www.aclweb.org/anthology/L14-1675/
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [More Information Needed]
### Dataset Summary
To load a language pair which isn't part of the config, all you need to do is specify the language code as pairs.
You can find the valid pairs in Homepage section of Dataset Description: http://opus.nlpl.eu/QED.php
E.g.
`dataset = load_dataset("qed_amara", lang1="cs", lang2="nb")`
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The languages in the dataset are:
- aa
- ab
- ae
- aeb
- af
- aka: `ak`
- amh: `am`
- an
- ar
- arq
- arz
- as
- ase
- ast
- av
- ay
- az
- ba
- bam: `bm`
- be
- ber
- bg
- bh
- bi
- bn
- bnt
- bo
- br
- bs
- bug
- ca
- ce
- ceb
- ch
- cho
- cku
- cnh
- co
- cr
- cs
- cu
- cv
- cy
- da
- de
- dv
- dz
- ee
- efi
- el
- en
- eo
- es
- et
- eu
- fa
- ff
- fi
- fil
- fj
- fo
- fr
- ful: `ff`
- ga
- gd
- gl
- gn
- gu
- hai
- hau: `ha`
- haw
- haz
- hb: ?
- hch
- he
- hi
- ho
- hr
- ht
- hu
- hup
- hus
- hy
- hz
- ia
- ibo: `ig`
- id
- ie
- ik
- inh
- io
- iro
- is
- it
- iu
- ja
- jv
- ka
- kar
- kau: `kr`
- kik: `ki`
- kin: `rw`
- kj
- kk
- kl
- km
- kn
- ko
- ksh
- ku
- kv
- kw
- ky
- la
- lb
- lg
- li
- lin: `ln`
- lkt
- lld
- lo
- lt
- ltg
- lu
- luo
- luy
- lv
- mad
- mfe
- mi
- mk
- ml
- mlg: `mg`
- mn
- mni
- mo: Moldavian (deprecated tag; preferred value: Romanian; Moldavian; Moldovan (`ro`))
- moh
- mos
- mr
- ms
- mt
- mus
- my
- nb
- nci
- nd
- ne
- nl
- nn
- nso
- nv
- nya: `ny`
- oc
- or
- orm: `om`
- pam
- pan: `pa`
- pap
- pi
- pl
- pnb
- prs
- ps
- pt
- que: `qu`
- rm
- ro
- ru
- run: `rn`
- rup
- ry: ?
- sa
- sc
- scn
- sco
- sd
- sg
- sgn
- sh
- si
- sk
- sl
- sm
- sna: `sn`
- som: `so`
- sot: `st`
- sq
- sr
- srp: `sr`
- sv
- swa: `sw`
- szl
- ta
- te
- tet
- tg
- th
- tir: `ti`
- tk
- tl
- tlh
- to
- tr
- ts
- tt
- tw
- ug
- uk
- umb
- ur
- uz
- ve
- vi
- vls
- vo
- wa
- wol: `wo`
- xh
- yaq
- yi
- yor: `yo`
- za
- zam
- zh
- zul: `zu`
## Dataset Structure
### Data Instances
Here are some examples of questions and facts:
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
true |
# Dataset Card for Wizard-of-Oz
## 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:** [More info needed]
- **Repository:** [GitHub](https://github.com/nmrksic/neural-belief-tracker/tree/master/data/woz)
- **Paper:** [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://arxiv.org/abs/1604.04562)
- **Leaderboard:** [More info needed]
- **Point of Contact:** [More info needed]
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset. |
false |
# Dataset Card for Dataset Name
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
Hebrew Dataset for ASR
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
```json
{'audio': {'path': '/root/.cache/huggingface/datasets/downloads/extracted/8ce7402f6482c6053251d7f3000eec88668c994beb48b7ca7352e77ef810a0b6/train/e429593fede945c185897e378a5839f4198.wav',
'array': array([-0.00265503, -0.0018158 , -0.00149536, ..., -0.00135803,
-0.00231934, -0.00190735]),
'sampling_rate': 16000},
'sentence': 'היא מבינה אותי יותר מכל אחד אחר'}
```
### Data Fields
[More Information Needed]
### Data Splits
| | train | validation |
| ---- | ----- | ---------- |
| number of samples | 8000 | 2000 |
| hours | 6.92 | 1.73 |
## Dataset Creation
### Curation Rationale
scraped data from youtube (channel כאן) with removing outliers (by length and ratio between length of the audio and sentences)
### Source Data
#### Initial Data Collection and Normalization
#### 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
```
@misc{imvladikon2022hebrew_speech_kan,
author = {Gurevich, Vladimir},
title = {Hebrew Speech Recognition Dataset: Kan},
year = {2022},
howpublished = \url{https://huggingface.co/datasets/imvladikon/hebrew_speech_kan},
}
```
### Contributions
[More Information Needed] |
false |
# Dataset Card for Tilde Multilingual Open Data for European Languages
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://opus.nlpl.eu/TildeMODEL.php
- **Repository:** None
- **Paper:** https://www.aclweb.org/anthology/W17-0235.pdf
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [More Information Needed]
### Dataset Summary
To load a language pair which isn't part of the config, all you need to do is specify the language code as pairs.
You can find the valid pairs in Homepage section of Dataset Description: http://opus.nlpl.eu/TildeMODEL.php
E.g.
`dataset = load_dataset("tilde_model", lang1="en", lang2="lv")`
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
Here are some examples of questions and facts:
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false |
# Dataset Card for Deal or No Deal Negotiator
## 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:** [Dataset Repository](https://github.com/facebookresearch/end-to-end-negotiator)
- **Paper:** [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://arxiv.org/abs/1706.05125)
### Dataset Summary
A large dataset of human-human negotiations on a multi-issue bargaining task, where agents who cannot observe each other’s reward functions must reach an agreement (or a deal) via natural language dialogue.
### Supported Tasks and Leaderboards
Train end-to-end models for negotiation
### Languages
The text in the dataset is in English
## Dataset Structure
### Data Instances
{'dialogue': 'YOU: i love basketball and reading <eos> THEM: no . i want the hat and the balls <eos> YOU: both balls ? <eos> THEM: yeah or 1 ball and 1 book <eos> YOU: ok i want the hat and you can have the rest <eos> THEM: okay deal ill take the books and the balls you can have only the hat <eos> YOU: ok <eos> THEM: <selection>',
'input': {'count': [3, 1, 2], 'value': [0, 8, 1]},
'output': 'item0=0 item1=1 item2=0 item0=3 item1=0 item2=2',
'partner_input': {'count': [3, 1, 2], 'value': [1, 3, 2]}}
### Data Fields
`dialogue`: The dialogue between the agents. \
`input`: The input of the firt agent. \
`partner_input`: The input of the other agent. \
`count`: The count of the three available items. \
`value`: The value of the three available items. \
`output`: Describes how many of each of the three item typesare assigned to each agent
### Data Splits
| | train | validation | test |
|------------|------:|-----------:|-----:|
| dialogues | 10095 | 1087 | 1052 |
| self_play | 8172 | NA | NA |
## 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?
Human workers using Amazon Mechanical Turk. They were paid $0.15 per dialogue, with a $0.05 bonus for maximal scores. Only workers based in the United States with a 95% approval rating and at least 5000 previous HITs were used.
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
The project is licenced under CC-by-NC
### Citation Information
```
@article{lewis2017deal,
title={Deal or no deal? end-to-end learning for negotiation dialogues},
author={Lewis, Mike and Yarats, Denis and Dauphin, Yann N and Parikh, Devi and Batra, Dhruv},
journal={arXiv preprint arXiv:1706.05125},
year={2017}
}
```
### Contributions
Thanks to [@moussaKam](https://github.com/moussaKam) for adding this dataset. |
false |
# Dataset Card for extension to the EventCorefBank
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://opus.nlpl.eu/ECB.php
- **Repository:** None
- **Paper:** http://www.lrec-conf.org/proceedings/lrec2012/pdf/463_Paper.pdf
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [More Information Needed]
### Dataset Summary
To load a language pair which isn't part of the config, all you need to do is specify the language code as pairs.
You can find the valid pairs in Homepage section of Dataset Description: http://opus.nlpl.eu/ECB.php
E.g.
`dataset = load_dataset("ecb", lang1="en", lang2="fi")`
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
Here are some examples of questions and facts:
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false |
# Dataset Card for "tner/bionlp2004"
## Dataset Description
- **Repository:** [T-NER](https://github.com/asahi417/tner)
- **Paper:** [https://aclanthology.org/U15-1010.pdf](https://aclanthology.org/U15-1010.pdf)
- **Dataset:** BioNLP2004
- **Domain:** Biochemical
- **Number of Entity:** 5
### Dataset Summary
BioNLP2004 NER dataset formatted in a part of [TNER](https://github.com/asahi417/tner) project.
BioNLP2004 dataset contains training and test only, so we randomly sample a half size of test instances from the training set to create validation set.
- Entity Types: `DNA`, `protein`, `cell_type`, `cell_line`, `RNA`
## Dataset Structure
### Data Instances
An example of `train` looks as follows.
```
{
'tags': [0, 0, 0, 0, 3, 0, 9, 10, 0, 0, 0, 0, 0, 7, 8, 0, 3, 0, 0, 9, 10, 10, 0, 0],
'tokens': ['In', 'the', 'presence', 'of', 'Epo', ',', 'c-myb', 'mRNA', 'declined', 'and', '20', '%', 'of', 'K562', 'cells', 'synthesized', 'Hb', 'regardless', 'of', 'antisense', 'myb', 'RNA', 'expression', '.']
}
```
### Label ID
The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/fin/raw/main/dataset/label.json).
```python
{
"O": 0,
"B-DNA": 1,
"I-DNA": 2,
"B-protein": 3,
"I-protein": 4,
"B-cell_type": 5,
"I-cell_type": 6,
"B-cell_line": 7,
"I-cell_line": 8,
"B-RNA": 9,
"I-RNA": 10
}
```
### Data Splits
| name |train|validation|test|
|---------|----:|---------:|---:|
|bionlp2004 |16619 | 1927| 3856|
### Citation Information
```
@inproceedings{collier-kim-2004-introduction,
title = "Introduction to the Bio-entity Recognition Task at {JNLPBA}",
author = "Collier, Nigel and
Kim, Jin-Dong",
booktitle = "Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications ({NLPBA}/{B}io{NLP})",
month = aug # " 28th and 29th",
year = "2004",
address = "Geneva, Switzerland",
publisher = "COLING",
url = "https://aclanthology.org/W04-1213",
pages = "73--78",
}
``` |
false |
# Dataset Card for Casino
## 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:** [Github: Kushal Chawla CaSiNo](https://github.com/kushalchawla/CaSiNo)
- **Paper:** [CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems](https://aclanthology.org/2021.naacl-main.254.pdf)
- **Point of Contact:** [Kushal Chawla](kchawla@usc.edu)
### Dataset Summary
We provide a novel dataset (referred to as CaSiNo) of 1030 negotiation dialogues. Two participants take the role of campsite neighbors and negotiate for Food, Water, and Firewood packages, based on their individual preferences and requirements. This design keeps the task tractable, while still facilitating linguistically rich and personal conversations. This helps to overcome the limitations of prior negotiation datasets such as Deal or No Deal and Craigslist Bargain. Each dialogue consists of rich meta-data including participant demographics, personality, and their subjective evaluation of the negotiation in terms of satisfaction and opponent likeness.
### Supported Tasks and Leaderboards
Train end-to-end models for negotiation
### Languages
English
## Dataset Structure
### Data Instances
```
{
"chat_logs": [
{
"text": "Hello! \ud83d\ude42 Let's work together on a deal for these packages, shall we? What are you most interested in?",
"task_data": {},
"id": "mturk_agent_1"
},
...
],
"participant_info": {
"mturk_agent_1":
{
"value2issue": ...
"value2reason": ...
"outcomes": ...
"demographics": ...
"personality": ...
},
"mturk_agent_2": ...
},
"annotations": [
["Hello! \ud83d\ude42 Let's work together on a deal for these packages, shall we? What are you most interested in?", "promote-coordination,elicit-pref"],
...
]
}
```
### Data Fields
- `chat_logs`: The negotiation dialogue between two participants
- `text`: The dialogue utterance
- `task_data`: Meta-data associated with the utterance such as the deal submitted by a participant
- `id`: The ID of the participant who typed this utterance
- `participant_info`: Meta-data about the two participants in this conversation
- `mturk_agent_1`: For the first participant (Note that 'first' is just for reference. There is no order between the participants and any participant can start the conversation)
- `value2issue`: The priority order of this participant among Food, Water, Firewood
- `value2reason`: The personal arguments given by the participants themselves, consistent with the above preference order. This preference order and these arguments were submitted before the negotiation began.
- `outcomes`: The negotiation outcomes for this participant including objective and subjective assessment.
- `demographics`: Demographic attributes of the participant in terms of age, gender, ethnicity, and education.
- `personality`: Personality attributes for this participant, in terms of Big-5 and Social Value Orientation
- `mturk_agent_2`: For the second participant; follows the same structure as above
- `annotations`: Strategy annotations for each utterance in the dialogue, wherever available. The first element represents the utterance and the second represents a comma-separated list of all strategies present in that utterance.
### Data Splits
No default data split has been provided. Hence, all 1030 data points are under the 'train' split.
| | Train |
| ----- | ----- |
| total dialogues | 1030 |
| annotated dialogues | 396 |
## Dataset Creation
### Curation Rationale
The dataset was collected to address the limitations in prior negotiation datasets from the perspective of downstream applications in pedagogy and conversational AI. Please refer to the original paper published at NAACL 2021 for details about the rationale and data curation steps ([source paper](https://aclanthology.org/2021.naacl-main.254.pdf)).
### Source Data
#### Initial Data Collection and Normalization
The dialogues were crowdsourced on Amazon Mechanical Turk. The strategy annotations were performed by expert annotators (first three authors of the paper). Please refer to the original dataset paper published at NAACL 2021 for more details ([source paper](https://aclanthology.org/2021.naacl-main.254.pdf)).
#### Who are the source language producers?
The primary producers are Turkers on Amazon Mechanical Turk platform. Two turkers were randomly paired with each other to engage in a negotiation via a chat interface. Please refer to the original dataset paper published at NAACL 2021 for more details ([source paper](https://aclanthology.org/2021.naacl-main.254.pdf)).
### Annotations
#### Annotation process
From the [source paper](https://aclanthology.org/2021.naacl-main.254.pdf) for this dataset:
>Three expert annotators independently annotated 396 dialogues containing 4615 utterances. The annotation guidelines were iterated over a subset of 5 dialogues, while the reliability scores were computed on a different subset of 10 dialogues. We use the nominal form of Krippendorff’s alpha (Krippendorff, 2018) to measure the inter-annotator agreement. We provide the annotation statistics in Table 2. Although we release all the annotations, we skip Coordination and Empathy for our analysis in this work, due to higher subjectivity resulting in relatively lower reliability scores.
#### Who are the annotators?
Three expert annotators (first three authors of the paper).
### Personal and Sensitive Information
All personally identifiable information about the participants such as MTurk Ids or HIT Ids was removed before releasing the data.
## Considerations for Using the Data
### Social Impact of Dataset
Please refer to Section 8.2 in the [source paper](https://aclanthology.org/2021.naacl-main.254.pdf).
### Discussion of Biases
Please refer to Section 8.2 in the [source paper](https://aclanthology.org/2021.naacl-main.254.pdf).
### Other Known Limitations
Please refer to Section 7 in the [source paper](https://aclanthology.org/2021.naacl-main.254.pdf).
## Additional Information
### Dataset Curators
Corresponding Author: Kushal Chawla (`kchawla@usc.edu`)\
Affiliation: University of Southern California\
Please refer to the [source paper](https://aclanthology.org/2021.naacl-main.254.pdf) for the complete author list.
### Licensing Information
The project is licensed under CC-by-4.0
### Citation Information
```
@inproceedings{chawla2021casino,
title={CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems},
author={Chawla, Kushal and Ramirez, Jaysa and Clever, Rene and Lucas, Gale and May, Jonathan and Gratch, Jonathan},
booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
pages={3167--3185},
year={2021}
}
```
### Contributions
Thanks to [Kushal Chawla](https://kushalchawla.github.io/) for adding this dataset. |
false |
# Dataset Card for Europeana Newspapers
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Github](https://github.com/EuropeanaNewspapers/ner-corpora)
- **Repository:** [Github](https://github.com/EuropeanaNewspapers/ner-corpora)
- **Paper:** [Aclweb](https://www.aclweb.org/anthology/L16-1689/)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@jplu](https://github.com/jplu) for adding this dataset. |
false | # Dataset Card for reasoning_bg
## 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/mhardalov/bg-reason-BERT
- **Repository:** https://github.com/mhardalov/bg-reason-BERT
- **Paper:** [Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bulgarian](https://arxiv.org/abs/1908.01519)
- **Leaderboard:** [N/A]
- **Point of Contact:** [Momchil Hardalov](mailto:hardalov@fmi.uni-sofia.bg)
### Dataset Summary
Recently, reading comprehension models achieved near-human performance on large-scale datasets such as SQuAD, CoQA, MS Macro, RACE, etc. This is largely due to the release of pre-trained contextualized representations such as BERT and ELMo, which can be fine-tuned for the target task. Despite those advances and the creation of more challenging datasets, most of the work is still done for English. Here, we study the effectiveness of multilingual BERT fine-tuned on large-scale English datasets for reading comprehension (e.g., for RACE), and we apply it to Bulgarian multiple-choice reading comprehension. We propose a new dataset containing 2,221 questions from matriculation exams for twelfth grade in various subjects -history, biology, geography and philosophy-, and 412 additional questions from online quizzes in history. While the quiz authors gave no relevant context, we incorporate knowledge from Wikipedia, retrieving documents matching the combination of question + each answer option.
### Supported Tasks and Leaderboards
[Needs More Information]
### Languages
Bulgarian
## Dataset Structure
### Data Instances
A typical data point comprises of question sentence and 4 possible choice answers and the correct answer.
```
{
"id": "21181dda96414fd9b7a5e336ad84b45d",
"qid": 1,
"question": "!0<>AB>OB5;=> AJI5AB2C20I8 6828 A8AB5<8 A0:",
"answers": [
"28@CA8B5",
"BJ:0=8B5",
"<8B>E>=4@88B5",
"54=>:;5BJG=8B5 >@30=87<8"
],
"correct": "54=>:;5BJG=8B5 >@30=87<8",
"url": "http://zamatura.eu/files/dzi/biologiq/2010/matura-biologiq-2010.pdf"
},
```
### Data Fields
- url : A string having the url from which the question has been sourced from
- id: A string question identifier for each example
- qid: An integer which shows the sequence of the question in that particular URL
- question: The title of the question
- answers: A list of each answers
- correct: The correct answer
### Data Splits
The dataset covers the following domains
| Domain | #QA-paris | #Choices | Len Question | Len Options | Vocab Size |
|:-------|:---------:|:--------:|:------------:|:-----------:|:----------:|
| **12th Grade Matriculation Exam** |
| Biology | 437 | 4 | 10.44 | 2.64 | 2,414 (12,922)|
| Philosophy | 630 | 4 | 8.91 | 2.94| 3,636 (20,392) |
| Geography | 612 | 4 | 12.83 | 2.47 | 3,239 (17,668) |
| History | 542 | 4 | 23.74 | 3.64 | 5,466 (20,456) |
| **Online History Quizzes** |
| Bulgarian History | 229 | 4 | 14.05 | 2.80 | 2,287 (10,620) |
| PzHistory | 183 | 3 | 38.89 | 2.44 | 1,261 (7,518) |
| **Total** | 2,633 | 3.93 | 15.67 | 2.89 | 13,329 (56,104) |
## Dataset Creation
### Curation Rationale
The dataset has been curated from matriculation exams and online quizzes. These questions cover a large variety of science topics in biology, philosophy, geography, and history.
### Source Data
#### Initial Data Collection and Normalization
Data has been sourced from the matriculation exams and online quizzes.
#### 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
```
@article{hardalov2019beyond,
title={Beyond english-only reading comprehension: Experiments in zero-shot multilingual transfer for bulgarian},
author={Hardalov, Momchil and Koychev, Ivan and Nakov, Preslav},
journal={arXiv preprint arXiv:1908.01519},
year={2019}
}
```
### Contributions
Thanks to [@saradhix](https://github.com/saradhix) for adding this dataset. |
false |
## Table of Contents
- [Description](#description)
- [Dataset Structure](#dataset-structure)
- [Additional Information](#additional-information)
## Dataset Card for WikiNEuRal dataset
## Dataset Description
- **Summary:** Training data for NER in 9 languages.
- **Repository:** [https://github.com/Babelscape/wikineural](https://github.com/Babelscape/wikineural)
- **Paper:** [https://aclanthology.org/wikineural](https://aclanthology.org/2021.findings-emnlp.215/)
- **Point of Contact:** [tedeschi@babelscape.com](tedeschi@babelscape.com)
## Description
- **Summary:** In a nutshell, WikiNEuRal consists in a novel technique which builds upon a multilingual lexical knowledge base (i.e., [BabelNet](https://babelnet.org/)) and transformer-based architectures (i.e., [BERT](https://arxiv.org/abs/1810.04805)) to produce high-quality annotations for multilingual NER. It shows consistent improvements of up to 6 span-based F1-score points against state-of-the-art alternative data production methods on common benchmarks for NER. We used this methodology to automatically generate training data for NER in 9 languages.
- **Repository:** [https://github.com/Babelscape/wikineural](https://github.com/Babelscape/wikineural)
- **Paper:** [https://aclanthology.org/wikineural](https://aclanthology.org/2021.findings-emnlp.215/)
- **Point of Contact:** [tedeschi@babelscape.com](tedeschi@babelscape.com)
## Dataset Structure
The data fields are the same among all splits.
- `tokens`: a `list` of `string` features.
- `ner_tags`: a `list` of classification labels (`int`). Full tagset with indices:
```python
{'O': 0, 'B-PER': 1, 'I-PER': 2, 'B-ORG': 3, 'I-ORG': 4, 'B-LOC': 5, 'I-LOC': 6, 'B-MISC': 7, 'I-MISC': 8}
```
- `lang`: a `string` feature. Full list of language: Dutch (nl), English (en), French (fr), German (de), Italian (it), Polish (pl), Portugues (pt), Russian (ru), Spanish (es).
## Dataset Statistics
The table below shows the number of sentences, number of tokens and number of instances per class, for each of the 9 languages.
| Dataset Version | Sentences | Tokens | PER | ORG | LOC | MISC | OTHER |
| :------------- | -------------: | -------------: | -------------: | -------------: | -------------: | -------------: | -------------: |
| WikiNEuRal EN | 116k | 2.73M | 51k | 31k | 67k | 45k | 2.40M |
| WikiNEuRal ES | 95k | 2.33M | 43k | 17k | 68k | 25k | 2.04M |
| WikiNEuRal NL | 107k | 1.91M | 46k | 22k | 61k | 24k | 1.64M |
| WikiNEuRal DE | 124k | 2.19M | 60k | 32k | 59k | 25k | 1.87M |
| WikiNEuRal RU | 123k | 2.39M | 40k | 26k | 89k | 25k | 2.13M |
| WikiNEuRal IT | 111k | 2.99M | 67k | 22k | 97k | 26k | 2.62M |
| WikiNEuRal FR | 127k | 3.24M | 76k | 25k | 101k | 29k | 2.83M |
| WikiNEuRal PL | 141k | 2.29M | 59k | 34k | 118k | 22k | 1.91M |
| WikiNEuRal PT | 106k | 2.53M | 44k | 17k | 112k | 25k | 2.20M |
## Additional Information
- **Licensing Information**: Contents of this repository are restricted to only non-commercial research purposes under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/). Copyright of the dataset contents belongs to the original copyright holders.
- **Citation Information**: Please consider citing our work if you use data and/or code from this repository.
```bibtex
@inproceedings{tedeschi-etal-2021-wikineural-combined,
title = "{W}iki{NE}u{R}al: {C}ombined Neural and Knowledge-based Silver Data Creation for Multilingual {NER}",
author = "Tedeschi, Simone and
Maiorca, Valentino and
Campolungo, Niccol{\`o} and
Cecconi, Francesco and
Navigli, Roberto",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.215",
pages = "2521--2533",
abstract = "Multilingual Named Entity Recognition (NER) is a key intermediate task which is needed in many areas of NLP. In this paper, we address the well-known issue of data scarcity in NER, especially relevant when moving to a multilingual scenario, and go beyond current approaches to the creation of multilingual silver data for the task. We exploit the texts of Wikipedia and introduce a new methodology based on the effective combination of knowledge-based approaches and neural models, together with a novel domain adaptation technique, to produce high-quality training corpora for NER. We evaluate our datasets extensively on standard benchmarks for NER, yielding substantial improvements up to 6 span-based F1-score points over previous state-of-the-art systems for data creation.",
}
```
- **Contributions**: Thanks to [@sted97](https://github.com/sted97) for adding this dataset.
|
true |
# Dataset Card for cardiffnlp/tweet_sentiment_multilingual
## Dataset Description
- **Homepage:** [https://github.com/cardiffnlp/xlm-t](https://github.com/cardiffnlp/xlm-t)
- **Repository:** - **Homepage:** [https://github.com/cardiffnlp/xlm-t](https://github.com/cardiffnlp/xlm-t)
- **Paper:** [https://aclanthology.org/2022.lrec-1.27/](https://aclanthology.org/2022.lrec-1.27/)
- **Point of Contact:** [Asahi Ushio](https://asahiushio.com/)
### Dataset Summary
Tweet Sentiment Multilingual consists of sentiment analysis dataset on Twitter in 8 different lagnuages.
- arabic
- english
- french
- german
- hindi
- italian
- portuguese
- spanish
### Supported Tasks and Leaderboards
- `text_classification`: The dataset can be trained using a SentenceClassification model from HuggingFace transformers.
## Dataset Structure
### Data Instances
An instance from `sentiment` config:
```
{'label': 2, 'text': '"QT @user In the original draft of the 7th book, Remus Lupin survived the Battle of Hogwarts. #HappyBirthdayRemusLupin"'}
```
### Data Fields
For `sentiment` config:
- `text`: a `string` feature containing the tweet.
- `label`: an `int` classification label with the following mapping:
`0`: negative
`1`: neutral
`2`: positive
### Data Splits
- arabic
- english
- french
- german
- hindi
- italian
- portuguese
- spanish
| name | train | validation | test |
| --------------- | ----- | ---------- | ----- |
| arabic | 1838 | 323 | 869 |
| english | 1838 | 323 | 869 |
| french | 1838 | 323 | 869 |
| german | 1838 | 323 | 869 |
| hindi | 1838 | 323 | 869 |
| italian | 1838 | 323 | 869 |
| portuguese | 1838 | 323 | 869 |
| spanish | 1838 | 323 | 869 |
### Dataset Curators
Francesco Barbieri, Jose Camacho-Collados, Luis Espiinosa-Anke and Leonardo Neves through Cardiff NLP.
### Licensing Information
[Creative Commons Attribution 3.0 Unported License](https://groups.google.com/g/semevaltweet/c/k5DDcvVb_Vo/m/zEOdECFyBQAJ), and all of the datasets require complying with Twitter [Terms Of Service](https://twitter.com/tos) and Twitter API [Terms Of Service](https://developer.twitter.com/en/developer-terms/agreement-and-policy)
### Citation Information
```
@inproceedings{barbieri-etal-2022-xlm,
title = "{XLM}-{T}: Multilingual Language Models in {T}witter for Sentiment Analysis and Beyond",
author = "Barbieri, Francesco and
Espinosa Anke, Luis and
Camacho-Collados, Jose",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.27",
pages = "258--266",
abstract = "Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, current analyses have almost exclusively focused on (multilingual variants of) standard benchmarks, and have relied on clean pre-training and task-specific corpora as multilingual signals. In this paper, we introduce XLM-T, a model to train and evaluate multilingual language models in Twitter. In this paper we provide: (1) a new strong multilingual baseline consisting of an XLM-R (Conneau et al. 2020) model pre-trained on millions of tweets in over thirty languages, alongside starter code to subsequently fine-tune on a target task; and (2) a set of unified sentiment analysis Twitter datasets in eight different languages and a XLM-T model trained on this dataset.",
}
```
|
false | # Dataset Card for SLF5K
## Dataset Description
- **Repository: https://github.com/JeremyAlain/imitation_learning_from_language_feedback**
- **Paper: Training Language Models with Language Feedback at Scale**
- **Point of Contact: jeremy.scheurer@nyu.edu and ethan@anthropic.com**
### Dataset Summary
The Summarization with Language Feedback (SLF5K) dataset is an English-language dataset containing 5K unique samples that can be used
for the task of abstraction summarization. Each sample consists
of a Reddit title and post, a model-generated ([FeedME](https://beta.openai.com/docs/model-index-for-researchers)) summary, and human-written language feedback on that summary.
Additionally, each sample has a high-quality, human-written (gold) summary that should be ideal for the Reddit post.
Lastly, each sample has two additional model-generated summaries with binary human preference labels, on which summary is preferred by a human.
The dataset can be used to train language models with language feedback on abstractive summarization. It can also be
used to train a reward model on binary preferences.
The Reddit posts were taken from the datasets provided by [Learning to Summarize from Human Feedbback](https://arxiv.org/pdf/2009.01325.pdf), who used the initial Reddit post dataset
[TL;DR: Mining Reddit to Learn Automatic Summarization](https://aclanthology.org/W17-4508.pdf).
### Supported Tasks and Leaderboards
The dataset can be used to train a model for abstractive and extractive summarization. It can either be trained directly on
human-written summaries, or leverage language feedback or binary human preferences.
The model performance is evaluated in a human evaluation, where annotators rate the quality of the generated summaries.
Previous work has used [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge) scores, but in [Learning to Summarize from Human Feedbback](https://arxiv.org/pdf/2009.01325.pdf) they
show that ROUGE is not an ideal metric.
### Languages
English
## Dataset Structure
### Data Instances
Each instance is a line in the dataset file (which is saved as .jsonl). Each instance contains various fields, where the most important are
Here is an example instance:
```
{"id":"t3_3w7gyp",
"subreddit":"dogs",
"title":"Puppy playing at park - other owner aggressive towards him [help]",
"post":"Hi all, looking for some advice. I have a 6m old kelpie, buzz, who goes with me daily to a dog park, [...]",
"tldr_human_reference_summary":"other owner at park harsh with my dog for playing to rough with his. Have tried talking to him about it, hasn't helped.",
"summary_prompt":"Write an excellent summary of the given text.\n\nTitle: Puppy playing at park - other owner aggressive towards him [help]\n\nText: Hi all, looking for some advice. [...] that too.\n\nTL;DR:",
"generated_summary_for_comparison_A":"New dog at park is being aggressive to my pup, owner won't stop. What do I do?",
"generated_summary_for_comparison_B":"A new dog has been coming to the dog park and the first day the new dog came, the old dog (a kelpie) was all over him.",
"generated_summary_for_feedback":"A new dog has been coming to the dog park and the first day the owner hauled buzz off and whacked him. Today, the owner was staring daggers at me and lunging at buzz\/pulling his collar roughly.",
"comparison_preference":"Summary A",
"feedback":"The summary is concise but could include information about the poster knowing the dogs are just playing and will react if they become aggressive and wants to know how to handle things with Max's dad. ",
"feedback_class":"Coverage",
"has_additional_feedback":"No",
"ideal_human_summary":"The poster is frustrated with a new person at the dog park who is upset with him because their young dogs are playing roughly. The poster will step in if it gets aggressive and wants the new person to understand this. "}
```
There are some additional fields like `time_spent_in_seconds_ideal_human_summary`, `time_spent_in_seconds_feedback`,`time_spent_in_seconds_comparison` which only have values for the development dataset.
### Data Fields
- `id`: a unique string identifying the reddit post.
- `subreddit`: subreddit of the post.
- `title`: title of the reddit post.
- `post`: reddit post
- `tldr_human_reference_summary`: human reference summary automatically extracted from reddit (taken from the dataset of [TL;DR: Mining Reddit to Learn Automatic Summarization](https://aclanthology.org/W17-4508.pdf))
- `summary_prompt`: the whole prompt used to generate summaries
- `generated_summary_for_comparison_A`: summary A used for binary human comparison (generated with FeedME)
- `generated_summary_for_comparison_B`: summary B used for binary human comparison (generated with FeedME)
- `generated_summary_for_feedback`: summary used to gather human language feedback ((generated with FeedME))
- `comparison_preference`: prefered Summary of human comparison, Values: "Summary A", "Summary B"
- `feedback`: human language feedback on `generated_summary_for_feedback`(most important feedback point)
- `feedback_class`: Class of language feedback, Values: "Coverage", "Accuracy", "Coherence", "other"
- `has_additional_feedback`: Whether this sample could use more feedback on an important point.
- `ideal_human_summary`: high-quality human-written summary for this sample. We instructed annotators to write an ideal summary.
- `time_spent_in_seconds_ideal_human_summary`: Annotation time for ideal human summary
- `time_spent_in_seconds_feedback`: Annotation time for language feedback
- `time_spent_in_seconds_comparison`: Annotation time for binary comparison
Note that the various datasplits have varying fields. The fields that are not contained in a dataset have the value None.
### Data Splits
The SLF5K dataset has 4 splits: _train_, _development_, _validation_, and _test_. Below are the statistics of the dataset.
| Dataset Split | Number of Instances in Split |
| ------------- | ------------------------------------------- |
| Train | 5000 |
| Development | 200 |
| Validation | 500 |
| Test | 698 |
The reason we introduce a development and validation dataset, is the following.
## Dataset Creation
### Curation Rationale
This dataset aims to support supervised language model training from human preferences on a summarization task with real natural training data.
### Source Data
#### Initial Data Collection and Normalization
The initial TL;DR dataset was made public by Völkse et. al. in the paper [TL;DR: Mining Reddit to Learn Automatic Summarization](https://aclanthology.org/W17-4508.pdf) (licensed under CC By 4.0).
Stiennon et. al. then use this TL;DR dataset for their work [Learning to Summarize from Human Feedbback](https://arxiv.org/pdf/2009.01325.pdf).
They filter the TL;DR dataset for quality reasons and collect binary human preference labels.
Our datset is a subset from Stiennon et. al. Dataset, which can be downloaded [here](https://github.com/openai/summarize-from-feedback).
Our train and development dataset are taken form their train dataset and our test and validation datasets are taken from their test datasest.
#### Who are the source language producers?
The reddit posts are written by users of reddit.com.
### Annotations
#### Annotation process
We first onboarded annotators by giving them test tasks on which we evaluated their annotation quality. We then selected 31
annotators for the remainder of the project (a few were removed later on due to quality issues). Througout the process
we updated our instructions to make the tasks clearer and stayed in close contact with the annotators to answer questions etc.
The various dataset splits were collected in multiple annotation iterations. The largest annotation was a single iteration of annotation
5000 samples for the train dataset.
#### Who are the annotators?
We used annotators through the annotation service [Surge AI](https://www.surgehq.ai/).
### Personal and Sensitive Information
The annotators were completely anonymized and no information about them can be found in the dataset.
## Considerations for Using the Data
### Social Impact of Dataset
The purpose of this dataset is to align language models with human preferences by leveraging language feedback, on the task of summarization. Concretely, the goal is to
to develop models that produce summaries for reddit posts that are more in line with human preferences.
Note that this does not imply that the outputs will perfectly be aligned with human values, i.e. outputs can still be misaligned, offensive and contain harumful biases.
While outputs from a model trained on our dataset may reflect the language of the reddit posts, summaries, and human feedback, it should always be made clear that such an output
is automatically generated.
### Discussion of Biases
The TL;DR dataset consists of user-submitted posts to the website reddit.com. It can thus contain content that is offensive or reflects harmful social biases.
We thus recommend that models trained on the SLF5K dataset (which is based on the TL;DR) dataset be thoroughly studied for potential harmful behavior.
The human preferences and feedback represented in this dataset were collected through crowd-workers and may disproportionally represent the views, biases, and values
of the respective demographic of the annotators.
### Other Known Limitations
The "human-summaries" collected in the TL;DR dataset (and available in the SLF5K dataset under the field `tldr_human_reference_summary`, were automatically extracted from reddit.com.
They are often of poor quality and do not accurately reflect human summarization performance. In our paper, we show that our human written summaries (available in the SLF5K dataset under the field
`ideal_human_summary`) are of much higher quality.
## Additional Information
### Dataset Curators
The data is collected by Jérémy Scheurer, Jon Ander Campos, Tomasz Korbak, Jun Shern Chan, Angelica Chen, Kyunghyun Cho, and Ethan Perez.
All authors are affiliated with New York University. Additionally, Jérémy Scheurer is affiliated with FAR AI. Jon Ander
is affiliated with the University of the Basque Country. Tomek Korbak is affiliated with FAR AI and the University of Sussesx.
Kyunghyun Cho is affiliated with Genentech and CIFAR LMB. Ethan Perez is affiliated with FAR AI and Anthropic.
### Licensing Information
The SLF5K dataset is released under the Apache 2.0 license.
### Citation Information
TBD |
false | # Multi-HumanEval
## Table of Contents
- [multi-humaneval](#multi-humaneval)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#related-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Executional Correctness](#execution)
- [Execution Example](#execution-example)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
# multi-humaneval
## Dataset Description
- **Repository:** [GitHub Repository](https://github.com/amazon-science/mbxp-exec-eval)
- **Paper:** [Multi-lingual Evaluation of Code Generation Models](https://openreview.net/forum?id=Bo7eeXm6An8)
### Dataset Summary
This repository contains data and code to perform execution-based multi-lingual evaluation of code generation capabilities and the corresponding data,
namely, a multi-lingual benchmark MBXP, multi-lingual MathQA and multi-lingual HumanEval.
<br>Results and findings can be found in the paper ["Multi-lingual Evaluation of Code Generation Models"](https://arxiv.org/abs/2210.14868).
### Related Tasks and Leaderboards
* [Multi-HumanEval](https://huggingface.co/datasets/mxeval/multi-humaneval)
* [MBXP](https://huggingface.co/datasets/mxeval/mbxp)
* [MathQA-X](https://huggingface.co/datasets/mxeval/mathqa-x)
### Languages
The programming problems are written in multiple programming languages and contain English natural text in comments and docstrings.
## Dataset Structure
To lookup currently supported datasets
```python
get_dataset_config_names("mxeval/multi-humaneval")
['python', 'csharp', 'go', 'java', 'javascript', 'kotlin', 'perl', 'php', 'ruby', 'scala', 'swift', 'typescript']
```
To load a specific dataset and language
```python
from datasets import load_dataset
load_dataset("mxeval/multi-humaneval", "python")
DatasetDict({
test: Dataset({
features: ['task_id', 'language', 'prompt', 'test', 'entry_point', 'canonical_solution', 'description'],
num_rows: 164
})
})
```
### Data Instances
An example of a dataset instance:
```python
{
"task_id": "HumanEval/0",
"language": "python",
"prompt": "from typing import List\n\n\ndef has_close_elements(numbers: List[float], threshold: float) -> bool:\n \"\"\" Check if in given list of numbers, are any two numbers closer to each other than\n given threshold.\n >>> has_close_elements([1.0, 2.0, 3.0], 0.5)\n False\n >>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)\n True\n \"\"\"\n",
"test": "\n\nMETADATA = {\n \"author\": \"jt\",\n \"dataset\": \"test\"\n}\n\n\ndef check(candidate):\n assert candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.3) == True\n assert candidate([1.0, 2.0, 3.9, 4.0, 5.0, 2.2], 0.05) == False\n assert candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.95) == True\n assert candidate([1.0, 2.0, 5.9, 4.0, 5.0], 0.8) == False\n assert candidate([1.0, 2.0, 3.0, 4.0, 5.0, 2.0], 0.1) == True\n assert candidate([1.1, 2.2, 3.1, 4.1, 5.1], 1.0) == True\n assert candidate([1.1, 2.2, 3.1, 4.1, 5.1], 0.5) == False\n\n",
"entry_point": "has_close_elements",
"canonical_solution": " for idx, elem in enumerate(numbers):\n for idx2, elem2 in enumerate(numbers):\n if idx != idx2:\n distance = abs(elem - elem2)\n if distance < threshold:\n return True\n\n return False\n",
"description": "Check if in given list of numbers, are any two numbers closer to each other than\n given threshold.\n >>> has_close_elements([1.0, 2.0, 3.0], 0.5)\n False\n >>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)\n True"
}
```
### Data Fields
- `task_id`: identifier for the data sample
- `prompt`: input for the model containing function header and docstrings
- `canonical_solution`: solution for the problem in the `prompt`
- `description`: task description
- `test`: contains function to test generated code for correctness
- `entry_point`: entry point for test
- `language`: programming lanuage identifier to call the appropriate subprocess call for program execution
### Data Splits
- HumanXEval
- Python
- Csharp
- Go
- Java
- Javascript
- Kotlin
- Perl
- Php
- Ruby
- Scala
- Swift
- Typescript
## Dataset Creation
### Curation Rationale
Since code generation models are often trained on dumps of GitHub a dataset not included in the dump was necessary to properly evaluate the model. However, since this dataset was published on GitHub it is likely to be included in future dumps.
### Personal and Sensitive Information
None.
### Social Impact of Dataset
With this dataset code generating models can be better evaluated which leads to fewer issues introduced when using such models.
## Execution
### Execution Example
Install the repo [mbxp-exec-eval](https://github.com/amazon-science/mbxp-exec-eval) to execute generations or canonical solutions for the prompts from this dataset.
```python
>>> from datasets import load_dataset
>>> from mxeval.execution import check_correctness
>>> humaneval_python = load_dataset("mxeval/multi-humaneval", "python", split="test")
>>> example_problem = humaneval_python[0]
>>> check_correctness(example_problem, example_problem["canonical_solution"], timeout=20.0)
{'task_id': 'HumanEval/0', 'passed': True, 'result': 'passed', 'completion_id': None, 'time_elapsed': 9.636878967285156}
```
### Considerations for Using the Data
Make sure to sandbox the execution environment.
### Dataset Curators
AWS AI Labs
### Licensing Information
[LICENSE](https://huggingface.co/datasets/mxeval/multi-humaneval/blob/main/multi-humaneval-LICENSE) <br>
[THIRD PARTY LICENSES](https://huggingface.co/datasets/mxeval/multi-humaneval/blob/main/THIRD_PARTY_LICENSES)
### Citation Information
```
@article{mbxp_athiwaratkun2022,
title = {Multi-lingual Evaluation of Code Generation Models},
author = {Athiwaratkun, Ben and
Gouda, Sanjay Krishna and
Wang, Zijian and
Li, Xiaopeng and
Tian, Yuchen and
Tan, Ming
and Ahmad, Wasi Uddin and
Wang, Shiqi and
Sun, Qing and
Shang, Mingyue and
Gonugondla, Sujan Kumar and
Ding, Hantian and
Kumar, Varun and
Fulton, Nathan and
Farahani, Arash and
Jain, Siddhartha and
Giaquinto, Robert and
Qian, Haifeng and
Ramanathan, Murali Krishna and
Nallapati, Ramesh and
Ray, Baishakhi and
Bhatia, Parminder and
Sengupta, Sudipta and
Roth, Dan and
Xiang, Bing},
doi = {10.48550/ARXIV.2210.14868},
url = {https://arxiv.org/abs/2210.14868},
keywords = {Machine Learning (cs.LG), Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
### Contributions
[skgouda@](https://github.com/sk-g) [benathi@](https://github.com/benathi) |
true |
# Dataset Card for Yoruba BBC News Topic Classification dataset (yoruba_bbc_topics)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** -
- **Repository:** https://github.com/uds-lsv/transfer-distant-transformer-african
- **Paper:** https://www.aclweb.org/anthology/2020.emnlp-main.204/
- **Leaderboard:** -
- **Point of Contact:** Michael A. Hedderich and David Adelani
{mhedderich, didelani} (at) lsv.uni-saarland.de
### Dataset Summary
A news headline topic classification dataset, similar to AG-news, for Yorùbá. The news headlines were collected from [BBC Yoruba](https://www.bbc.com/yoruba).
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Yorùbá (ISO 639-1: yo)
## Dataset Structure
### Data Instances
An instance consists of a news title sentence and the corresponding topic label as well as publishing information (date and website id).
### Data Fields
- `news_title`: A news title.
- `label`: The label describing the topic of the news title. Can be one of the following classes: africa, entertainment, health, nigeria, politics, sport or world.
- `date`: The publication date (in Yorùbá).
- `bbc_url_id`: The identifier of the article in the BBC URL.
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@michael-aloys](https://github.com/michael-aloys) for adding this dataset. |
false |
# Dataset Card for [covid_qa_castorini]
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** http://covidqa.ai
- **Repository:** https://github.com/castorini/pygaggle
- **Paper:** https://arxiv.org/abs/2004.11339
- **Point of Contact:** [Castorini research group @UWaterloo](https://github.com/castorini/)
### Dataset Summary
CovidQA is a question answering dataset specifically designed for COVID-19, built by hand from knowledge gathered
from Kaggle’s COVID-19 Open Research Dataset Challenge.
The dataset comprises 156 question-article pairs with 27 questions (topics) and 85 unique articles.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The text in the dataset is in English.
## Dataset Structure
### Data Instances
**What do the instances that comprise the dataset represent?**
Each represents a question, a context (document passage from the CORD19 dataset) and an answer.
**How many instances are there in total?**
**What data does each instance consist of?**
Each instance is a query (natural language question and keyword-based), a set of answers, and a document id with its title associated with each answer.
[More Information Needed]
### Data Fields
The data was annotated in SQuAD style fashion, where each row contains:
* **question_query**: Natural language question query
* **keyword_query**: Keyword-based query
* **category_name**: Category in which the queries are part of
* **answers**: List of answers
* **id**: The document ID the answer is found on
* **title**: Title of the document of the answer
* **exact_answer**: Text (string) of the exact answer
### Data Splits
**data/kaggle-lit-review-0.2.json**: 156 question-article pairs with 27 questions (topics) and 85 unique articles from
CORD-19.
[More Information Needed]
## Dataset Creation
The dataset aims to help for guiding research until more substantial evaluation resources become available. Being a smaller dataset,
it can be helpful for evaluating the zero-shot or transfer capabilities of existing models on topics specifically related to COVID-19.
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
#### Who are the source language producers?
[More Information Needed]
### Annotations
Five of the co-authors participated in this annotation effort, applying the aforementioned approach, with one lead
annotator responsible for approving topics and answering technical questions from the other annotators. Two annotators are
undergraduate students majoring in computer science, one is a science alumna, another is a computer science professor,
and the lead annotator is a graduate student in computer science—all affiliated with the University of Waterloo.
#### Annotation process
#### Who are the annotators?
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
The dataset was intended as a stopgap measure for guiding research until more substantial evaluation resources become available.
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
While this dataset, comprising 124 question–article pairs as of the present version 0.1 release, does not have sufficient
examples for supervised machine learning, it can be helpful for evaluating the zero-shot or transfer capabilities
of existing models on topics specifically related to COVID-19.
## Additional Information
The listed authors in the homepage are maintaining/supporting the dataset.
### Dataset Curators
[More Information Needed]
### Licensing Information
The dataset is licensed under the [Apache License 2.0](https://github.com/castorini/pygaggle/blob/master/LICENSE).
### Citation Information
```
@article{tang2020rapidly,
title={Rapidly Bootstrapping a Question Answering Dataset for COVID-19},
author={Tang, Raphael and Nogueira, Rodrigo and Zhang, Edwin and Gupta, Nikhil and Cam, Phuong and Cho, Kyunghyun and Lin, Jimmy},
journal={arXiv preprint arXiv:2004.11339},
year={2020}
}
```
### Contributions
Thanks to [@olinguyen](https://github.com/olinguyen) for adding this dataset. |
false |
# Dataset Card for WikiTableQuestions
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** [WikiTableQuestions homepage](https://nlp.stanford.edu/software/sempre/wikitable)
- **Repository:** [WikiTableQuestions repository](https://github.com/ppasupat/WikiTableQuestions)
- **Paper:** [Compositional Semantic Parsing on Semi-Structured Tables](https://arxiv.org/abs/1508.00305)
- **Leaderboard:** [WikiTableQuestions leaderboard on PaperWithCode](https://paperswithcode.com/dataset/wikitablequestions)
- **Point of Contact:** [Needs More Information]
### Dataset Summary
The WikiTableQuestions dataset is a large-scale dataset for the task of question answering on semi-structured tables.
### Supported Tasks and Leaderboards
question-answering, table-question-answering
### Languages
en
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 29.27 MB
- **Size of the generated dataset:** 47.90 MB
- **Total amount of disk used:** 77.18 MB
An example of 'validation' looks as follows:
```
{
"id": "nt-0",
"question": "what was the last year where this team was a part of the usl a-league?",
"answers": ["2004"],
"table": {
"header": ["Year", "Division", "League", ...],
"name": "csv/204-csv/590.csv",
"rows": [
["2001", "2", "USL A-League", ...],
["2002", "2", "USL A-League", ...],
...
]
}
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `id`: a `string` feature.
- `question`: a `string` feature.
- `answers`: a `list` of `string` feature.
- `table`: a dictionary feature containing:
- `header`: a `list` of `string` features.
- `rows`: a `list` of `list` of `string` features:
- `name`: a `string` feature.
### Data Splits
| name |train|validation|test |
|-------|----:|---------:|----:|
|default|11321| 2831|4344|
## 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
Panupong Pasupat and Percy Liang
### Licensing Information
Creative Commons Attribution Share Alike 4.0 International
### Citation Information
```
@inproceedings{pasupat-liang-2015-compositional,
title = "Compositional Semantic Parsing on Semi-Structured Tables",
author = "Pasupat, Panupong and Liang, Percy",
booktitle = "Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = jul,
year = "2015",
address = "Beijing, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P15-1142",
doi = "10.3115/v1/P15-1142",
pages = "1470--1480",
}
```
### Contributions
Thanks to [@SivilTaram](https://github.com/SivilTaram) for adding this dataset. |
true |
# Dataset Card for Jigsaw Unintended Bias in Toxicity Classification
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification
- **Repository:**
- **Paper:**
- **Leaderboard:** https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification/leaderboard
- **Point of Contact:**
### Dataset Summary
The Jigsaw Unintended Bias in Toxicity Classification dataset comes from the eponymous Kaggle competition.
Please see the original [data](https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification/data)
description for more information.
### Supported Tasks and Leaderboards
The main target for this dataset is toxicity prediction. Several toxicity subtypes are also available, so the dataset
can be used for multi-attribute prediction.
See the original [leaderboard](https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification/leaderboard)
for reference.
### Languages
English
## Dataset Structure
### Data Instances
A data point consists of an id, a comment, the main target, the other toxicity subtypes as well as identity attributes.
For instance, here's the first train example.
```
{
"article_id": 2006,
"asian": NaN,
"atheist": NaN,
"bisexual": NaN,
"black": NaN,
"buddhist": NaN,
"christian": NaN,
"comment_text": "This is so cool. It's like, 'would you want your mother to read this??' Really great idea, well done!",
"created_date": "2015-09-29 10:50:41.987077+00",
"disagree": 0,
"female": NaN,
"funny": 0,
"heterosexual": NaN,
"hindu": NaN,
"homosexual_gay_or_lesbian": NaN,
"identity_annotator_count": 0,
"identity_attack": 0.0,
"insult": 0.0,
"intellectual_or_learning_disability": NaN,
"jewish": NaN,
"latino": NaN,
"likes": 0,
"male": NaN,
"muslim": NaN,
"obscene": 0.0,
"other_disability": NaN,
"other_gender": NaN,
"other_race_or_ethnicity": NaN,
"other_religion": NaN,
"other_sexual_orientation": NaN,
"parent_id": NaN,
"physical_disability": NaN,
"psychiatric_or_mental_illness": NaN,
"publication_id": 2,
"rating": 0,
"sad": 0,
"severe_toxicity": 0.0,
"sexual_explicit": 0.0,
"target": 0.0,
"threat": 0.0,
"toxicity_annotator_count": 4,
"transgender": NaN,
"white": NaN,
"wow": 0
}
```
### Data Fields
- `id`: id of the comment
- `target`: value between 0(non-toxic) and 1(toxic) classifying the comment
- `comment_text`: the text of the comment
- `severe_toxicity`: value between 0(non-severe_toxic) and 1(severe_toxic) classifying the comment
- `obscene`: value between 0(non-obscene) and 1(obscene) classifying the comment
- `identity_attack`: value between 0(non-identity_hate) or 1(identity_hate) classifying the comment
- `insult`: value between 0(non-insult) or 1(insult) classifying the comment
- `threat`: value between 0(non-threat) and 1(threat) classifying the comment
- For a subset of rows, columns containing whether the comment mentions the entities (they may contain NaNs):
- `male`
- `female`
- `transgender`
- `other_gender`
- `heterosexual`
- `homosexual_gay_or_lesbian`
- `bisexual`
- `other_sexual_orientation`
- `christian`
- `jewish`
- `muslim`
- `hindu`
- `buddhist`
- `atheist`
- `other_religion`
- `black`
- `white`
- `asian`
- `latino`
- `other_race_or_ethnicity`
- `physical_disability`
- `intellectual_or_learning_disability`
- `psychiatric_or_mental_illness`
- `other_disability`
- Other metadata related to the source of the comment, such as creation date, publication id, number of likes,
number of annotators, etc:
- `created_date`
- `publication_id`
- `parent_id`
- `article_id`
- `rating`
- `funny`
- `wow`
- `sad`
- `likes`
- `disagree`
- `sexual_explicit`
- `identity_annotator_count`
- `toxicity_annotator_count`
### Data Splits
There are four splits:
- train: The train dataset as released during the competition. Contains labels and identity information for a
subset of rows.
- test: The train dataset as released during the competition. Does not contain labels nor identity information.
- test_private_expanded: The private leaderboard test set, including toxicity labels and subgroups. The competition target was a binarized version of the toxicity column, which can be easily reconstructed using a >=0.5 threshold.
- test_public_expanded: The public leaderboard test set, including toxicity labels and subgroups. The competition target was a binarized version of the toxicity column, which can be easily reconstructed using a >=0.5 threshold.
## Dataset Creation
### Curation Rationale
The dataset was created to help in efforts to identify and curb instances of toxicity online.
### 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 is released under CC0, as is the underlying comment text.
### Citation Information
No citation is available for this dataset, though you may link to the [kaggle](https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification) competition
### Contributions
Thanks to [@iwontbecreative](https://github.com/iwontbecreative) for adding this dataset. |
true |
# Dataset Card for ConvAi
## 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:** [Add homepage URL here if available (unless it's a GitHub repository)]()
- **Repository:** [If the dataset is hosted on github or has a github homepage, add URL here]()
- **Paper:** [If the dataset was introduced by a paper or there was a paper written describing the dataset, add URL here (landing page for Arxiv paper preferred)]()
- **Leaderboard:** [If the dataset supports an active leaderboard, add link here]()
- **Point of Contact:** [If known, name and email of at least one person the reader can contact for questions about the dataset.]()
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset. |
false |
# Dataset Card for "wiki_split"
## 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://dataset-homepage/](https://dataset-homepage/)
- **Repository:** https://github.com/google-research-datasets/wiki-split
- **Paper:** [Learning To Split and Rephrase From Wikipedia Edit History](https://arxiv.org/abs/1808.09468)
- **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:** 100.28 MB
- **Size of the generated dataset:** 388.40 MB
- **Total amount of disk used:** 488.68 MB
### Dataset Summary
One million English sentences, each split into two sentences that together preserve the original meaning, extracted from Wikipedia
Google's WikiSplit dataset was constructed automatically from the publicly available Wikipedia revision history. Although
the dataset contains some inherent noise, it can serve as valuable training data for models that split or merge sentences.
### Supported Tasks and Leaderboards
- Split and Rephrase
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 100.28 MB
- **Size of the generated dataset:** 388.40 MB
- **Total amount of disk used:** 488.68 MB
An example of 'train' looks as follows.
```
{
"complex_sentence": " '' As she translates from one language to another , she tries to find the appropriate wording and context in English that would correspond to the work in Spanish her poems and stories started to have differing meanings in their respective languages .",
"simple_sentence_1": "' '' As she translates from one language to another , she tries to find the appropriate wording and context in English that would correspond to the work in Spanish . ",
"simple_sentence_2": " Ergo , her poems and stories started to have differing meanings in their respective languages ."
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `complex_sentence`: a `string` feature.
- `simple_sentence_1`: a `string` feature.
- `simple_sentence_2`: a `string` feature.
### Data Splits
| name |train |validation|test|
|-------|-----:|---------:|---:|
|default|989944| 5000|5000|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
The WikiSplit dataset is a verbatim copy of certain content from the publicly available Wikipedia revision history.
The dataset is therefore licensed under [CC BY-SA 4.0](http://creativecommons.org/licenses/by-sa/4.0/).
Any third party content or data is provided "As Is" without any warranty, express or implied.
### Citation Information
```
@inproceedings{botha-etal-2018-learning,
title = "Learning To Split and Rephrase From {W}ikipedia Edit History",
author = "Botha, Jan A. and
Faruqui, Manaal and
Alex, John and
Baldridge, Jason and
Das, Dipanjan",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1080",
doi = "10.18653/v1/D18-1080",
pages = "732--737",
}
```
### Contributions
Thanks to [@thomwolf](https://github.com/thomwolf), [@patrickvonplaten](https://github.com/patrickvonplaten), [@albertvillanova](https://github.com/albertvillanova), [@lewtun](https://github.com/lewtun) for adding this dataset. |
false | # Dataset Card for the MeDAL dataset
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Repository:** https://github.com/BruceWen120/medal
- **Paper:** https://www.aclweb.org/anthology/2020.clinicalnlp-1.15/
- **Dataset (Kaggle):** https://www.kaggle.com/xhlulu/medal-emnlp
- **Dataset (Zenodo):** https://zenodo.org/record/4265632
- **Pretrained model:** https://huggingface.co/xhlu/electra-medal
- **Leaderboard:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Dataset Summary
A large medical text dataset (14Go) curated to 4Go for abbreviation disambiguation, designed for natural language understanding pre-training in the medical domain. For example, DHF can be disambiguated to dihydrofolate, diastolic heart failure, dengue hemorragic fever or dihydroxyfumarate
### Supported Tasks and Leaderboards
Medical abbreviation disambiguation
### Languages
English (en)
## Dataset Structure
Each file is a table consisting of three columns:
* text: The normalized content of an abstract
* location: The location (index) of each abbreviation that was substituted
* label: The word at that was substituted at the given location
### Data Instances
An example from the train split is:
```
{'abstract_id': 14145090,
'text': 'velvet antlers vas are commonly used in traditional chinese medicine and invigorant and contain many PET components for health promotion the velvet antler peptide svap is one of active components in vas based on structural study the svap interacts with tgfβ receptors and disrupts the tgfβ pathway we hypothesized that svap prevents cardiac fibrosis from pressure overload by blocking tgfβ signaling SDRs underwent TAC tac or a sham operation T3 one month rats received either svap mgkgday or vehicle for an additional one month tac surgery induced significant cardiac dysfunction FB activation and fibrosis these effects were improved by treatment with svap in the heart tissue tac remarkably increased the expression of tgfβ and connective tissue growth factor ctgf ROS species C2 and the phosphorylation C2 of smad and ERK kinases erk svap inhibited the increases in reactive oxygen species C2 ctgf expression and the phosphorylation of smad and erk but not tgfβ expression in cultured cardiac fibroblasts angiotensin ii ang ii had similar effects compared to tac surgery such as increases in αsmapositive CFs and collagen synthesis svap eliminated these effects by disrupting tgfβ IB to its receptors and blocking ang iitgfβ downstream signaling these results demonstrated that svap has antifibrotic effects by blocking the tgfβ pathway in CFs',
'location': [63],
'label': ['transverse aortic constriction']}
```
### Data Fields
The column types are:
* text: content of the abstract as a string
* location: index of the substitution as an integer
* label: substitued word as a string
### Data Splits
The following files are present:
* `full_data.csv`: The full dataset with all 14M abstracts.
* `train.csv`: The subset used to train the baseline and proposed models.
* `valid.csv`: The subset used to validate the model during training for hyperparameter selection.
* `test.csv`: The subset used to evaluate the model and report the results in the tables.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
The original dataset was retrieved and modified from the [NLM website](https://www.nlm.nih.gov/databases/download/pubmed_medline.html).
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
Details on how the abbreviations were created can be found in section 2.2 (Dataset Creation) of the [ACL ClinicalNLP paper](https://aclanthology.org/2020.clinicalnlp-1.15.pdf).
#### 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
Since the abstracts are written in English, the data is biased towards anglo-centric medical research. If you plan to use a model pre-trained on this dataset for a predominantly non-English community, it is important to verify whether there are negative biases present in your model, and ensure that they are correctly mitigated. For instance, you could fine-tune your dataset on a multilingual medical disambiguation dataset, or collect a dataset specific to your use case.
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
The ELECTRA model is licensed under [Apache 2.0](https://github.com/google-research/electra/blob/master/LICENSE). The license for the libraries used in this project (`transformers`, `pytorch`, etc.) can be found in their respective GitHub repository. Our model is released under a MIT license.
The original dataset was retrieved and modified from the [NLM website](https://www.nlm.nih.gov/databases/download/pubmed_medline.html). By using this dataset, you are bound by the [terms and conditions](https://www.nlm.nih.gov/databases/download/terms_and_conditions_pubmed.html) specified by NLM:
> INTRODUCTION
>
> Downloading data from the National Library of Medicine FTP servers indicates your acceptance of the following Terms and Conditions: No charges, usage fees or royalties are paid to NLM for this data.
>
> MEDLINE/PUBMED SPECIFIC TERMS
>
> NLM freely provides PubMed/MEDLINE data. Please note some PubMed/MEDLINE abstracts may be protected by copyright.
>
> GENERAL TERMS AND CONDITIONS
>
> * Users of the data agree to:
> * acknowledge NLM as the source of the data by including the phrase "Courtesy of the U.S. National Library of Medicine" in a clear and conspicuous manner,
> * properly use registration and/or trademark symbols when referring to NLM products, and
> * not indicate or imply that NLM has endorsed its products/services/applications.
>
> * Users who republish or redistribute the data (services, products or raw data) agree to:
> * maintain the most current version of all distributed data, or
> * make known in a clear and conspicuous manner that the products/services/applications do not reflect the most current/accurate data available from NLM.
>
> * These data are produced with a reasonable standard of care, but NLM makes no warranties express or implied, including no warranty of merchantability or fitness for particular purpose, regarding the accuracy or completeness of the data. Users agree to hold NLM and the U.S. Government harmless from any liability resulting from errors in the data. NLM disclaims any liability for any consequences due to use, misuse, or interpretation of information contained or not contained in the data.
>
> * NLM does not provide legal advice regarding copyright, fair use, or other aspects of intellectual property rights. See the NLM Copyright page.
>
> * NLM reserves the right to change the type and format of its machine-readable data. NLM will take reasonable steps to inform users of any changes to the format of the data before the data are distributed via the announcement section or subscription to email and RSS updates.
### Citation Information
```
@inproceedings{wen-etal-2020-medal,
title = "{M}e{DAL}: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining",
author = "Wen, Zhi and
Lu, Xing Han and
Reddy, Siva",
booktitle = "Proceedings of the 3rd Clinical Natural Language Processing Workshop",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.clinicalnlp-1.15",
pages = "130--135",
abstract = "One of the biggest challenges that prohibit the use of many current NLP methods in clinical settings is the availability of public datasets. In this work, we present MeDAL, a large medical text dataset curated for abbreviation disambiguation, designed for natural language understanding pre-training in the medical domain. We pre-trained several models of common architectures on this dataset and empirically showed that such pre-training leads to improved performance and convergence speed when fine-tuning on downstream medical tasks.",
}
```
### Contributions
Thanks to [@Narsil](https://github.com/Narsil) and [@xhlulu](https://github.com/xhlulu)) for adding this dataset. |
false |
# Dataset Card for Mocha
## 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:** [Mocha](https://allennlp.org/mocha)
- **Repository:** [https://github.com/anthonywchen/MOCHA](https://github.com/anthonywchen/MOCHA)
- **Paper:** [MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics](https://www.aclweb.org/anthology/2020.emnlp-main.528/)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
Posing reading comprehension as a generation problem provides a great deal of flexibility, allowing for open-ended questions with few restrictions on possible answers. However, progress is impeded by existing generation metrics, which rely on token overlap and are agnostic to the nuances of reading comprehension. To address this, we introduce a benchmark for training and evaluating generative reading comprehension metrics: MOdeling Correctness with Human Annotations. MOCHA contains 40K human judgement scores on model outputs from 6 diverse question answering datasets and an additional set of minimal pairs for evaluation. Using MOCHA, we train a Learned Evaluation metric for Reading Comprehension, LERC, to mimic human judgement scores. LERC outperforms baseline metrics by 10 to 36 absolute Pearson points on held-out annotations. When we evaluate robustness on minimal pairs, LERC achieves 80% accuracy, outperforming baselines by 14 to 26 absolute percentage points while leaving significant room for improvement. MOCHA presents a challenging problem for developing accurate and robust generative reading comprehension metrics.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English
## Dataset Structure
### Data Instances
MOCHA contains 40K human judgement scores on model outputs from 6 diverse question answering datasets and an additional set of minimal pairs for evaluation. MOCHA pairs reading comprehension instances, which consists of a passage, question, and reference, with candidates and human judgement scores.
### Data Fields
- `constituent_dataset`: the original QA dataset which the data instance came from.
- `id`
- `context`: the passage content.
- `question`: the question related to the passage content.
- `reference`: the correct answer for the question.
- `candidate`: the answer generated from the `reference` by `source`
- `score`: the human judgement score for the `candidate`. Not included in test split, defaults to `-1`
- `metadata`: Not included in minimal pairs split.
- `scores`: list of scores from difference judges, averaged out to get final `score`. defaults to `[]`
- `source`: the generative model to generate the `candidate`
In minimal pairs, we'll have an additional candidate for robust evaluation.
- `candidate2`
- `score2`
### Data Splits
Dataset Split | Number of Instances in Split
--------------|--------------------------------------------
Train | 31,069
Validation | 4,009
Test | 6,321
Minimal Pairs | 200
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/legalcode)
### Citation Information
```bitex
@inproceedings{Chen2020MOCHAAD,
author={Anthony Chen and Gabriel Stanovsky and Sameer Singh and Matt Gardner},
title={MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics},
booktitle={EMNLP},
year={2020}
}
```
### Contributions
Thanks to [@mattbui](https://github.com/mattbui) for adding this dataset. |
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 sentiment.
1. The dataset holds 11,932 documents annotated with 3 labels:
```python
sentiments = {
"LABEL_0": "Bearish",
"LABEL_1": "Bullish",
"LABEL_2": "Neutral"
}
```
The data was collected using the Twitter API. The current dataset supports the multi-class classification task.
### Task: Sentiment Analysis
# Data Splits
There are 2 splits: train and validation. Below are the statistics:
| Dataset Split | Number of Instances in Split |
| ------------- | ------------------------------------------- |
| Train | 9,938 |
| Validation | 2,486 |
# Licensing Information
The Twitter Financial Dataset (sentiment) version 1.0.0 is released under the MIT License. |
true |
# Dataset Card for Media-Bias-Identification-Benchmark
## Table of Contents
- [Dataset Card for Media-Bias-Identification-Benchmark](#dataset-card-for-mbib)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Tasks and Information](#tasks-and-information)
- [Baseline](#baseline)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [cognitive-bias](#cognitive-bias)
- [Data Fields](#data-fields)
- [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)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://github.com/Media-Bias-Group/Media-Bias-Identification-Benchmark
- **Repository:** https://github.com/Media-Bias-Group/Media-Bias-Identification-Benchmark
- **Paper:** TODO
- **Point of Contact:** [Martin Wessel](mailto:martin.wessel@uni-konstanz.de)
### Baseline
<table>
<tr><td><b>Task</b></td><td><b>Model</b></td><td><b>Micro F1</b></td><td><b>Macro F1</b></td></tr>
<td>cognitive-bias</td> <td> ConvBERT/ConvBERT</td> <td>0.7126</td> <td> 0.7664</td></tr>
<td>fake-news</td> <td>Bart/RoBERTa-T</td> <td>0.6811</td> <td> 0.7533</td> </tr>
<td>gender-bias</td> <td> RoBERTa-T/ELECTRA</td> <td>0.8334</td> <td>0.8211</td> </tr>
<td>hate-speech</td> <td>RoBERTA-T/Bart</td> <td>0.8897</td> <td> 0.7310</td> </tr>
<td>linguistic-bias</td> <td> ConvBERT/Bart </td> <td> 0.7044 </td> <td> 0.4995 </td> </tr>
<td>political-bias</td> <td> ConvBERT/ConvBERT </td> <td> 0.7041 </td> <td> 0.7110 </td> </tr>
<td>racial-bias</td> <td> ConvBERT/ELECTRA </td> <td> 0.8772 </td> <td> 0.6170 </td> </tr>
<td>text-leve-bias</td> <td> ConvBERT/ConvBERT </td> <td> 0.7697</td> <td> 0.7532 </td> </tr>
</table>
### Languages
All datasets are in English
## Dataset Structure
### Data Instances
#### cognitive-bias
An example of one training instance looks as follows.
```json
{
"text": "A defense bill includes language that would require military hospitals to provide abortions on demand",
"label": 1
}
```
### Data Fields
- `text`: a sentence from various sources (eg., news articles, twitter, other social media).
- `label`: binary indicator of bias (0 = unbiased, 1 = biased)
## Considerations for Using the Data
### Social Impact of Dataset
We believe that MBIB offers a new common ground
for research in the domain, especially given the rising amount of
(research) attention directed toward media bias
### Citation Information
```
@inproceedings{
title = {Introducing MBIB - the first Media Bias Identification Benchmark Task and Dataset Collection},
author = {Wessel, Martin and Spinde, Timo and Horych, Tomáš and Ruas, Terry and Aizawa, Akiko and Gipp, Bela},
year = {2023},
note = {[in review]}
}
```
|
false |
# Dataset Card for Generics KB
## 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://allenai.org/data/genericskb)
- **Repository:** [Repository](https://drive.google.com/drive/folders/1vqfVXhJXJWuiiXbUa4rZjOgQoJvwZUoT)
- **Paper:** [Paper](https://arxiv.org/pdf/2005.00660.pdf)
- **Point of Contact:**[Sumithra Bhakthavatsalam](sumithrab@allenai.org)
[Chloe Anastasiades](chloea@allenai.org)
[Peter Clark](peterc@allenai.org)
Alternatively email_at info@allenai.org
### Dataset Summary
Dataset contains a large (3.5M+ sentence) knowledge base of *generic sentences*. This is the first large resource to contain *naturally occurring* generic sentences, rich in high-quality, general, semantically complete statements. All GenericsKB sentences are annotated with their topical term, surrounding context (sentences), and a (learned) confidence. We also release GenericsKB-Best (1M+ sentences), containing the best-quality generics in GenericsKB augmented with selected, synthesized generics from WordNet and ConceptNet. This demonstrates that GenericsKB can be a useful resource for NLP applications, as well as providing data for linguistic studies of generics and their semantics.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is in English.
## Dataset Structure
### Data Instances
The GENERICSKB contains 3,433,000 sentences. GENERICS-KB-BEST comprises of GENERICSKB generics with a score > 0.234, augmented with short generics synthesized from three other resources for all the terms (generic categories) in GENERICSKB- BEST. GENERICSKB-BEST contains 1,020,868 generics (774,621 from GENERICSKB plus 246,247 synthesized).
SimpleWikipedia is a filtered scrape of SimpleWikipedia pages (simple.wikipedia.org). The Waterloo corpus is 280GB of English plain text, gathered by Charles Clarke (Univ. Waterloo) using a webcrawler in 2001 from .edu domains.
###### Sample SimpleWikipedia/ Waterloo config look like this
```
{'source_name': 'SimpleWikipedia', 'sentence': 'Sepsis happens when the bacterium enters the blood and make it form tiny clots.', 'sentences_before': [], 'sentences_after': [], 'concept_name': 'sepsis', 'quantifiers': {}, 'id': 'SimpleWikipedia--tmp-sw-rs1-with-bug-fixes-initialprocessing-inputs-articles-with-clean-sentences-jsonl-c27816b298e1e0b5326916ee4e2fd0f1603caa77-100-Bubonic-plague--Different-kinds-of-the-same-disease--Septicemic-plague-0-0-039fbe9c11adde4ff9a829376ca7e0ed-1560874903-47882-/Users/chloea/Documents/aristo/commonsense/kbs/simplewikipedia/commonsense-filtered-good-rs1.jsonl-1f33b1e84018a2b1bfdf446f9a6491568b5585da-1561086091.8220549', 'bert_score': 0.8396177887916565}
```
###### Sample instance for Generics KB datasets look like this:
```
{'source': 'Waterloo', 'term': 'aardvark', 'quantifier_frequency': '', 'quantifier_number': '', 'generic_sentence': 'Aardvarks are very gentle animals.', 'score': '0.36080607771873474'}
{'source': 'TupleKB', 'term': 'aardvark', 'quantifier_frequency': '', 'quantifier_number': '', 'generic_sentence': 'Aardvarks dig burrows.', 'score': '1.0'}
```
### Data Fields
The fields in GenericsKB-Best.tsv and GenericsKB.tsv are as follows:
- `SOURCE`: denotes the source of the generic
- `TERM`: denotes the category that is the topic of the generic.
- `GENERIC SENTENCE`: is the sentence itself.
- `SCORE`: Is the BERT-trained score, measuring the degree to which the generic represents a "useful, general truth" about the world (as judged by crowdworkers). Score ranges from 0 (worst) to 1 (best). Sentences with scores below 0.23 (corresponding to an "unsure" vote by crowdworkers) are in GenericsKB, but are not part of GenericsKB-Best due to their unreliability.
- `QUANTIFIER_FREQUENCY`:For generics with explicit quantifiers (all, most, etc.) the quantifier is listed - Frequency contains values such as 'usually', 'often', 'frequently'
- `QUANTIFIER_NUMBER`: For generics with explicit quantifiers (all, most, etc.) with values such as 'all'|'any'|'most'|'much'|'some' etc...
The SimpleWiki/Waterloo generics from GenericsKB.tsv, but expanded to also include their surrounding context (before/after sentences). The Waterloo generics are the majority of GenericsKB. This zip file is 1.4GB expanding to 5.5GB.
There is a json representation for every generic statement in the Generics KB. The generic statement is stored under the `sentence` field within the `knowledge` object. There is also a `bert_score` associated with each sentence which is the BERT-based classifier's score for the 'genericness' of the statement. This score is meant to reflect how much generalized world knowledge/commonsense the statement captures vs only being contextually meaningful.
Detailed description of each of the fields:
- `source_name`: The name of the corpus the generic statement was picked from.
- `sentence`: The generic sentence.
- `sentences_before`: Provides context information surrounding the generic statement from the original corpus.Up to five sentences preceding the generic sentence in the original corpus.
- `sentences_after`: Up to five sentences following the generic sentence in the original corpus.
- `concept_name`: A concept that is the subject of the generic statement.
- `quantifiers`: The quantifiers for the key concept of the generic statement. There can be multiple quantifiers to allow for statements such as "All bats sometimes fly", where 'all' and 'sometimes' are both quantifiers reflecting number and frequency respectively.
- `id`: Unique identifier for a generic statement in the kb.
- `bert_score`: Score for the generic statement from the BERT-based generics classifier.
<br>**Additional fields that apply only to SimpleWiki dataset**
- `headings`: A breadcrumb of section/subsection headings from the top down to the location of the generic statement in the corpus. It applies to SimpleWikipedia which has a hierarchical structure.
- `categories`:The listed categories under which the source article falls. Applies to SimpleWikipedia.
### Data Splits
There are no splits.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
Data was crawled. SimpleWikipedia is a filtered scrape of SimpleWikipedia pages (simple.wikipedia.org). The Waterloo corpus is 280GB of English plain text, gathered by Charles Clarke (Univ. Waterloo) using a webcrawler in 2001 from .edu domains.
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
Bert was used to decide whether the sentence is useful or not. Every sentence has a bert score.
#### Who are the annotators?
No annotations were made.
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
The GenericsKB is available under the Creative Commons - Attribution 4.0 International - licence.
As an informal summary, from https://creativecommons.org/licenses/by/4.0/, you are free to:
Share ― copy and redistribute the material in any medium or format
Adapt ― remix, transform, and build upon the material for any purpose, even commercially.
under the following terms:
Attribution ― You must give appropriate credit, provide a link to the license, and
indicate if changes were made. You may do so in any reasonable manner,
but not in any way that suggests the licensor endorses you or your use.
No additional restrictions ― You may not apply legal terms or technological measures
that legally restrict others from doing anything the license permits.
For details, see https://creativecommons.org/licenses/by/4.0/ or the or the included
file "Creative Commons ― Attribution 4.0 International ― CC BY 4.0.pdf" in this folder.
### Citation Information
```
@InProceedings{huggingface:dataset,
title = {GenericsKB: A Knowledge Base of Generic Statements},
authors={Sumithra Bhakthavatsalam, Chloe Anastasiades, Peter Clark},
year={2020},
publisher = {Allen Institute for AI},
}
```
### Contributions
Thanks to [@bpatidar](https://github.com/bpatidar) for adding this dataset. |
false |
# Dataset Card for Corpus for Knowledge-Enhanced Language Model Pre-training (KELM)
## 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/google-research-datasets/KELM-corpus
- **Repository:** https://github.com/google-research-datasets/KELM-corpus
- **Paper:** https://arxiv.org/abs/2010.12688
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
Data-To-Text Generation involves converting knowledge graph (KG) triples of the form (subject, relation, object) into
a natural language sentence(s). This dataset consists of English KG data converted into paired natural language text.
The generated corpus consists of ∼18M sentences spanning ∼45M triples with ∼1500 distinct relations.
### Supported Tasks and Leaderboards
The intended task is data-to-text generation, taking in a knowledge graph tuple and generating a natural language
representation from it. Specifically, the data is in the format the authors used to train a seq2seq language model
with the tuples concatenated into a single sequence.
### Languages
The dataset is in English.
## Dataset Structure
### Data Instances
Each instance consists of one KG triple paired with corresponding natural language.
### Data Fields
- `triple`: Wikipedia triples of the form `<subject> <relation> <object>` where some subjects have multiple
relations, e.g. `<subject> <relation1> <object1> <relation2> <object2> <relation3> <object3>`. For more details on
how these relations are grouped, please refer to the paper.
- `sentence`: The corresponding Wikipedia sentence.
### Data Splits
The dataset includes a pre-determined train, validation, and test split.
## Dataset Creation
### Curation Rationale
The goal of the dataset's curation and the associated modeling work discussed in the paper is to be able to generate
natural text from a knowledge graph.
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
The data is sourced from English Wikipedia and it's associated knowledge graph.
### 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
From the paper:
> Wikipedia has documented ideological, gender6, and racial biases in its text. While the KELM corpus may still
contain some of these biases, certain types of biases may be reduced.
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
This dataset has been released under the [CC BY-SA 2.0 license](https://creativecommons.org/licenses/by-sa/2.0/).
### Citation Information
```
@misc{agarwal2020large,
title={Large Scale Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training},
author={Oshin Agarwal and Heming Ge and Siamak Shakeri and Rami Al-Rfou},
year={2020},
eprint={2010.12688},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@joeddav](https://github.com/joeddav) for adding this dataset. |
true |
# Dataset Card for generated_reviews_enth
## 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:** ttp://airesearch.in.th/
- **Repository:** https://github.com/vistec-ai/generated_reviews_enth
- **Paper:** https://arxiv.org/pdf/2007.03541.pdf
- **Leaderboard:**
- **Point of Contact:** [AIResearch](http://airesearch.in.th/)
### Dataset Summary
`generated_reviews_enth` is created as part of [scb-mt-en-th-2020](https://arxiv.org/pdf/2007.03541.pdf) for machine translation task. This dataset (referred to as `generated_reviews_yn` in [scb-mt-en-th-2020](https://arxiv.org/pdf/2007.03541.pdf)) are English product reviews generated by [CTRL](https://arxiv.org/abs/1909.05858), translated by Google Translate API and annotated as accepted or rejected (`correct`) based on fluency and adequacy of the translation by human annotators. This allows it to be used for English-to-Thai translation quality esitmation (binary label), machine translation, and sentiment analysis.
### Supported Tasks and Leaderboards
English-to-Thai translation quality estimation (binary label) is the intended use. Other uses include machine translation and sentiment analysis.
### Languages
English, Thai
## Dataset Structure
### Data Instances
```
{'correct': 0, 'review_star': 4, 'translation': {'en': "I had a hard time finding a case for my new LG Lucid 2 but finally found this one on amazon. The colors are really pretty and it works just as well as, if not better than the otterbox. Hopefully there will be more available by next Xmas season. Overall, very cute case. I love cheetah's. :)", 'th': 'ฉันมีปัญหาในการหาเคสสำหรับ LG Lucid 2 ใหม่ของฉัน แต่ในที่สุดก็พบเคสนี้ใน Amazon สีสวยมากและใช้งานได้ดีเช่นเดียวกับถ้าไม่ดีกว่านาก หวังว่าจะมีให้มากขึ้นในช่วงเทศกาลคริสต์มาสหน้า โดยรวมแล้วน่ารักมาก ๆ ฉันรักเสือชีตาห์ :)'}}
{'correct': 0, 'review_star': 1, 'translation': {'en': "This is the second battery charger I bought as a Christmas present, that came from Amazon, after one purchased before for my son. His was still working. The first charger, received in July, broke apart and wouldn't charge anymore. Just found out two days ago they discontinued it without warning. It took quite some time to find the exact replacement charger. Too bad, really liked it. One of these days, will purchase an actual Nikon product, or go back to buying batteries.", 'th': 'นี่เป็นเครื่องชาร์จแบตเตอรี่ก้อนที่สองที่ฉันซื้อเป็นของขวัญคริสต์มาสซึ่งมาจากอเมซอนหลังจากที่ซื้อมาเพื่อลูกชายของฉัน เขายังทำงานอยู่ เครื่องชาร์จแรกที่ได้รับในเดือนกรกฎาคมแตกเป็นชิ้น ๆ และจะไม่ชาร์จอีกต่อไป เพิ่งค้นพบเมื่อสองวันก่อนพวกเขาหยุดมันโดยไม่มีการเตือนล่วงหน้า ใช้เวลาพอสมควรในการหาที่ชาร์จที่ถูกต้อง แย่มากชอบมาก สักวันหนึ่งจะซื้อผลิตภัณฑ์ Nikon จริงหรือกลับไปซื้อแบตเตอรี่'}}
{'correct': 1, 'review_star': 1, 'translation': {'en': 'I loved the idea of having a portable computer to share pictures with family and friends on my big screen. It worked really well for about 3 days, then when i opened it one evening there was water inside where all the wires came out. I cleaned that up and put some tape over that, so far, no leaks. My husband just told me yesterday, however, that this thing is trash.', 'th': 'ฉันชอบไอเดียที่มีคอมพิวเตอร์พกพาเพื่อแชร์รูปภาพกับครอบครัวและเพื่อน ๆ บนหน้าจอขนาดใหญ่ของฉัน มันใช้งานได้ดีจริง ๆ ประมาณ 3 วันจากนั้นเมื่อฉันเปิดมันในเย็นวันหนึ่งมีน้ำอยู่ภายในที่ซึ่งสายไฟทั้งหมดออกมา ฉันทำความสะอาดมันแล้ววางเทปไว้ที่นั่นจนถึงตอนนี้ไม่มีรอยรั่ว สามีของฉันเพิ่งบอกฉันเมื่อวานนี้ว่าสิ่งนี้เป็นขยะ'}}
```
### Data Fields
- `translation`:
- `en`: English product reviews generated by [CTRL](https://arxiv.org/abs/1909.05858)
- `th`: Thai product reviews translated from `en` by Google Translate API
- `review_star`: Stars of the generated reviews, put as condition for [CTRL](https://arxiv.org/abs/1909.05858)
- `correct`: 1 if the English-to-Thai translation is accepted (`correct`) based on fluency and adequacy of the translation by human annotators else 0
### Data Splits
| | train | valid | test |
|-----------------|--------|-------|-------|
| # samples | 141369 | 15708 | 17453 |
| # correct:0 | 99296 | 10936 | 12208 |
| # correct:1 | 42073 | 4772 | 5245 |
| # review_star:1 | 50418 | 5628 | 6225 |
| # review_star:2 | 22876 | 2596 | 2852 |
| # review_star:3 | 22825 | 2521 | 2831 |
| # review_star:1 | 22671 | 2517 | 2778 |
| # review_star:5 | 22579 | 2446 | 2767 |
## Dataset Creation
### Curation Rationale
`generated_reviews_enth` is created as part of [scb-mt-en-th-2020](https://arxiv.org/pdf/2007.03541.pdf) for machine translation task. This dataset (referred to as `generated_reviews_yn` in [scb-mt-en-th-2020](https://arxiv.org/pdf/2007.03541.pdf)) are English product reviews generated by [CTRL](https://arxiv.org/abs/1909.05858), translated by Google Translate API and annotated as accepted or rejected (`correct`) based on fluency and adequacy of the translation by human annotators. This allows it to be used for English-to-Thai translation quality esitmation (binary label), machine translation, and sentiment analysis.
### Source Data
#### Initial Data Collection and Normalization
The data generation process is as follows:
- `en` is generated using conditional generation of [CTRL](https://arxiv.org/abs/1909.05858), stating a star review for each generated product review.
- `th` is translated from `en` using Google Translate API
- `correct` is annotated as accepted or rejected (1 or 0) based on fluency and adequacy of the translation by human annotators
For this specific dataset for translation quality estimation task, we apply the following preprocessing:
- Drop duplciates on `en`,`th`,`review_star`,`correct`; duplicates might exist because the translation checking is done by annotators.
- Remove reviews that are not between 1-5 stars.
- Remove reviews whose `correct` are not 0 or 1.
- Deduplicate on `en` which contains the source sentences.
#### Who are the source language producers?
[CTRL](https://arxiv.org/abs/1909.05858)
### Annotations
#### Annotation process
Annotators are given English and Thai product review pairs. They are asked to label the pair as acceptable translation or not based on fluency and adequacy of the translation.
#### Who are the annotators?
Human annotators of [Hope Data Annotations](https://www.hopedata.org/) hired by [AIResearch.in.th](http://airesearch.in.th/)
### Personal and Sensitive Information
The authors do not expect any personal or sensitive information to be in the generated product reviews, but they could slip through from pretraining of [CTRL](https://arxiv.org/abs/1909.05858).
## Considerations for Using the Data
### Social Impact of Dataset
- English-Thai translation quality estimation for machine translation
- Product review classification for Thai
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
Due to annotation process constraints, the number of one-star reviews are notably higher than other-star reviews. This makes the dataset slighly imbalanced.
## Additional Information
### Dataset Curators
The dataset was created by [AIResearch.in.th](http://airesearch.in.th/)
### Licensing Information
CC BY-SA 4.0
### Citation Information
```
@article{lowphansirikul2020scb,
title={scb-mt-en-th-2020: A Large English-Thai Parallel Corpus},
author={Lowphansirikul, Lalita and Polpanumas, Charin and Rutherford, Attapol T and Nutanong, Sarana},
journal={arXiv preprint arXiv:2007.03541},
year={2020}
}
```
### Contributions
Thanks to [@cstorm125](https://github.com/cstorm125) for adding this dataset. |
true |
# STSb Turkish
Semantic textual similarity dataset for the Turkish language. It is a machine translation (Azure) of the [STSb English](http://ixa2.si.ehu.eus/stswiki/index.php/STSbenchmark) dataset. This dataset is not reviewed by expert human translators.
Uploaded from [this repository](https://github.com/emrecncelik/sts-benchmark-tr). |
false |
# Dataset Card for "lmqg/qg_squad"
## Dataset Description
- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
- **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
- **Point of Contact:** [Asahi Ushio](http://asahiushio.com/)
### Dataset Summary
This is a subset of [QG-Bench](https://github.com/asahi417/lm-question-generation/blob/master/QG_BENCH.md#datasets), a unified question generation benchmark proposed in
["Generative Language Models for Paragraph-Level Question Generation: A Unified Benchmark and Evaluation, EMNLP 2022 main conference"](https://arxiv.org/abs/2210.03992).
This is [SQuAD](https://rajpurkar.github.io/SQuAD-explorer/) dataset for question generation (QG) task. The split
of train/development/test set follows the ["Neural Question Generation"](https://arxiv.org/abs/1705.00106) work and is
compatible with the [leader board](https://paperswithcode.com/sota/question-generation-on-squad11).
### Supported Tasks and Leaderboards
* `question-generation`: The dataset is assumed to be used to train a model for question generation.
Success on this task is typically measured by achieving a high BLEU4/METEOR/ROUGE-L/BERTScore/MoverScore (see our paper for more in detail).
This task has an active leaderboard which can be found at [here](https://paperswithcode.com/sota/question-generation-on-squad11).
### Languages
English (en)
## Dataset Structure
An example of 'train' looks as follows.
```
{
"question": "What is heresy mainly at odds with?",
"paragraph": "Heresy is any provocative belief or theory that is strongly at variance with established beliefs or customs. A heretic is a proponent of such claims or beliefs. Heresy is distinct from both apostasy, which is the explicit renunciation of one's religion, principles or cause, and blasphemy, which is an impious utterance or action concerning God or sacred things.",
"answer": "established beliefs or customs",
"sentence": "Heresy is any provocative belief or theory that is strongly at variance with established beliefs or customs .",
"paragraph_sentence": "<hl> Heresy is any provocative belief or theory that is strongly at variance with established beliefs or customs . <hl> A heretic is a proponent of such claims or beliefs. Heresy is distinct from both apostasy, which is the explicit renunciation of one's religion, principles or cause, and blasphemy, which is an impious utterance or action concerning God or sacred things.",
"paragraph_answer": "Heresy is any provocative belief or theory that is strongly at variance with <hl> established beliefs or customs <hl>. A heretic is a proponent of such claims or beliefs. Heresy is distinct from both apostasy, which is the explicit renunciation of one's religion, principles or cause, and blasphemy, which is an impious utterance or action concerning God or sacred things.",
"sentence_answer": "Heresy is any provocative belief or theory that is strongly at variance with <hl> established beliefs or customs <hl> ."
}
```
The data fields are the same among all splits.
- `question`: a `string` feature.
- `paragraph`: a `string` feature.
- `answer`: a `string` feature.
- `sentence`: a `string` feature.
- `paragraph_answer`: a `string` feature, which is same as the paragraph but the answer is highlighted by a special token `<hl>`.
- `paragraph_sentence`: a `string` feature, which is same as the paragraph but a sentence containing the answer is highlighted by a special token `<hl>`.
- `sentence_answer`: a `string` feature, which is same as the sentence but the answer is highlighted by a special token `<hl>`.
Each of `paragraph_answer`, `paragraph_sentence`, and `sentence_answer` feature is assumed to be used to train a question generation model,
but with different information. The `paragraph_answer` and `sentence_answer` features are for answer-aware question generation and
`paragraph_sentence` feature is for sentence-aware question generation.
## Data Splits
|train|validation|test |
|----:|---------:|----:|
|75722| 10570|11877|
## Citation Information
```
@inproceedings{ushio-etal-2022-generative,
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
author = "Ushio, Asahi and
Alva-Manchego, Fernando and
Camacho-Collados, Jose",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, U.A.E.",
publisher = "Association for Computational Linguistics",
}
``` |
true |
# Dataset Card for LiMiT
## 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:** [github](https://github.com/ilmgut/limit_dataset)
- **Paper:** [LiMiT: The Literal Motion in Text Dataset](https://www.aclweb.org/anthology/2020.findings-emnlp.88/)
- **Leaderboard:** N/A
- **Point of Contact:** [More Information Needed]
### Dataset Summary
Motion recognition is one of the basic cognitive capabilities of many life forms, yet identifying
motion of physical entities in natural language have not been explored extensively and empirically.
Literal-Motion-in-Text (LiMiT) dataset, is a large human-annotated collection of English text sentences
describing physical occurrence of motion, with annotated physical entities in motion.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The text in the dataset is in English (`en`).
## Dataset Structure
### Data Instances
Example of one instance in the dataset
```
{
"id": 0,
"motion": "yes",
"motion_entities": [
{
"entity": "little boy",
"start_index": 2
},
{
"entity": "ball",
"start_index": 30
}
],
"sentence": " A little boy holding a yellow ball walks by."
}
```
### Data Fields
- `id`: intger index of the example
- `motion`: indicates whether the sentence is literal motion i.e. describes the movement of a physical entity or not
- `motion_entities`: A `list` of `dicts` with following keys
- `entity`: the extracted entity in motion
- `start_index`: index in the sentence for the first char of the entity text
### Data Splits
The dataset is split into a `train`, and `test` split with the following sizes:
| | train | validation |
| ----- |------:|-----------:|
| Number of examples | 23559 | 1000 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
```
@inproceedings{manotas-etal-2020-limit,
title = "{L}i{M}i{T}: The Literal Motion in Text Dataset",
author = "Manotas, Irene and
Vo, Ngoc Phuoc An and
Sheinin, Vadim",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.findings-emnlp.88",
doi = "10.18653/v1/2020.findings-emnlp.88",
pages = "991--1000",
abstract = "Motion recognition is one of the basic cognitive capabilities of many life forms, yet identifying motion of physical entities in natural language have not been explored extensively and empirically. We present the Literal-Motion-in-Text (LiMiT) dataset, a large human-annotated collection of English text sentences describing physical occurrence of motion, with annotated physical entities in motion. We describe the annotation process for the dataset, analyze its scale and diversity, and report results of several baseline models. We also present future research directions and applications of the LiMiT dataset and share it publicly as a new resource for the research community.",
}
```
### Contributions
Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset. |
false |
__ODEX__ is an Open-Domain EXecution-based NL-to-Code generation data benchmark.
It contains 945 samples with a total of 1,707 human-written test cases, covering intents in four different natural languages -- 439 in English, 90 in Spanish, 164 in Japanese, and 252 in Russian.
You can load the dataset by specifying a subset from *en, es, ja, ru* (by default the english subset *en* is loaded):
```python
from datasets import load_dataset
ds = load_dataset("neulab/odex", "ja", split="test")
```
If you find our dataset useful, please cite the paper
```
@article{wang2022execution,
title={Execution-Based Evaluation for Open-Domain Code Generation},
author={Zhiruo Wang, Shuyan Zhou, Daniel Fried, Graham Neubig},
journal={arXiv preprint arXiv:2212.10481},
year={2022}
}
``` |
false |
# Dataset Card for British Library Books
## Table of Contents
- [Dataset Card for British Library Books](#dataset-card-for-British-Library-Books)
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Language model training](#language-model-training)
- [Supervised tasks](#supervised-tasks)
- [Languages](#languages)
- [Language change](#language-change)
- [Optical Character Recognition](#optical-character-recognition)
- [OCR word confidence](#ocr-word-confidence)
- [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)
- [Date normalization](#date-normalization)
- [Metadata included](#metadata-included)
- [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)
- [Colonialism](#colonialism)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.bl.uk/collection-guides/digitised-printed-books
- **Repository:** https://doi.org/10.21250/db14
- **Paper:**
- **Leaderboard:**
- **Point of Contact:** labs@bl.uk
### Dataset Summary
This dataset consists of books digitised by the British Library in partnership with Microsoft. The dataset includes ~25 million pages of out of copyright texts. The majority of the texts were published in the 18th and 19th Century, but the collection also consists of a smaller number of books from earlier periods. Items within this collection cover a wide range of subject areas, including geography, philosophy, history, poetry and literature and are published in various languages.
While the books are predominately from the 18th and 19th Centuries, there are fewer books from earlier periods. The number of pages in the corpus by decade:
| | page count |
| ---- | ---------- |
| 1510 | 94 |
| 1520 | 32 |
| 1540 | 184 |
| 1550 | 16 |
| 1580 | 276 |
| 1590 | 540 |
| 1600 | 1117 |
| 1610 | 1132 |
| 1620 | 1856 |
| 1630 | 9274 |
| 1640 | 4232 |
| 1650 | 2944 |
| 1660 | 5858 |
| 1670 | 11415 |
| 1680 | 8348 |
| 1690 | 13756 |
| 1700 | 10160 |
| 1710 | 9556 |
| 1720 | 10314 |
| 1730 | 13282 |
| 1740 | 10778 |
| 1750 | 12001 |
| 1760 | 21415 |
| 1770 | 28490 |
| 1780 | 32676 |
| 1790 | 50014 |
| 1800 | 307806 |
| 1810 | 478008 |
| 1820 | 589419 |
| 1830 | 681212 |
| 1840 | 1113473 |
| 1850 | 1726108 |
| 1860 | 1725407 |
| 1870 | 2069089 |
| 1880 | 2585159 |
| 1890 | 3365031 |
[More Information Needed]
### Supported Tasks and Leaderboards
This collection has been previously used across various digital history and humanities projects since being published.
The dataset consists of text and a range of metadata associated with this text. This metadata includes:
- date of publication
- place of publication
- country of publication
- language
- OCR quality
- physical description of the original physical item
#### Language model training
As a relatively large dataset, `blbooks` provides a source dataset for training language models. The presence of this metadata also offers interesting opportunities to use this dataset as a source for training language models based on:
- specific time-periods
- specific languages
- certain OCR quality thresholds
The above is not an exhaustive list but offer some suggestions of how the dataset can be used to explore topics such as the impact of OCR quality on language models, the ‘transferability’ of language models across time or the impact of training multilingual language models on historical languages.
#### Supervised tasks
Whilst this dataset does not have annotations for a specific NLP task, such as Named Entity Recognition, it does include a wide variety of metadata. This metadata has the potential to be used for training and/or evaluating a variety of supervised tasks predicting this metadata.
### Languages
This dataset consists of books published in several languages. The breakdown of the languages included (at the page level) is:
| Language | Pages |
| --------------------- | -------- |
| English | 10039463 |
| French | 1442929 |
| German | 1172793 |
| Spanish | 286778 |
| Italian | 214255 |
| Dutch | 204759 |
| Russian | 193347 |
| Danish | 93366 |
| Hungarian | 88094 |
| Swedish | 76225 |
| Polish | 58901 |
| Greek, Modern (1453-) | 26104 |
| Latin | 25611 |
| Portuguese | 25410 |
| Czech | 20160 |
| Bulgarian | 7891 |
| Finnish | 5677 |
| Irish | 2743 |
| Serbian | 1975 |
| Romanian | 1544 |
| Norwegian Nynorsk | 1398 |
| Croatian | 1306 |
| Norwegian | 1227 |
| Icelandic | 902 |
| Slovak | 840 |
| Lithuanian | 714 |
| Welsh | 580 |
| Slovenian | 545 |
| Indonesian | 418 |
| Cornish | 223 |
This breakdown was derived from the first language in the associated metadata field. Some books include multiple languages. Some of the languages codes for this data were also derived using computational methods. Therefore, the language fields in the dataset should be treated with some caution (discussed in more detail below).
#### Language change
The publication dates of books in the data cover a broad period of time (1500-1900). For languages in the dataset with broad temporal coverage, significant [language change](https://en.wikipedia.org/wiki/Language_change) might be found. The ability to study this change by taking reasonably large samples of languages covering different time periods is one of the opportunities offered by this dataset. The fact that the text in this dataset was produced via Optical Character Recognition (OCR) causes some challenges for this type of research (see below).
#### Optical Character Recognition
The digitised books in this collection were transformed into machine-readable text using Optical Character Recognition (OCR) software. The text produced via OCR software will usually include some errors. These errors include; mistakes at the character level; for example, an `i` is mistaken for an `l`, at the word level or across significant passages of text.
The books in this dataset can pose some additional challenges for OCR software. OCR errors can stem from:
- the quality of the original printing: printing technology was a developing technology during the time period covered by this corpus; some of the original book text will include misprints, blurred or faded ink that is hard to read
- damage to the page: some of the books will have become damaged over time, this can obscure all or parts of the text on a page
- poor quality scans: scanning books can be challenging; for example, if the book has tight bindings, it can be hard to capture text that has fallen into the [gutter](https://www.abaa.org/glossary/entry/gutter) of the book.
- the language used in the books may differ from the languages OCR software is predominantly trained to recognise.
##### OCR word confidence
Many OCR engines produce some form of confidence score alongside the predicted text. These confidence scores are usually at the character or word level. The word confidence score was given for each word in the original ALTO XML versions of the text in this dataset in this dataset. The OCR confidence scores should be treated with some scepticism. For historical text or in a lower resource language, for example, a low confidence score may be more likely for words not included in a modern dictionary but may be accurate transcriptions of the original text. With that said, the confidence scores do give some sense of the OCR quality.
An example of text with a high (over 90% mean word confidence score):
```
8 direction to the Conduit, round which is a wide open space, and a good broad pavement called the Parade. It commands a pleasant peep of the slopes and terrace throughout its entire length. The street continuing from the Conduit, in the same general direction, was known anciently as Lodborne Lane, and is now named South Street. From the Conduit two other streets, at right angles to these, are Long Street, leading Eastwards, and Half-Moon Street (formerly Lodborne), leading to Westbury, Trendle Street, and the Horsecastles Road.
```
An example of text with a score below 40%:
```
Hannover. Schrift und Druck von Fr. CultniTmn,',
"LeMNs'utluirui.",
'ü 8u«llim» M^äalßwi 01de!lop 1<M.',
'p^dnalmw vom Xr^u/e, lpiti>»**Kmm lie« !»^2!M kleine lii!<! (,«>* ttünee!<»e^ v»n tndzt Lievclum, 1872,
```
The quality of OCR - as measured by mean OCR confidence for a page - across the dataset correlates with other features. A groupby of publication decade and mean word confidence:
| decade | mean_wc_ocr |
| ------ | ----------- |
| 1510 | 0.499151 |
| 1520 | 0.544818 |
| 1540 | 0.511589 |
| 1550 | 0.4505 |
| 1580 | 0.321858 |
| 1590 | 0.461282 |
| 1600 | 0.467318 |
| 1610 | 0.495895 |
| 1620 | 0.501257 |
| 1630 | 0.49766 |
| 1640 | 0.512095 |
| 1650 | 0.528534 |
| 1660 | 0.521014 |
| 1670 | 0.592575 |
| 1680 | 0.583901 |
| 1690 | 0.567202 |
| 1700 | 0.575175 |
| 1710 | 0.61436 |
| 1720 | 0.627725 |
| 1730 | 0.658534 |
| 1740 | 0.64214 |
| 1750 | 0.657357 |
| 1760 | 0.6389 |
| 1770 | 0.651883 |
| 1780 | 0.632326 |
| 1790 | 0.664279 |
| 1800 | 0.682338 |
| 1810 | 0.708915 |
| 1820 | 0.730015 |
| 1830 | 0.730973 |
| 1840 | 0.713886 |
| 1850 | 0.697106 |
| 1860 | 0.696701 |
| 1870 | 0.717233 |
| 1880 | 0.733331 |
| 1890 | 0.762364 |
As might be expected, the earlier periods have lower mean word confidence scores. Again, all of this should be treated with some scepticism, especially as the size of the data grows over time.
As with time, the mean word confidence of the OCR software varies across languages:
| Language_1 | mean_wc_ocr |
| --------------------- | ----------- |
| Croatian | 0.755565 |
| Welsh | 0.7528 |
| Norwegian Nynorsk | 0.751648 |
| Slovenian | 0.746007 |
| French | 0.740772 |
| Finnish | 0.738032 |
| Czech | 0.737849 |
| Hungarian | 0.736076 |
| Dutch | 0.734977 |
| Cornish | 0.733682 |
| Danish | 0.733106 |
| English | 0.733037 |
| Irish | 0.732658 |
| Portuguese | 0.727746 |
| Spanish | 0.725111 |
| Icelandic | 0.724427 |
| Italian | 0.715839 |
| Swedish | 0.715633 |
| Polish | 0.715133 |
| Lithuanian | 0.700003 |
| Bulgarian | 0.694657 |
| Romanian | 0.692957 |
| Latin | 0.689022 |
| Russian | 0.685847 |
| Serbian | 0.674329 |
| Slovak | 0.66739 |
| Greek, Modern (1453-) | 0.632195 |
| German | 0.631457 |
| Indonesian | 0.6155 |
| Norwegian | 0.597987 |
Again, these numbers should be treated sceptically since some languages appear very infrequently. For example, the above table suggests the mean word confidence for Welsh is relatively high. However, there isn’t much Welsh in the dataset. Therefore, it is unlikely that this data will be particularly useful for training (historic) Welsh language models.
[More Information Needed]
## Dataset Structure
The dataset has a number of configurations relating to the different dates of publication in the underlying data:
- `1500_1899`: this configuration covers all years
- `1800_1899`: this configuration covers the years between 1800 and 1899
- `1700_1799`: this configuration covers the years between 1700 and 1799
- `1510_1699`: this configuration covers the years between 1510 and 1699
### Configuration option
All of the configurations have an optional keyword argument `skip_empty_pages` which is set to `True` by default. The underlying dataset includes some pages where there is no text. This could either be because the underlying book page didn't have any text or the OCR software failed to detect this text.
For many uses of this dataset it doesn't make sense to include empty pages so these are skipped by default. However, for some uses you may prefer to retain a representation of the data that includes these empty pages. Passing `skip_empty_pages=False` when loading the dataset will enable this option.
### Data Instances
An example data instance:
```python
{'Country of publication 1': 'England',
'Language_1': 'English',
'Language_2': None,
'Language_3': None,
'Language_4': None,
'Physical description': None,
'Publisher': None,
'all Countries of publication': 'England',
'all names': 'Settle, Elkanah [person]',
'date': 1689,
'empty_pg': True,
'mean_wc_ocr': 0.0,
'multi_language': False,
'name': 'Settle, Elkanah',
'pg': 1,
'place': 'London',
'raw_date': '1689',
'record_id': '001876770',
'std_wc_ocr': 0.0,
'text': None,
‘title’: ‘The Female Prelate: being the history and the life and death of Pope Joan. A tragedy [in five acts and in verse] . Written by a Person of Quality [i.e. Elkanah Settle]’}
```
Each instance in the dataset represents a single page from an original digitised book.
### Data Fields
Included in this dataset are:
| Field | Data Type | Description |
| ---------------------------- | --------- | ------------------------------------------------------------------------------------------------------------- |
| record_id | string | British Library ID for the item |
| date | int | parsed/normalised year for the item. i.e. 1850 |
| raw_date | string | the original raw date for an item i.e. 1850- |
| title | string | title of the book |
| place | string | Place of publication, i.e. London |
| empty_pg | bool | whether page contains text |
| text | string | OCR generated text for a page |
| pg | int | page in original book the instance refers to |
| mean_wc_ocr | float | mean word confidence values for the page |
| std_wc_ocr | float | standard deviation of the word confidence values for the page |
| name | string | name associated with the item (usually author) |
| all names | string | all names associated with a publication |
| Publisher | string | publisher of the book |
| Country of publication 1 | string | first country associated with publication |
| all Countries of publication | string | all countries associated with a publication |
| Physical description | string | physical description of the item (size). This requires some normalisation before use and isn’t always present |
| Language_1 | string | first language associated with the book, this is usually present |
| Language_2 | string | |
| Language_3 | string | |
| Language_4 | string | |
| multi_language | bool | |
Some of these fields are not populated a large proportion of the time. You can get some sense of this from this [Pandas Profiling](https://github.com/pandas-profiling/pandas-profiling) [report](https://davanstrien.github.io/BL-datasets-pandas-profile-reports/pandas_profile_report_MS_digitised_books_2021-01-09.html)
The majority of these fields relate to metadata about the books. Most of these fields were created by staff working for the British Library. The notable exception is the “Languages” fields that have sometimes been determined using computational methods. This work is reported in more detail in [Automated Language Identification of Bibliographic Resources](https://doi.org/10.1080/01639374.2019.1700201). It is important to note that metadata is neither perfect nor static. The metadata associated with this book was generated based on export from the British Library catalogue in 2021.
[More Information Needed]
### Data Splits
This dataset contains a single split `train`.
## Dataset Creation
**Note** this section is a work in progress.
### Curation Rationale
The books in this collection were digitised as part of a project partnership between the British Library and Microsoft. [Mass digitisation](https://en.wikipedia.org/wiki/Category:Mass_digitization), i.e. projects intending to quickly digitise large volumes of materials shape the selection of materials to include in several ways. Some considerations which are often involved in the decision of whether to include items for digitisation include (but are not limited to):
- copyright status
- preservation needs
- the size of an item, very large and very small items are often hard to digitise quickly
These criteria can have knock-on effects on the makeup of a collection. For example, systematically excluding large books may result in some types of book content not being digitised. Large volumes are likely to be correlated to content to at least some extent, so excluding them from digitisation will mean that material is underrepresented. Similarly, copyright status is often (but not only) determined by publication date. This can often lead to a rapid fall in the number of items in a collection after a certain cut-off date.
All of the above is largely to make clear that this collection was not curated to create a representative sample of the British Library’s holdings. Some material will be over-represented, and others under-represented. Similarly, the collection should not be considered a representative sample of what was published across the period covered by the dataset (nor that the relative proportions of the data for each time period represent a proportional sample of publications from that period). Finally, and this probably does not need stating, the language included in the text should not be considered representative of either written or spoken language(s) from that time period.
[More Information Needed]
### Source Data
The source data (physical items) includes a variety of resources (predominantly monographs) held by the [British Library](bl.uk/](https://bl.uk/). The British Library is a [Legal Deposit](https://www.bl.uk/legal-deposit/about-legal-deposit) library. “Legal deposit requires publishers to provide a copy of every work they publish in the UK to the British Library. It’s existed in English law since 1662.” [source](https://www.bl.uk/legal-deposit/about-legal-deposit).
The source data for this version of the data is derived from the original ALTO XML files and a recent metadata export #TODO add links
[More Information Needed]
#### Initial Data Collection and Normalization
This version of the dataset was created using the original ALTO XML files and, where a match was found, updating the metadata associated with that item with more recent metadata using an export from the British Library catalogue. The process of creating this new dataset is documented here #TODO add link.
There are a few decisions made in the above processing steps worth highlighting in particular:
##### Date normalization
The metadata around date of publication for an item is not always exact. It often is represented as a date range e.g. `1850-1860`. The `date` field above takes steps to normalise this date to a single integer value. In most cases, this is taking the mean of the values associated with the item. The `raw_date` field includes the unprocessed date string.
##### Metadata included
The metadata associated with each item includes most of the fields available via the ALTO XML. However, the data doesn’t include some metadata fields from the metadata export file. The reason fields were excluded because they are frequently not populated. A cut off of 50% was chosen, i.e. values from the metadata which are missing above 50% of the time were not included. This is slightly arbitrary, but since the aim of this version of the data was to support computational research using the collection it was felt that these fields with frequent missing values would be less valuable.
#### Who are the source language producers?
[More Information Needed]
### Annotations
This dataset does not include annotations as usually understood in the context of NLP. The data does include metadata associated with the books.
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
There a range of considerations around using the data. These include the representativeness of the dataset, the OCR quality and the language used. Depending on your use case, these may be more or less important. For example, the impact of OCR quality on downstream tasks will depend on the target task. It may also be possible to mitigate this negative impact from OCR through tokenizer choice, Language Model training objectives, oversampling high-quality OCR, etc.
[More Information Needed]
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
The text in this collection is derived from historical text. As a result, the text will reflect this time period's social beliefs and attitudes. The books include both fiction and non-fiction books.
Examples of book titles that appear in the data (these are randomly sampled from all titles):
- ‘Rhymes and Dreams, Legends of Pendle Forest, and other poems’,
- “Précis of Information concerning the Zulu Country, with a map. Prepared in the Intelligence Branch of the Quarter-Master-General’s Department, Horse Guards, War Office, etc”,
- ‘The fan. A poem’,
- ‘Grif; a story of Australian Life’,
- ‘Calypso; a masque: in three acts, etc’,
- ‘Tales Uncle told [With illustrative woodcuts.]’,
- 'Questings',
- 'Home Life on an Ostrich Farm. With ... illustrations’,
- ‘Bulgarya i Bulgarowie’,
- 'Εἰς τα βαθη της Ἀφρικης [In darkest Africa.] ... Μεταφρασις Γεωρ. Σ. Βουτσινα, etc',
- ‘The Corsair, a tale’,
‘Poems ... With notes [With a portrait.]’,
- ‘Report of the Librarian for the year 1898 (1899, 1901, 1909)’,
- “The World of Thought. A novel. By the author of ‘Before I began to speak.’”,
- 'Amleto; tragedia ... recata in versi italiani da M. Leoni, etc']
While using titles alone is insufficient to integrate bias in this collection, it gives some insight into the topics covered by books. Further, the tiles highlight some particular types of bias we might find in the collection. This should in no way be considered an exhaustive list.
#### Colonialism
Even in the above random sample of titles examples of colonial attitudes, we can see examples of titles. We can try and interrogate this further by searching for the name of places that were part of the British Empire when many of these books were published.
Searching for the string `India` in the titles and randomly sampling 10 titles returns:
- “Travels in India in the Seventeenth Century: by Sir Thomas Roe and Dr. John Fryer. Reprinted from the ‘Calcutta Weekly Englishman.’”,
- ‘A Winter in India and Malaysia among the Methodist Missions’,
- “The Tourist’s Guide to all the principal stations on the railways of Northern India [By W. W.] ... Fifth edition”,
- ‘Records of Sport and Military Life in Western India ... With an introduction by ... G. B. Malleson’,
- "Lakhmi, the Rájpút's Bride. A tale of Gujarát in Western India [A poem.]”,
- ‘The West India Commonplace Book: compiled from parliamentary and official documents; shewing the interest of Great Britain in its Sugar Colonies’,
- “From Tonkin to India : by the sources of the Irawadi, January’ 95-January ’96”,
- ‘Case of the Ameers of Sinde : speeches of Mr. John Sullivan, and Captain William Eastwick, at a special court held at the India House, ... 26th January, 1844’,
- ‘The Andaman Islands; their colonisation, etc. A correspondence addressed to the India Office’,
- ‘Ancient India as described by Ptolemy; being a translation of the chapters which describe India and Eastern Asia in the treatise on Geography written by Klaudios Ptolemaios ... with introduction, commentary, map of India according to Ptolemy, and ... index, by J. W. McCrindle’]
Searching form the string `Africa` in the titles and randomly sampling 10 titles returns:
- ['De Benguella ás Terras de Iácca. Descripção de uma viagem na Africa Central e Occidental ... Expedição organisada nos annos de 1877-1880. Edição illustrada',
- ‘To the New Geographical Society of Edinburgh [An address on Africa by H. M. Stanley.]’,
- ‘Diamonds and Gold in South Africa ... With maps, etc’,
- ‘Missionary Travels and Researches in South Africa ... With notes by F. S. Arnot. With map and illustrations. New edition’,
- ‘A Narrative of a Visit to the Mauritius and South Africa ... Illustrated by two maps, sixteen etchings and twenty-eight wood-cuts’,
- ‘Side Lights on South Africa ... With a map, etc’,
- ‘My Second Journey through Equatorial Africa ... in ... 1886 and 1887 ... Translated ... by M. J. A. Bergmann. With a map ... and ... illustrations, etc’,
- ‘Missionary Travels and Researches in South Africa ... With portrait and fullpage illustrations’,
- ‘[African sketches.] Narrative of a residence in South Africa ... A new edition. To which is prefixed a biographical sketch of the author by J. Conder’,
- ‘Lake Ngami; or, Explorations and discoveries during four years wandering in the wilds of South Western Africa ... With a map, and numerous illustrations, etc’]
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
The books are licensed under the [CC Public Domain Mark 1.0](https://creativecommons.org/publicdomain/mark/1.0/) license.
### Citation Information
```bibtext
@misc{bBritishLibraryBooks2021,
author = {British Library Labs},
title = {Digitised Books. c. 1510 - c. 1900. JSONL (OCR derived text + metadata)},
year = {2021},
publisher = {British Library},
howpublished={https://doi.org/10.23636/r7w6-zy15}
```
### Contributions
Thanks to [@davanstrien](https://github.com/davanstrien) for adding this dataset. |
false |
# Dataset Card for "asnq"
## 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/alexa/wqa_tanda#answer-sentence-natural-questions-asnq](https://github.com/alexa/wqa_tanda#answer-sentence-natural-questions-asnq)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection](https://arxiv.org/abs/1911.04118)
- **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:** 3.56 GB
- **Size of the generated dataset:** 3.82 GB
- **Total amount of disk used:** 7.39 GB
### Dataset Summary
ASNQ is a dataset for answer sentence selection derived from
Google's Natural Questions (NQ) dataset (Kwiatkowski et al. 2019).
Each example contains a question, candidate sentence, label indicating whether or not
the sentence answers the question, and two additional features --
sentence_in_long_answer and short_answer_in_sentence indicating whether ot not the
candidate sentence is contained in the long_answer and if the short_answer is in the candidate sentence.
For more details please see
https://arxiv.org/abs/1911.04118
and
https://research.google/pubs/pub47761/
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 3.56 GB
- **Size of the generated dataset:** 3.82 GB
- **Total amount of disk used:** 7.39 GB
An example of 'validation' looks as follows.
```
{
"label": 0,
"question": "when did somewhere over the rainbow come out",
"sentence": "In films and TV shows ( edit ) In the film Third Finger , Left Hand ( 1940 ) with Myrna Loy , Melvyn Douglas , and Raymond Walburn , the tune played throughout the film in short sequences .",
"sentence_in_long_answer": false,
"short_answer_in_sentence": false
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `question`: a `string` feature.
- `sentence`: a `string` feature.
- `label`: a classification label, with possible values including `neg` (0), `pos` (1).
- `sentence_in_long_answer`: a `bool` feature.
- `short_answer_in_sentence`: a `bool` feature.
### Data Splits
| name | train |validation|
|-------|-------:|---------:|
|default|20377568| 930062|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
The data is made available under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License:
https://github.com/alexa/wqa_tanda/blob/master/LICENSE
### Citation Information
```
@article{Garg_2020,
title={TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection},
volume={34},
ISSN={2159-5399},
url={http://dx.doi.org/10.1609/AAAI.V34I05.6282},
DOI={10.1609/aaai.v34i05.6282},
number={05},
journal={Proceedings of the AAAI Conference on Artificial Intelligence},
publisher={Association for the Advancement of Artificial Intelligence (AAAI)},
author={Garg, Siddhant and Vu, Thuy and Moschitti, Alessandro},
year={2020},
month={Apr},
pages={7780–7788}
}
```
### Contributions
Thanks to [@mkserge](https://github.com/mkserge) for adding this dataset. |
false |
# Dataset Card for QED
## 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:** N/A
- **Repository:** [GitHub](https://github.com/google-research-datasets/QED)
- **Paper:** [QED: A Framework and Dataset for Explanations in Question Answering](https://arxiv.org/abs/2009.06354)
- **Leaderboard:** N/A
- **Point of Contact:** -
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset. |
true |
# Dataset Card for BingCoronavirusQuerySet
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** None
- **Repository:** https://github.com/microsoft/BingCoronavirusQuerySet
- **Paper:** Nonewww
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [More Information Needed]
### Dataset Summary
Please note that you can specify the start and end date of the data. You can get start and end dates from here: https://github.com/microsoft/BingCoronavirusQuerySet/tree/master/data/2020
example:
```
load_dataset("bing_coronavirus_query_set", queries_by="state", start_date="2020-09-01", end_date="2020-09-30")
```
You can also load the data by country by using `queries_by="country"`.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false |
# Dataset Card for "squad_it"
## 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/crux82/squad-it](https://github.com/crux82/squad-it)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Size of downloaded dataset files:** 8.78 MB
- **Size of the generated dataset:** 58.79 MB
- **Total amount of disk used:** 67.57 MB
### Dataset Summary
SQuAD-it is derived from the SQuAD dataset and it is obtained through semi-automatic translation of the SQuAD dataset
into Italian. It represents a large-scale dataset for open question answering processes on factoid questions in Italian.
The dataset contains more than 60,000 question/answer pairs derived from the original English dataset. The dataset is
split into training and test sets to support the replicability of the benchmarking of QA systems:
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 8.78 MB
- **Size of the generated dataset:** 58.79 MB
- **Total amount of disk used:** 67.57 MB
An example of 'train' looks as follows.
```
This example was too long and was cropped:
{
"answers": "{\"answer_start\": [243, 243, 243, 243, 243], \"text\": [\"evitare di essere presi di mira dal boicottaggio\", \"evitare di essere pres...",
"context": "\"La crisi ha avuto un forte impatto sulle relazioni internazionali e ha creato una frattura all' interno della NATO. Alcune nazi...",
"id": "5725b5a689a1e219009abd28",
"question": "Perchè le nazioni europee e il Giappone si sono separati dagli Stati Uniti durante la crisi?"
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `id`: a `string` feature.
- `context`: a `string` feature.
- `question`: a `string` feature.
- `answers`: a dictionary feature containing:
- `text`: a `string` feature.
- `answer_start`: a `int32` feature.
### Data Splits
| name | train | test |
| ------- | ----: | ---: |
| default | 54159 | 7609 |
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
```
@InProceedings{10.1007/978-3-030-03840-3_29,
author="Croce, Danilo and Zelenanska, Alexandra and Basili, Roberto",
editor="Ghidini, Chiara and Magnini, Bernardo and Passerini, Andrea and Traverso, Paolo",
title="Neural Learning for Question Answering in Italian",
booktitle="AI*IA 2018 -- Advances in Artificial Intelligence",
year="2018",
publisher="Springer International Publishing",
address="Cham",
pages="389--402",
isbn="978-3-030-03840-3"
}
```
### Contributions
Thanks to [@thomwolf](https://github.com/thomwolf), [@lewtun](https://github.com/lewtun), [@albertvillanova](https://github.com/albertvillanova), [@mariamabarham](https://github.com/mariamabarham), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset. |
false |
# Dataset Card for GEM/BiSECT
## Dataset Description
- **Homepage:** https://github.com/mounicam/BiSECT
- **Repository:** https://github.com/mounicam/BiSECT/tree/main/bisect
- **Paper:** https://aclanthology.org/2021.emnlp-main.500/
- **Leaderboard:** N/A
- **Point of Contact:** Joongwon Kim, Mounica Maddela, Reno Kriz
### Link to Main Data Card
You can find the main data card on the [GEM Website](https://gem-benchmark.com/data_cards/BiSECT).
### Dataset Summary
This dataset is composed of 1 million complex sentences with the task to split and simplify them while retaining the full meaning. Compared to other simplification corpora, BiSECT requires more significant edits. BiSECT offers splits in English, German, French, and Spanish.
You can load the dataset via:
```
import datasets
data = datasets.load_dataset('GEM/BiSECT')
```
The data loader can be found [here](https://huggingface.co/datasets/GEM/BiSECT).
#### website
[Link](https://github.com/mounicam/BiSECT)
#### paper
[Link](https://aclanthology.org/2021.emnlp-main.500/)
## Dataset Overview
### Where to find the Data and its Documentation
#### Webpage
<!-- info: What is the webpage for the dataset (if it exists)? -->
<!-- scope: telescope -->
[Link](https://github.com/mounicam/BiSECT)
#### Download
<!-- info: What is the link to where the original dataset is hosted? -->
<!-- scope: telescope -->
[Link](https://github.com/mounicam/BiSECT/tree/main/bisect)
#### Paper
<!-- info: What is the link to the paper describing the dataset (open access preferred)? -->
<!-- scope: telescope -->
[Link](https://aclanthology.org/2021.emnlp-main.500/)
#### BibTex
<!-- info: Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex. -->
<!-- scope: microscope -->
```
@inproceedings{kim-etal-2021-bisect,
title = "{B}i{SECT}: Learning to Split and Rephrase Sentences with Bitexts",
author = "Kim, Joongwon and
Maddela, Mounica and
Kriz, Reno and
Xu, Wei and
Callison-Burch, Chris",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.500",
pages = "6193--6209"
}
```
#### Contact Name
<!-- quick -->
<!-- info: If known, provide the name of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
Joongwon Kim, Mounica Maddela, Reno Kriz
#### Contact Email
<!-- info: If known, provide the email of at least one person the reader can contact for questions about the dataset. -->
<!-- scope: periscope -->
jkim0118@seas.upenn.edu, mmaddela3@gatech.edu, rkriz1@jh.edu
#### Has a Leaderboard?
<!-- info: Does the dataset have an active leaderboard? -->
<!-- scope: telescope -->
no
### Languages and Intended Use
#### Multilingual?
<!-- quick -->
<!-- info: Is the dataset multilingual? -->
<!-- scope: telescope -->
yes
#### Covered Languages
<!-- quick -->
<!-- info: What languages/dialects are covered in the dataset? -->
<!-- scope: telescope -->
`English`, `German`, `French`, `Spanish, Castilian`
#### License
<!-- quick -->
<!-- info: What is the license of the dataset? -->
<!-- scope: telescope -->
other: Other license
#### Intended Use
<!-- info: What is the intended use of the dataset? -->
<!-- scope: microscope -->
Split and Rephrase.
#### Add. License Info
<!-- info: What is the 'other' license of the dataset? -->
<!-- scope: periscope -->
The dataset is not licensed by itself, and the source OPUS data consists solely of publicly available parallel corpora.
#### Primary Task
<!-- info: What primary task does the dataset support? -->
<!-- scope: telescope -->
Simplification
#### Communicative Goal
<!-- quick -->
<!-- info: Provide a short description of the communicative goal of a model trained for this task on this dataset. -->
<!-- scope: periscope -->
To rewrite a long, complex sentence into shorter, readable, meaning-equivalent sentences.
### Credit
### Dataset Structure
#### Data Fields
<!-- info: List and describe the fields present in the dataset. -->
<!-- scope: telescope -->
- `gem_id` (string): a unique identifier for the instance
- `source_sentence` (string): sentence to be simplified
- `target_sentence` (string)" simplified text that was split and rephrased
#### Example Instance
<!-- info: Provide a JSON formatted example of a typical instance in the dataset. -->
<!-- scope: periscope -->
```
{
"gem_id": "bisect-train-0",
"source_sentence": "The report on the visit to Bhutan states that the small community has made the task of coordination less complex and success is manifested in the synchronized programming cycles which now apply to all but one of the agencies ( the World Health Organization ) .",
"target_sentence": "The report on the visit to Bhutan says that the small community has made the coordination work less complex . Success manifests itself in synchronized programming cycles that now apply to all but one organism ( the World Health Organization ) ."
}
```
#### Data Splits
<!-- info: Describe and name the splits in the dataset if there are more than one. -->
<!-- scope: periscope -->
For the main English BiSECT dataset, the splits are as follows: 1. Train (n=928440) 2. Validation (n=9079) 3. Test (n=583) Additional challenge sets were derived from the data presented in the paper. Please refer to the challenge set sections. The train/validation/test splits for other languages are as follows: German (n=184638/n=864/n=735) Spanish (n=282944/n=3638/n=3081) French (n=491035/n=2400/n=1036)
#### Splitting Criteria
<!-- info: Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here. -->
<!-- scope: microscope -->
While all training data were derived from subsets of the OPUS corpora, different source subsets were used for training v.s., validation and testing. The training set comprised more web crawl data, whereas development and test sets comprised EMEA and EU texts. Details can be found in the BiSECT paper.
## Dataset in GEM
### Rationale for Inclusion in GEM
#### Why is the Dataset in GEM?
<!-- info: What does this dataset contribute toward better generation evaluation and why is it part of GEM? -->
<!-- scope: microscope -->
Understanding long and complex sentences is challenging for both humans and NLP models. The BiSECT dataset helps facilitate more research on Split and Rephrase as a task within itself, as well as how it can benefit downstream NLP applications.
#### Similar Datasets
<!-- info: Do other datasets for the high level task exist? -->
<!-- scope: telescope -->
yes
#### Unique Language Coverage
<!-- info: Does this dataset cover other languages than other datasets for the same task? -->
<!-- scope: periscope -->
yes
#### Difference from other GEM datasets
<!-- info: What else sets this dataset apart from other similar datasets in GEM? -->
<!-- scope: microscope -->
BiSECT is the largest available corpora for the Split and Rephrase task. In addition, it has been shown that BiSECT is of higher quality than previous Split and Rephrase corpora and contains a wider variety of splitting operations.
Most previous Split and Rephrase corpora (HSplit-Wiki, Cont-Benchmark, and Wiki-Benchmark) were manually written at a small scale and focused on evaluation, while the one corpus of comparable size, WikiSplit, contains around 25% of pairs contain significant errors. This is because Wikipedia editors are not only trying to split a sentence, but also often simultaneously modifying the sentence for other purposes, which results in changes of the initial meaning.
### GEM-Specific Curation
#### Modificatied for GEM?
<!-- info: Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data? -->
<!-- scope: telescope -->
yes
#### GEM Modifications
<!-- info: What changes have been made to he original dataset? -->
<!-- scope: periscope -->
`data points added`
#### Modification Details
<!-- info: For each of these changes, described them in more details and provided the intended purpose of the modification -->
<!-- scope: microscope -->
The original BiSECT training, validation, and test splits are maintained to ensure a fair comparison. Note that the original BiSECT test set was created by manually selecting 583 high-quality Split and Rephrase instances from 1000 random source-target pairs sampled from the EMEA and JRC-Acquis corpora from OPUS.
As the first challenge set, we include the HSPLIT-Wiki test set, containing 359 pairs. For each complex sentence, there are four reference splits; To ensure replicability, as reference splits, we again follow the BiSECT paper and present only the references from HSplit2-full.
In addition to the two evaluation sets used in the original BiSECT paper, we also introduce a second challenge set. For this, we initially consider all 7,293 pairs from the EMEA and JRC-Acquis corpora. From there, we classify each pair using the classification algorithm from Section 4.2 of the original BiSECT paper. The three classes are as follows:
1. Direct Insertion: when a long sentence l contains two independent clauses and requires only minor changes in order to make a fluent and meaning-preserving split s.
2. Changes near Split, when l contains one independent and one dependent clause, but modifications are restricted to the region where l is split.
3. Changes across Sentences, where major changes are required throughout l in order to create a fluent split s.
We keep only pairs labeled as Type 3, and after filtering out pairs with significant length differences (signaling potential content addition/deletion), we present a second challenge set of 1,798 pairs.
#### Additional Splits?
<!-- info: Does GEM provide additional splits to the dataset? -->
<!-- scope: telescope -->
no
### Getting Started with the Task
#### Pointers to Resources
<!-- info: Getting started with in-depth research on the task. Add relevant pointers to resources that researchers can consult when they want to get started digging deeper into the task. -->
<!-- scope: microscope -->
The dataset can be downloaded from the original repository by the authors.
The original BiSECT paper proposes several transformer-based models that can be used as baselines, which also compares against Copy512, an LSTM-based model and the previous state-of-the-art.
The common metric used for automatic evaluation of Split and Rephrase, and sentence simplification more generally is SARI. The BiSECT paper also evaluates using BERTScore. Note that automatic evaluations tend to not correlate well with human judgments, so a human evaluation for quality is generally expected for publication. The original BiSECT paper provides templates for collecting quality annotations from Amazon Mechanical Turk.
## Previous Results
### Previous Results
#### Measured Model Abilities
<!-- info: What aspect of model ability can be measured with this dataset? -->
<!-- scope: telescope -->
Text comprehension (needed to generate meaning-equivalent output) and notions of complexity (what is more 'readable' in terms of syntactic structure, lexical choice, punctuation).
#### Metrics
<!-- info: What metrics are typically used for this task? -->
<!-- scope: periscope -->
`Other: Other Metrics`, `BERT-Score`
#### Other Metrics
<!-- info: Definitions of other metrics -->
<!-- scope: periscope -->
SARI is a metric used for evaluating automatic text simplification systems. The metric compares the predicted simplified sentences against the reference and the source sentences. It explicitly measures the goodness of words that are added, deleted and kept by the system.
#### Proposed Evaluation
<!-- info: List and describe the purpose of the metrics and evaluation methodology (including human evaluation) that the dataset creators used when introducing this task. -->
<!-- scope: microscope -->
Existing automatic metrics, such as BLEU (Papineni et al., 2002) and SAMSA (Sulem et al., 2018),
are not optimal for the Split and Rephrase task as
they rely on lexical overlap between the output and
the target (or source) and underestimate the splitting capability of the models that rephrase often.
As such, the dataset creators focused on BERTScore (Zhang et al., 2020) and SARI (Xu et al., 2016). BERTScore captures meaning preservation and fluency
well (Scialom et al., 2021). SARI can provide three
separate F1/precision scores that explicitly measure the correctness of inserted, kept and deleted
n-grams when compared to both the source and
the target. The authors used an extended version of SARI
that considers lexical paraphrases of the reference.
#### Previous results available?
<!-- info: Are previous results available? -->
<!-- scope: telescope -->
yes
## Dataset Curation
### Original Curation
#### Original Curation Rationale
<!-- info: Original curation rationale -->
<!-- scope: telescope -->
BiSECT was constructed to satisfy the need of a Split and Rephrase corpus that is both large-scale and high-quality. Most previous Split and Rephrase corpora (HSplit-Wiki, Cont-Benchmark, and Wiki-Benchmark) were manually written at a small scale and focused on evaluation, while the one corpus of comparable size, WikiSplit, contains around 25% of pairs contain significant errors. This is because Wikipedia editors are not only trying to split a sentence, but also often simultaneously modifying the sentence for other purposes, which results in changes of the initial meaning.
#### Communicative Goal
<!-- info: What was the communicative goal? -->
<!-- scope: periscope -->
The goal of Split and Rephrase is to break down longer sentences into multiple shorter sentences, which has downstream applications for many NLP tasks, including machine translation and dependency parsing.
#### Sourced from Different Sources
<!-- info: Is the dataset aggregated from different data sources? -->
<!-- scope: telescope -->
no
### Language Data
#### How was Language Data Obtained?
<!-- info: How was the language data obtained? -->
<!-- scope: telescope -->
`Found`
#### Where was it found?
<!-- info: If found, where from? -->
<!-- scope: telescope -->
`Other`
#### Language Producers
<!-- info: What further information do we have on the language producers? -->
<!-- scope: microscope -->
N/A.
#### Topics Covered
<!-- info: Does the language in the dataset focus on specific topics? How would you describe them? -->
<!-- scope: periscope -->
There is a range of topics spanning domains such as web crawl and government documents (European Parliament, United Nations, EMEA).
#### Data Validation
<!-- info: Was the text validated by a different worker or a data curator? -->
<!-- scope: telescope -->
validated by data curator
#### Data Preprocessing
<!-- info: How was the text data pre-processed? (Enter N/A if the text was not pre-processed) -->
<!-- scope: microscope -->
The construction of the BiSECT corpus relies on leveraging the sentence-level alignments from OPUS), a collection of bilingual parallel corpora over many language pairs. Given a target language A, this work extracts all 1-2 and 2-1 sentence alignments from parallel corpora between A and a set of foreign languages B.
Next, the foreign sentences are translated into English using Google Translate’s Web API service to obtain sentence alignments between a single long sentence and two corresponding split sentences, both in the desired language.
The authors further filtered the data in a hybrid fashion.
#### Was Data Filtered?
<!-- info: Were text instances selected or filtered? -->
<!-- scope: telescope -->
hybrid
#### Filter Criteria
<!-- info: What were the selection criteria? -->
<!-- scope: microscope -->
To remove noise, the authors remove pairs where the single long sentence (l) contains a token with a punctuation after the first two and before the last two alphabetic characters. The authors also removed instances where l contains more than one unconnected component in its dependency tree, generated via SpaCy.
### Structured Annotations
#### Additional Annotations?
<!-- quick -->
<!-- info: Does the dataset have additional annotations for each instance? -->
<!-- scope: telescope -->
none
#### Annotation Service?
<!-- info: Was an annotation service used? -->
<!-- scope: telescope -->
no
### Consent
#### Any Consent Policy?
<!-- info: Was there a consent policy involved when gathering the data? -->
<!-- scope: telescope -->
no
#### Justification for Using the Data
<!-- info: If not, what is the justification for reusing the data? -->
<!-- scope: microscope -->
Since this data is collected from OPUS, all instances are already in the public domain.
### Private Identifying Information (PII)
#### Contains PII?
<!-- quick -->
<!-- info: Does the source language data likely contain Personal Identifying Information about the data creators or subjects? -->
<!-- scope: telescope -->
unlikely
#### Categories of PII
<!-- info: What categories of PII are present or suspected in the data? -->
<!-- scope: periscope -->
`generic PII`
#### Any PII Identification?
<!-- info: Did the curators use any automatic/manual method to identify PII in the dataset? -->
<!-- scope: periscope -->
no identification
### Maintenance
#### Any Maintenance Plan?
<!-- info: Does the original dataset have a maintenance plan? -->
<!-- scope: telescope -->
no
## Broader Social Context
### Previous Work on the Social Impact of the Dataset
#### Usage of Models based on the Data
<!-- info: Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems? -->
<!-- scope: telescope -->
no
### Impact on Under-Served Communities
#### Addresses needs of underserved Communities?
<!-- info: Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models). -->
<!-- scope: telescope -->
yes
#### Details on how Dataset Addresses the Needs
<!-- info: Describe how this dataset addresses the needs of underserved communities. -->
<!-- scope: microscope -->
The data as provided in GEMv2 is in English, which is a language with abundant existing resources. However, the original paper also provides Split and Rephrase pairs for French, Spanish, and German, while providing a framework for leveraging bilingual corpora from any language pair found within OPUS.
### Discussion of Biases
#### Any Documented Social Biases?
<!-- info: Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group. -->
<!-- scope: telescope -->
no
#### Are the Language Producers Representative of the Language?
<!-- info: Does the distribution of language producers in the dataset accurately represent the full distribution of speakers of the language world-wide? If not, how does it differ? -->
<!-- scope: periscope -->
The language produced in the dataset is limited to what is captured in the used subset of the OPUS corpora, which might not represent the full distribution of speakers from all locations. For example, the corpora used are from a limited set of relatively formal domains, so it is possible that high performance on the BiSECT test set may not transfer to more informal text.
## Considerations for Using the Data
### PII Risks and Liability
#### Potential PII Risk
<!-- info: Considering your answers to the PII part of the Data Curation Section, describe any potential privacy to the data subjects and creators risks when using the dataset. -->
<!-- scope: microscope -->
Since this data is collected from OPUS, all pairs are already in the public domain.
### Licenses
#### Copyright Restrictions on the Dataset
<!-- info: Based on your answers in the Intended Use part of the Data Overview Section, which of the following best describe the copyright and licensing status of the dataset? -->
<!-- scope: periscope -->
`public domain`
#### Copyright Restrictions on the Language Data
<!-- info: Based on your answers in the Language part of the Data Curation Section, which of the following best describe the copyright and licensing status of the underlying language data? -->
<!-- scope: periscope -->
`public domain`
### Known Technical Limitations
#### Technical Limitations
<!-- info: Describe any known technical limitations, such as spurrious correlations, train/test overlap, annotation biases, or mis-annotations, and cite the works that first identified these limitations when possible. -->
<!-- scope: microscope -->
The creation of English BiSECT relies on translating non-English text back to English. While machine translation systems tend to perform well on high-resource languages, there is still a non-negligible chance that there these systems make errors; through a manual evaluation of a subset of BiSECT, it was found that 15% of pairs contained significant errors, while an additional 22% contained minor adequacy/fluency errors. This problem is exacerbated slightly when creating German BiSECT (22% significant errors, 24% minor errors), and these numbers would likely get larger if lower-resource languages were used.
|
true |
# Dataset Card for News Popularity in Multiple Social Media Platforms
## 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:** [UCI](https://archive.ics.uci.edu/ml/datasets/News+Popularity+in+Multiple+Social+Media+Platforms)
- **Repository:**
- **Paper:** [Arxiv](https://arxiv.org/abs/1801.07055)
- **Leaderboard:** [Kaggle](https://www.kaggle.com/nikhiljohnk/news-popularity-in-multiple-social-media-platforms/code)
- **Point of Contact:**
### Dataset Summary
Social sharing data across Facebook, Google+ and LinkedIn for 100k news items on the topics of: economy, microsoft, obama and palestine.
### Supported Tasks and Leaderboards
Popularity prediction/shares prediction
### Languages
English
## Dataset Structure
### Data Instances
```
{ "id": 35873,
"title": "Microsoft's 'teen girl' AI turns into a Hitler-loving sex robot within 24 ...",
"headline": "Developers at Microsoft created 'Tay', an AI modelled to speak 'like a teen girl', in order to improve the customer service on their voice",
"source": "Telegraph.co.uk",
"topic": "microsoft",
"publish_date": "2016-03-24 09:53:54",
"facebook": 22346,
"google_plus": 973,
"linked_in": 1009
}
```
### Data Fields
- id: the sentence id in the source dataset
- title: the title of the link as shared on social media
- headline: the headline, or sometimes the lede of the story
- source: the source news site
- topic: the topic: one of "economy", "microsoft", "obama" and "palestine"
- publish_date: the date the original article was published
- facebook: the number of Facebook shares, or -1 if this data wasn't collected
- google_plus: the number of Google+ likes, or -1 if this data wasn't collected
- linked_in: the number of LinkedIn shares, or -1 if if this data wasn't collected
### Data Splits
None
## Dataset Creation
### Curation Rationale
### Source Data
#### Initial Data Collection and Normalization
#### Who are the source language producers?
The source headlines were by journalists, while the titles were written by the
people sharing it on social media.
### Annotations
#### Annotation process
The 'annotations' are simply the number of shares, or likes in the case of
Google+ as collected from various API endpoints.
#### Who are the annotators?
Social media users.
### 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
License: Creative Commons Attribution 4.0 International License (CC-BY)
### Citation Information
```
@article{Moniz2018MultiSourceSF,
title={Multi-Source Social Feedback of Online News Feeds},
author={N. Moniz and L. Torgo},
journal={ArXiv},
year={2018},
volume={abs/1801.07055}
}
```
### Contributions
Thanks to [@frankier](https://github.com/frankier) for adding this dataset. |
false |
# Dataset Card for NewsQA
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://www.microsoft.com/en-us/research/project/newsqa-dataset/
- **Repository:** https://github.com/Maluuba/newsqa
- **Paper:** https://www.aclweb.org/anthology/W17-2623/
- **Leaderboard:** [Needs More Information]
- **Point of Contact:** [Needs More Information]
### Dataset Summary
NewsQA is a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs.
Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text from the corresponding articles.
### Supported Tasks and Leaderboards
[Needs More Information]
### Languages
English
## Dataset Structure
### Data Instances
```
{'storyId': './cnn/stories/42d01e187213e86f5fe617fe32e716ff7fa3afc4.story',
'text': 'NEW DELHI, India (CNN) -- A high court in northern India on Friday acquitted a wealthy businessman facing the death sentence for the killing of a teen in a case dubbed "the house of horrors."\n\n\n\nMoninder Singh Pandher was sentenced to death by a lower court in February.\n\n\n\nThe teen was one of 19 victims -- children and young women -- in one of the most gruesome serial killings in India in recent years.\n\n\n\nThe Allahabad high court has acquitted Moninder Singh Pandher, his lawyer Sikandar B. Kochar told CNN.\n\n\n\nPandher and his domestic employee Surinder Koli were sentenced to death in February by a lower court for the rape and murder of the 14-year-old.\n\n\n\nThe high court upheld Koli\'s death sentence, Kochar said.\n\n\n\nThe two were arrested two years ago after body parts packed in plastic bags were found near their home in Noida, a New Delhi suburb. Their home was later dubbed a "house of horrors" by the Indian media.\n\n\n\nPandher was not named a main suspect by investigators initially, but was summoned as co-accused during the trial, Kochar said.\n\n\n\nKochar said his client was in Australia when the teen was raped and killed.\n\n\n\nPandher faces trial in the remaining 18 killings and could remain in custody, the attorney said.',
'type': 'train',
'questions': {'q': ['What was the amount of children murdered?',
'When was Pandher sentenced to death?',
'The court aquitted Moninder Singh Pandher of what crime?',
'who was acquitted',
'who was sentenced',
'What was Moninder Singh Pandher acquitted for?',
'Who was sentenced to death in February?',
'how many people died',
'How many children and young women were murdered?'],
'isAnswerAbsent': [0, 0, 0, 0, 0, 0, 0, 0, 0],
'isQuestionBad': [0, 0, 0, 0, 0, 0, 0, 0, 0],
'consensus': [{'s': 294, 'e': 297, 'badQuestion': False, 'noAnswer': False},
{'s': 261, 'e': 271, 'badQuestion': False, 'noAnswer': False},
{'s': 624, 'e': 640, 'badQuestion': False, 'noAnswer': False},
{'s': 195, 'e': 218, 'badQuestion': False, 'noAnswer': False},
{'s': 195, 'e': 218, 'badQuestion': False, 'noAnswer': False},
{'s': 129, 'e': 151, 'badQuestion': False, 'noAnswer': False},
{'s': 195, 'e': 218, 'badQuestion': False, 'noAnswer': False},
{'s': 294, 'e': 297, 'badQuestion': False, 'noAnswer': False},
{'s': 294, 'e': 297, 'badQuestion': False, 'noAnswer': False}],
'answers': [{'sourcerAnswers': [{'s': [294],
'e': [297],
'badQuestion': [False],
'noAnswer': [False]},
{'s': [0], 'e': [0], 'badQuestion': [False], 'noAnswer': [True]},
{'s': [0], 'e': [0], 'badQuestion': [False], 'noAnswer': [True]}]},
{'sourcerAnswers': [{'s': [261],
'e': [271],
'badQuestion': [False],
'noAnswer': [False]},
{'s': [258], 'e': [271], 'badQuestion': [False], 'noAnswer': [False]},
{'s': [261], 'e': [271], 'badQuestion': [False], 'noAnswer': [False]}]},
{'sourcerAnswers': [{'s': [26],
'e': [33],
'badQuestion': [False],
'noAnswer': [False]},
{'s': [0], 'e': [0], 'badQuestion': [False], 'noAnswer': [True]},
{'s': [624], 'e': [640], 'badQuestion': [False], 'noAnswer': [False]}]},
{'sourcerAnswers': [{'s': [195],
'e': [218],
'badQuestion': [False],
'noAnswer': [False]},
{'s': [195], 'e': [218], 'badQuestion': [False], 'noAnswer': [False]}]},
{'sourcerAnswers': [{'s': [0],
'e': [0],
'badQuestion': [False],
'noAnswer': [True]},
{'s': [195, 232],
'e': [218, 271],
'badQuestion': [False, False],
'noAnswer': [False, False]},
{'s': [0], 'e': [0], 'badQuestion': [False], 'noAnswer': [True]}]},
{'sourcerAnswers': [{'s': [129],
'e': [192],
'badQuestion': [False],
'noAnswer': [False]},
{'s': [129], 'e': [151], 'badQuestion': [False], 'noAnswer': [False]},
{'s': [133], 'e': [151], 'badQuestion': [False], 'noAnswer': [False]}]},
{'sourcerAnswers': [{'s': [195],
'e': [218],
'badQuestion': [False],
'noAnswer': [False]},
{'s': [195], 'e': [218], 'badQuestion': [False], 'noAnswer': [False]}]},
{'sourcerAnswers': [{'s': [294],
'e': [297],
'badQuestion': [False],
'noAnswer': [False]},
{'s': [294], 'e': [297], 'badQuestion': [False], 'noAnswer': [False]}]},
{'sourcerAnswers': [{'s': [294],
'e': [297],
'badQuestion': [False],
'noAnswer': [False]},
{'s': [294], 'e': [297], 'badQuestion': [False], 'noAnswer': [False]}]}],
'validated_answers': [{'s': [0, 294],
'e': [0, 297],
'badQuestion': [False, False],
'noAnswer': [True, False],
'count': [1, 2]},
{'s': [], 'e': [], 'badQuestion': [], 'noAnswer': [], 'count': []},
{'s': [624],
'e': [640],
'badQuestion': [False],
'noAnswer': [False],
'count': [2]},
{'s': [], 'e': [], 'badQuestion': [], 'noAnswer': [], 'count': []},
{'s': [195],
'e': [218],
'badQuestion': [False],
'noAnswer': [False],
'count': [2]},
{'s': [129],
'e': [151],
'badQuestion': [False],
'noAnswer': [False],
'count': [2]},
{'s': [], 'e': [], 'badQuestion': [], 'noAnswer': [], 'count': []},
{'s': [], 'e': [], 'badQuestion': [], 'noAnswer': [], 'count': []},
{'s': [], 'e': [], 'badQuestion': [], 'noAnswer': [], 'count': []}]}}
```
### Data Fields
Configuration: combined-csv
- 'story_id': An identifier of the story.
- 'story_text': Text of the story.
- 'question': A question about the story.
- 'answer_char_ranges': The raw data collected for character based indices to answers in story_text. E.g. 196:228|196:202,217:228|None. Answers from different crowdsourcers are separated by `|`; within those, multiple selections from the same crowdsourcer are separated by `,`. `None` means the crowdsourcer thought there was no answer to the question in the story. The start is inclusive and the end is exclusive. The end may point to whitespace after a token.
Configuration: combined-json
- 'storyId': An identifier of the story.
- 'text': Text of the story.
- 'type': Split type. Will be "train", "validation" or "test".
- 'questions': A list containing the following:
- 'q': A question about the story.
- 'isAnswerAbsent': Proportion of crowdsourcers that said there was no answer to the question in the story.
- 'isQuestionBad': Proportion of crowdsourcers that said the question does not make sense.
- 'consensus': The consensus answer. Use this field to pick the best continuous answer span from the text. If you want to know about a question having multiple answers in the text then you can use the more detailed "answers" and "validated_answers". The object can have start and end positions like in the example above or can be {"badQuestion": true} or {"noAnswer": true}. Note that there is only one consensus answer since it's based on the majority agreement of the crowdsourcers.
- 's': Start of the answer. The first character of the answer in "text" (inclusive).
- 'e': End of the answer. The last character of the answer in "text" (exclusive).
- 'badQuestion': The validator said that the question did not make sense.
- 'noAnswer': The crowdsourcer said that there was no answer to the question in the text.
- 'answers': The answers from various crowdsourcers.
- 'sourcerAnswers': The answer provided from one crowdsourcer.
- 's': Start of the answer. The first character of the answer in "text" (inclusive).
- 'e': End of the answer. The last character of the answer in "text" (exclusive).
- 'badQuestion': The crowdsourcer said that the question did not make sense.
- 'noAnswer': The crowdsourcer said that there was no answer to the question in the text.
- 'validated_answers': The answers from the validators.
- 's': Start of the answer. The first character of the answer in "text" (inclusive).
- 'e': End of the answer. The last character of the answer in "text" (exclusive).
- 'badQuestion': The validator said that the question did not make sense.
- 'noAnswer': The validator said that there was no answer to the question in the text.
- 'count': The number of validators that agreed with this answer.
Configuration: split
- 'story_id': An identifier of the story
- 'story_text': text of the story
- 'question': A question about the story.
- 'answer_token_ranges': Word based indices to answers in story_text. E.g. 196:202,217:228. Multiple selections from the same answer are separated by `,`. The start is inclusive and the end is exclusive. The end may point to whitespace after a token.
### Data Splits
| name | train | validation | test |
|---------------|-----------:|-----------:|--------:|
| combined-csv | 119633 | | |
| combined-json | 12744 | | |
| split | 92549 | 5166 | 5126 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### 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
NewsQA Code
Copyright (c) Microsoft Corporation
All rights reserved.
MIT License
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED *AS IS*, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
© 2020 GitHub, Inc.
### Citation Information
@inproceedings{trischler2017newsqa,
title={NewsQA: A Machine Comprehension Dataset},
author={Trischler, Adam and Wang, Tong and Yuan, Xingdi and Harris, Justin and Sordoni, Alessandro and Bachman, Philip and Suleman, Kaheer},
booktitle={Proceedings of the 2nd Workshop on Representation Learning for NLP},
pages={191--200},
year={2017}
### Contributions
Thanks to [@rsanjaykamath](https://github.com/rsanjaykamath) for adding this dataset. |
false |
# Dataset Card for Google Sentence Compression
## 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/google-research-datasets/sentence-compression](https://github.com/google-research-datasets/sentence-compression)
- **Repository:** [https://github.com/google-research-datasets/sentence-compression](https://github.com/google-research-datasets/sentence-compression)
- **Paper:** [https://www.aclweb.org/anthology/D13-1155/](https://www.aclweb.org/anthology/D13-1155/)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
A major challenge in supervised sentence compression is making use of rich feature representations because of very scarce parallel data. We address this problem and present a method to automatically build a compression corpus with hundreds of thousands of instances on which deletion-based algorithms can be trained. In our corpus, the syntactic trees of the compressions are subtrees of their uncompressed counterparts, and hence supervised systems which require a structural alignment between the input and output can be successfully trained. We also extend an existing unsupervised compression method with a learning module. The new system uses structured prediction to learn from lexical, syntactic and other features. An evaluation with human raters shows that the presented data harvesting method indeed produces a parallel corpus of high quality. Also, the supervised system trained on this corpus gets high scores both from human raters and in an automatic evaluation setting, significantly outperforming a strong baseline.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
English
## Dataset Structure
### Data Instances
Each data instance should contains the information about the original sentence in `instance["graph"]["sentence"]` as well as the compressed sentence in `instance["compression"]["text"]`. As this dataset was created by pruning dependency connections, the author also includes the dependency tree and transformed graph of the original sentence and compressed sentence.
### Data Fields
Each instance should contains these information:
- `graph` (`Dict`): the transformation graph/tree for extracting compression (a modified version of a dependency tree).
- This will have features similar to a dependency tree (listed bellow)
- `compression` (`Dict`)
- `text` (`str`)
- `edge` (`List`)
- `headline` (`str`): the headline of the original news page.
- `compression_ratio` (`float`): the ratio between compressed sentence vs original sentence.
- `doc_id` (`str`): url of the original news page.
- `source_tree` (`Dict`): the original dependency tree (features listed bellow).
- `compression_untransformed` (`Dict`)
- `text` (`str`)
- `edge` (`List`)
Dependency tree features:
- `id` (`str`)
- `sentence` (`str`)
- `node` (`List`): list of nodes, each node represent a word/word phrase in the tree.
- `form` (`string`)
- `type` (`string`): the enity type of a node. Defaults to `""` if it's not an entity.
- `mid` (`string`)
- `word` (`List`): list of words the node contains.
- `id` (`int`)
- `form` (`str`): the word from the sentence.
- `stem` (`str`): the stemmed/lemmatized version of the word.
- `tag` (`str`): dependency tag of the word.
- `gender` (`int`)
- `head_word_index` (`int`)
- `edge`: list of the dependency connections between words.
- `parent_id` (`int`)
- `child_id` (`int`)
- `label` (`str`)
- `entity_mention` list of the entities in the sentence.
- `start` (`int`)
- `end` (`int`)
- `head` (`str`)
- `name` (`str`)
- `type` (`str`)
- `mid` (`str`)
- `is_proper_name_entity` (`bool`)
- `gender` (`int`)
### 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 [@mattbui](https://github.com/mattbui) for adding this dataset. |
false |
# Dataset Card for CraigslistBargains
## 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:** [Decoupling Strategy and Generation in Negotiation Dialogues](https://worksheets.codalab.org/worksheets/0x453913e76b65495d8b9730d41c7e0a0c/)
- **Repository:** [Github: Stanford NLP Cocoa](https://github.com/stanfordnlp/cocoa/tree/master)
- **Paper:** [Decoupling Strategy and Generation in Negotiation Dialogues](https://arxiv.org/abs/1808.09637)
- **Leaderboard:** []()
- **Point of Contact:** [He He](hehe@cs.nyu.edu)
### Dataset Summary
We study negotiation dialogues where two agents, a buyer and a seller, negotiate over the price of an time for sale. We collected a dataset of more than 6K negotiation dialogues over multiple categories of products scraped from Craigslist. Our goal is to develop an agent that negotiates with humans through such conversations. The challenge is to handle both the negotiation strategy and the rich language for bargaining. To this end, we develop a modular framework which separates strategy learning from language generation. Specifically, we learn strategies in a coarse dialogue act space and instantiate that into utterances conditioned on dialogue history.
### Supported Tasks and Leaderboards
### Languages
This dataset is English
## Dataset Structure
### Data Instances
```
{
'agent_info': {
'Bottomline':
[
'None',
'None'
],
'Role':
[
'buyer',
'seller'
],
'Target':
[
7.0,
10.0
]
},
'agent_turn':
[
0,
1,
...
],
'dialogue_acts': {
'intent':
[
'init-price',
'unknown',
...
],
'price':
[
5.0,
-1.0,
...
]
},
'items': {
'Category':
[
'phone',
'phone'
],
'Description':
[
'Charge two devices simultaneously on the go...,
...
],
'Images':
[
'phone/6149527852_0.jpg',
'phone/6149527852_0.jpg'
],
'Price':
[
10.0,
10.0
],
'Title':
[
'Verizon Car Charger with Dual Output Micro USB and ...',
...
]
},
'utterance':
[
'Hi, not sure if the charger would work for my car...'
'It will work...',
...
]
}
```
### Data Fields
- `agent_info`: Information about each of the agents taking part in the dialogue
- `Bottomline`: TBD
- `Role`: Whether the agent is buyer or seller
- `Target`: Target price that the buyer/seller wants to hit in the negotiation
- `agent_turn`: Agent taking the current turn in the dialogue (`int` index corresponding to `Role` above)
- `dialogue_acts`: Rules-based information about the strategy of each agent for each turn
- `intent`: The intent of the agent at the particular turn (offer, accept, etc.)
- `price`: The current item price associated with the intent and turn in the bargaining process. Default value for missing: (`-1`)
- `items`: Information about the item the agents are bargaining for. **Note that there is an elembet for each of the fields below for each agent**
- `Category`: Category of the item
- `Description`: Description(s) of the item
- `Images`: (comma delimited) strings of image names of the item
- `Price`: Price(s) of the item. Default value for missing: (`-1`)
- `Title`: Title(s) of the item
- `utterance`: Utterance for each turn in the dialogue, corresponding to the agent in `agent_turns`. The utterance may be an empty string (`''`) for some turns if multiple dialogue acts take place after an utterance (e.g. there are often multiple dialogue acts associated with the closing of the bargaining process after all utterances have completed to describe the conclusion of the bargaining).
### Data Splits
This dataset contains three splits, `train`, `validation` and `test`. Note that `test` is not provided with `dialogue_acts` information as described above. To ensure schema consistency across dataset splits, the `dialogue_acts` field in the `test` split is populated with the default values: `{"price": -1.0, "intent": ""}`
The counts of examples in each split are as follows:
| | Train | Valid | Test |
| Input Examples | 5247 | 597 | 838 |
| Average Dialogue Length | 9.14 | 9.17 | 9.24 |
Note that
## Dataset Creation
From the [source paper](https://arxiv.org/pdf/1808.09637.pdf) for this dataset:
> To generate the negotiation scenarios, we
> scraped postings on sfbay.craigslist.org
> from the 6 most popular categories (housing, furniture, cars, bikes, phones, and electronics). Each
> posting produces three scenarios with the buyer’s
> target prices at 0.5x, 0.7x and 0.9x of the listing
> price. Statistics of the scenarios are shown in Table 2.
> We collected 6682 human-human dialogues on
> AMT using the interface shown in Appendix A
> Figure 2. The dataset statistics in Table 3 show
> that CRAIGSLISTBARGAIN has longer dialogues
> and more diverse utterances compared to prior
> datasets. Furthermore, workers were encouraged
> to embellish the item and negotiate side offers
> such as free delivery or pick-up. This highly relatable scenario leads to richer dialogues such as
> the one shown in Table 1. We also observed various persuasion techniques listed in Table 4 such as
> embellishment,
### Curation Rationale
See **Dataset Creation**
### Source Data
See **Dataset Creation**
#### Initial Data Collection and Normalization
See **Dataset Creation**
#### Who are the source language producers?
See **Dataset Creation**
### Annotations
If the dataset contains annotations which are not part of the initial data collection, describe them in the following paragraphs.
#### Annotation process
Annotations for the `dialogue_acts` in `train` and `test` were generated via a rules-based system which can be found in [this script](https://github.com/stanfordnlp/cocoa/blob/master/craigslistbargain/parse_dialogue.py)
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
[More Information Needed]
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
[More Information Needed]
### Dataset Curators
He He and Derek Chen and Anusha Balakrishnan and Percy Liang
Computer Science Department, Stanford University
`{hehe,derekchen14,anusha,pliang}@cs.stanford.edu`
The work through which this data was produced was supported by
DARPA Communicating with Computers (CwC)
program under ARO prime contract no. W911NF15-1-0462
### Licensing Information
[More Information Needed]
### Citation Information
```
@misc{he2018decoupling,
title={Decoupling Strategy and Generation in Negotiation Dialogues},
author={He He and Derek Chen and Anusha Balakrishnan and Percy Liang},
year={2018},
eprint={1808.09637},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@ZacharySBrown](https://github.com/ZacharySBrown) for adding this dataset. |
true |
# Dataset Card for "cardiffnlp/tweet_topic_multi"
## Dataset Description
- **Paper:** [https://arxiv.org/abs/2209.09824](https://arxiv.org/abs/2209.09824)
- **Dataset:** Tweet Topic Dataset
- **Domain:** Twitter
- **Number of Class:** 19
### Dataset Summary
This is the official repository of TweetTopic (["Twitter Topic Classification
, COLING main conference 2022"](https://arxiv.org/abs/2209.09824)), a topic classification dataset on Twitter with 19 labels.
Each instance of TweetTopic comes with a timestamp which distributes from September 2019 to August 2021.
See [cardiffnlp/tweet_topic_single](https://huggingface.co/datasets/cardiffnlp/tweet_topic_single) for single label version of TweetTopic.
The tweet collection used in TweetTopic is same as what used in [TweetNER7](https://huggingface.co/datasets/tner/tweetner7).
The dataset is integrated in [TweetNLP](https://tweetnlp.org/) too.
### Preprocessing
We pre-process tweets before the annotation to normalize some artifacts, converting URLs into a special token `{{URL}}` and non-verified usernames into `{{USERNAME}}`.
For verified usernames, we replace its display name (or account name) with symbols `{@}`.
For example, a tweet
```
Get the all-analog Classic Vinyl Edition
of "Takin' Off" Album from @herbiehancock
via @bluenoterecords link below:
http://bluenote.lnk.to/AlbumOfTheWeek
```
is transformed into the following text.
```
Get the all-analog Classic Vinyl Edition
of "Takin' Off" Album from {@herbiehancock@}
via {@bluenoterecords@} link below: {{URL}}
```
A simple function to format tweet follows below.
```python
import re
from urlextract import URLExtract
extractor = URLExtract()
def format_tweet(tweet):
# mask web urls
urls = extractor.find_urls(tweet)
for url in urls:
tweet = tweet.replace(url, "{{URL}}")
# format twitter account
tweet = re.sub(r"\b(\s*)(@[\S]+)\b", r'\1{\2@}', tweet)
return tweet
target = """Get the all-analog Classic Vinyl Edition of "Takin' Off" Album from @herbiehancock via @bluenoterecords link below: http://bluenote.lnk.to/AlbumOfTheWeek"""
target_format = format_tweet(target)
print(target_format)
'Get the all-analog Classic Vinyl Edition of "Takin\' Off" Album from {@herbiehancock@} via {@bluenoterecords@} link below: {{URL}}'
```
### Data Splits
| split | number of texts | description |
|:------------------------|-----:|------:|
| test_2020 | 573 | test dataset from September 2019 to August 2020 |
| test_2021 | 1679 | test dataset from September 2020 to August 2021 |
| train_2020 | 4585 | training dataset from September 2019 to August 2020 |
| train_2021 | 1505 | training dataset from September 2020 to August 2021 |
| train_all | 6090 | combined training dataset of `train_2020` and `train_2021` |
| validation_2020 | 573 | validation dataset from September 2019 to August 2020 |
| validation_2021 | 188 | validation dataset from September 2020 to August 2021 |
| train_random | 4564 | randomly sampled training dataset with the same size as `train_2020` from `train_all` |
| validation_random | 573 | randomly sampled training dataset with the same size as `validation_2020` from `validation_all` |
| test_coling2022_random | 5536 | random split used in the COLING 2022 paper |
| train_coling2022_random | 5731 | random split used in the COLING 2022 paper |
| test_coling2022 | 5536 | temporal split used in the COLING 2022 paper |
| train_coling2022 | 5731 | temporal split used in the COLING 2022 paper |
For the temporal-shift setting, model should be trained on `train_2020` with `validation_2020` and evaluate on `test_2021`.
In general, model would be trained on `train_all`, the most representative training set with `validation_2021` and evaluate on `test_2021`.
**IMPORTANT NOTE:** To get a result that is comparable with the results of the COLING 2022 Tweet Topic paper, please use `train_coling2022` and `test_coling2022` for temporal-shift, and `train_coling2022_random` and `test_coling2022_random` fir random split (the coling2022 split does not have validation set).
### Models
| model | training data | F1 | F1 (macro) | Accuracy |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|---------:|-------------:|-----------:|
| [cardiffnlp/roberta-large-tweet-topic-multi-all](https://huggingface.co/cardiffnlp/roberta-large-tweet-topic-multi-all) | all (2020 + 2021) | 0.763104 | 0.620257 | 0.536629 |
| [cardiffnlp/roberta-base-tweet-topic-multi-all](https://huggingface.co/cardiffnlp/roberta-base-tweet-topic-multi-all) | all (2020 + 2021) | 0.751814 | 0.600782 | 0.531864 |
| [cardiffnlp/twitter-roberta-base-2019-90m-tweet-topic-multi-all](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m-tweet-topic-multi-all) | all (2020 + 2021) | 0.762513 | 0.603533 | 0.547945 |
| [cardiffnlp/twitter-roberta-base-dec2020-tweet-topic-multi-all](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020-tweet-topic-multi-all) | all (2020 + 2021) | 0.759917 | 0.59901 | 0.536033 |
| [cardiffnlp/twitter-roberta-base-dec2021-tweet-topic-multi-all](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021-tweet-topic-multi-all) | all (2020 + 2021) | 0.764767 | 0.618702 | 0.548541 |
| [cardiffnlp/roberta-large-tweet-topic-multi-2020](https://huggingface.co/cardiffnlp/roberta-large-tweet-topic-multi-2020) | 2020 only | 0.732366 | 0.579456 | 0.493746 |
| [cardiffnlp/roberta-base-tweet-topic-multi-2020](https://huggingface.co/cardiffnlp/roberta-base-tweet-topic-multi-2020) | 2020 only | 0.725229 | 0.561261 | 0.499107 |
| [cardiffnlp/twitter-roberta-base-2019-90m-tweet-topic-multi-2020](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m-tweet-topic-multi-2020) | 2020 only | 0.73671 | 0.565624 | 0.513401 |
| [cardiffnlp/twitter-roberta-base-dec2020-tweet-topic-multi-2020](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2020-tweet-topic-multi-2020) | 2020 only | 0.729446 | 0.534799 | 0.50268 |
| [cardiffnlp/twitter-roberta-base-dec2021-tweet-topic-multi-2020](https://huggingface.co/cardiffnlp/twitter-roberta-base-dec2021-tweet-topic-multi-2020) | 2020 only | 0.731106 | 0.532141 | 0.509827 |
Model fine-tuning script can be found [here](https://huggingface.co/datasets/cardiffnlp/tweet_topic_multi/blob/main/lm_finetuning.py).
## Dataset Structure
### Data Instances
An example of `train` looks as follows.
```python
{
"date": "2021-03-07",
"text": "The latest The Movie theater Daily! {{URL}} Thanks to {{USERNAME}} {{USERNAME}} {{USERNAME}} #lunchtimeread #amc1000",
"id": "1368464923370676231",
"label": [0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
"label_name": ["film_tv_&_video"]
}
```
### Label ID
The label2id dictionary can be found at [here](https://huggingface.co/datasets/tner/tweet_topic_multi/raw/main/dataset/label.multi.json).
```python
{
"arts_&_culture": 0,
"business_&_entrepreneurs": 1,
"celebrity_&_pop_culture": 2,
"diaries_&_daily_life": 3,
"family": 4,
"fashion_&_style": 5,
"film_tv_&_video": 6,
"fitness_&_health": 7,
"food_&_dining": 8,
"gaming": 9,
"learning_&_educational": 10,
"music": 11,
"news_&_social_concern": 12,
"other_hobbies": 13,
"relationships": 14,
"science_&_technology": 15,
"sports": 16,
"travel_&_adventure": 17,
"youth_&_student_life": 18
}
```
### Citation Information
```
@inproceedings{dimosthenis-etal-2022-twitter,
title = "{T}witter {T}opic {C}lassification",
author = "Antypas, Dimosthenis and
Ushio, Asahi and
Camacho-Collados, Jose and
Neves, Leonardo and
Silva, Vitor and
Barbieri, Francesco",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics"
}
``` |
true |
# Dataset Card for PubMed
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** : [https://www.nlm.nih.gov/databases/download/pubmed_medline.html]()
- **Documentation:** : [https://www.nlm.nih.gov/databases/download/pubmed_medline_documentation.html]()
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
NLM produces a baseline set of MEDLINE/PubMed citation records in XML format for download on an annual basis. The annual baseline is released in December of each year. Each day, NLM produces update files that include new, revised and deleted citations. See our documentation page for more information.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
- English
## Dataset Structure
Bear in mind the data comes from XML that have various tags that are hard to reflect
in a concise JSON format. Tags and list are kind of non "natural" to XML documents
leading this library to make some choices regarding data. "Journal" info was dropped
altogether as it would have led to many fields being empty all the time.
The hierarchy is also a bit unnatural but the choice was made to keep as close as
possible to the original data for future releases that may change schema from NLM's side.
Author has been kept and contains either "ForeName", "LastName", "Initials", or "CollectiveName".
(All the fields will be present all the time, but only some will be filled)
### Data Instances
```json
{
"MedlineCitation": {
"PMID": 0,
"DateCompleted": {"Year": 0, "Month": 0, "Day": 0},
"NumberOfReferences": 0,
"DateRevised": {"Year": 0, "Month": 0, "Day": 0},
"Article": {
"Abstract": {"AbstractText": "Some abstract (can be missing)" },
"ArticleTitle": "Article title",
"AuthorList": {"Author": [
{"FirstName": "John", "ForeName": "Doe", "Initials": "JD", "CollectiveName": ""}
{"CollectiveName": "The Manhattan Project", "FirstName": "", "ForeName": "", "Initials": ""}
]},
"Language": "en",
"GrantList": {
"Grant": [],
},
"PublicationTypeList": {"PublicationType": []},
},
"MedlineJournalInfo": {"Country": "France"},
"ChemicalList": {"Chemical": [{
"RegistryNumber": "XX",
"NameOfSubstance": "Methanol"
}]},
"CitationSubset": "AIM",
"MeshHeadingList": {
"MeshHeading": [],
},
},
"PubmedData": {
"ArticleIdList": {"ArticleId": "10.1002/bjs.1800650203"},
"PublicationStatus": "ppublish",
"History": {"PubMedPubDate": [{"Year": 0, "Month": 0, "Day": 0}]},
"ReferenceList": [{"Citation": "Somejournal", "CitationId": 01}],
},
}
```
### Data Fields
Main Fields will probably interest people are:
- "MedlineCitation" > "Article" > "AuthorList" > "Author"
- "MedlineCitation" > "Article" > "Abstract" > "AbstractText"
- "MedlineCitation" > "Article" > "Article Title"
- "MedlineCitation" > "ChemicalList" > "Chemical"
- "MedlineCitation" > "NumberOfReferences"
### Data Splits
There are no splits in this dataset. It is given as is.
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[https://www.nlm.nih.gov/databases/download/pubmed_medline_faq.html]()
#### 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
[https://www.nlm.nih.gov/databases/download/terms_and_conditions.html]()
### Citation Information
[Courtesy of the U.S. National Library of Medicine](https://www.nlm.nih.gov/databases/download/terms_and_conditions.html).
### Contributions
Thanks to [@Narsil](https://github.com/Narsil) for adding this dataset.
|
true |
# Dataset Card for JGLUE
[](https://aclanthology.org/2022.lrec-1.317)
JGLUE is a benchmark to measure the ability of natural language understanding in Japanese. For further details please refer to [the original repository](https://github.com/yahoojapan/JGLUE).
### Licensing Information
> This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
### Citation Information
```bibtex
@inproceedings{kurihara-etal-2022-jglue,
title = "{JGLUE}: {J}apanese General Language Understanding Evaluation",
author = "Kurihara, Kentaro and
Kawahara, Daisuke and
Shibata, Tomohide",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.317",
pages = "2957--2966",
abstract = "To develop high-performance natural language understanding (NLU) models, it is necessary to have a benchmark to evaluate and analyze NLU ability from various perspectives. While the English NLU benchmark, GLUE, has been the forerunner, benchmarks are now being released for languages other than English, such as CLUE for Chinese and FLUE for French; but there is no such benchmark for Japanese. We build a Japanese NLU benchmark, JGLUE, from scratch without translation to measure the general NLU ability in Japanese. We hope that JGLUE will facilitate NLU research in Japanese.",
}
```
```bibtex
@InProceedings{Kurihara_nlp2022,
author = "栗原健太郎 and 河原大輔 and 柴田知秀",
title = "JGLUE: 日本語言語理解ベンチマーク",
booktitle = "言語処理学会第 28 回年次大会",
year = "2022",
url = "https://www.anlp.jp/proceedings/annual_meeting/2022/pdf_dir/E8-4.pdf"
note= "in Japanese"
}
```
### Contributions
Thanks to [Kentaro Kurihara](https://twitter.com/kkurihara_cs), [Daisuke Kawahara](https://twitter.com/daisukekawahar1), and [Tomohide Shibata](https://twitter.com/stomohide) for creating this dataset.
The code for integration with Hugging Face `datasets` is originally written by [Shunsuke Kitada](https://twitter.com/shunk031) and adapted from [this repository](https://huggingface.co/datasets/shunk031/JGLUE). |
false |
# **CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society**
- **Github:** https://github.com/lightaime/camel
- **Website:** https://www.camel-ai.org/
- **Arxiv Paper:** https://arxiv.org/abs/2303.17760
## Dataset Summary
Chemistry dataset is composed of 20K problem-solution pairs obtained using gpt-4. The dataset problem-solutions pairs generating from 25 chemistry topics, 25 subtopics for each topic and 32 problems for each "topic,subtopic" pairs.
We provide the data in `chemistry.zip`.
## Data Fields
**The data fields for files in `chemistry.zip` are as follows:**
* `role_1`: assistant role
* `topic`: chemistry topic
* `sub_topic`: chemistry subtopic belonging to topic
* `message_1`: refers to the problem the assistant is asked to solve.
* `message_2`: refers to the solution provided by the assistant.
**Download in python**
```
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="camel-ai/chemistry", repo_type="dataset", filename="chemistry.zip",
local_dir="datasets/", local_dir_use_symlinks=False)
```
### Citation
```
@misc{li2023camel,
title={CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society},
author={Guohao Li and Hasan Abed Al Kader Hammoud and Hani Itani and Dmitrii Khizbullin and Bernard Ghanem},
year={2023},
eprint={2303.17760},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
```
## Disclaimer:
This data was synthetically generated by GPT4 and might contain incorrect information. The dataset is there only for research purposes.
---
license: cc-by-nc-4.0
---
|
false |
# Dataset Card for "squad_es"
## 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/ccasimiro88/TranslateAlignRetrieve](https://github.com/ccasimiro88/TranslateAlignRetrieve)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Size of downloaded dataset files:** 39.29 MB
- **Size of the generated dataset:** 94.63 MB
- **Total amount of disk used:** 133.92 MB
### Dataset Summary
Automatic translation of the Stanford Question Answering Dataset (SQuAD) v2 into Spanish
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### v1.1.0
- **Size of downloaded dataset files:** 39.29 MB
- **Size of the generated dataset:** 94.63 MB
- **Total amount of disk used:** 133.92 MB
An example of 'train' looks as follows.
```
This example was too long and was cropped:
{
"answers": {
"answer_start": [404, 356, 356],
"text": ["Santa Clara, California", "Levi 's Stadium", "Levi 's Stadium en la Bahía de San Francisco en Santa Clara, California."]
},
"context": "\"El Super Bowl 50 fue un partido de fútbol americano para determinar al campeón de la NFL para la temporada 2015. El campeón de ...",
"id": "56be4db0acb8001400a502ee",
"question": "¿Dónde tuvo lugar el Super Bowl 50?",
"title": "Super Bowl _ 50"
}
```
### Data Fields
The data fields are the same among all splits.
#### v1.1.0
- `id`: a `string` feature.
- `title`: a `string` feature.
- `context`: a `string` feature.
- `question`: a `string` feature.
- `answers`: a dictionary feature containing:
- `text`: a `string` feature.
- `answer_start`: a `int32` feature.
### Data Splits
| name |train|validation|
|------|----:|---------:|
|v1.1.0|87595| 10570|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
The SQuAD-es dataset is licensed under the [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) license.
### Citation Information
```
@article{2016arXiv160605250R,
author = {Casimiro Pio , Carrino and Marta R. , Costa-jussa and Jose A. R. , Fonollosa},
title = "{Automatic Spanish Translation of the SQuAD Dataset for Multilingual
Question Answering}",
journal = {arXiv e-prints},
year = 2019,
eid = {arXiv:1912.05200v1},
pages = {arXiv:1912.05200v1},
archivePrefix = {arXiv},
eprint = {1912.05200v2},
}
```
### Contributions
Thanks to [@patrickvonplaten](https://github.com/patrickvonplaten), [@thomwolf](https://github.com/thomwolf), [@albertvillanova](https://github.com/albertvillanova), [@lewtun](https://github.com/lewtun) for adding this dataset. |
false |
# Dataset Card for QaZre
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [http://nlp.cs.washington.edu/zeroshot](http://nlp.cs.washington.edu/zeroshot)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Size of downloaded dataset files:** 516.06 MB
- **Size of the generated dataset:** 2.09 GB
- **Total amount of disk used:** 2.60 GB
### Dataset Summary
A dataset reducing relation extraction to simple reading comprehension questions
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 516.06 MB
- **Size of the generated dataset:** 2.09 GB
- **Total amount of disk used:** 2.60 GB
An example of 'validation' looks as follows.
```
{
"answers": [],
"context": "answer",
"question": "What is XXX in this question?",
"relation": "relation_name",
"subject": "Some entity Here is a bit of context which will explain the question in some way"
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `relation`: a `string` feature.
- `question`: a `string` feature.
- `subject`: a `string` feature.
- `context`: a `string` feature.
- `answers`: a `list` of `string` features.
### Data Splits
| name | train | validation | test |
|---------|--------:|-----------:|-------:|
| default | 8400000 | 6000 | 120000 |
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
Unknown.
### Citation Information
```
@inproceedings{levy-etal-2017-zero,
title = "Zero-Shot Relation Extraction via Reading Comprehension",
author = "Levy, Omer and
Seo, Minjoon and
Choi, Eunsol and
Zettlemoyer, Luke",
booktitle = "Proceedings of the 21st Conference on Computational Natural Language Learning ({C}o{NLL} 2017)",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/K17-1034",
doi = "10.18653/v1/K17-1034",
pages = "333--342",
}
```
### Contributions
Thanks to [@thomwolf](https://github.com/thomwolf), [@lhoestq](https://github.com/lhoestq), [@ghomasHudson](https://github.com/ghomasHudson), [@lewtun](https://github.com/lewtun) for adding this dataset. |
false |
# Dataset Card for "ZEST: ZEroShot learning from Task descriptions"
## 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://allenai.org/data/zest
- **Repository:** https://github.com/allenai/zest
- **Paper:** https://arxiv.org/abs/2011.08115
- **Leaderboard:** https://leaderboard.allenai.org/zest/submissions/public
- **Point of Contact:**
### Dataset Summary
ZEST tests whether NLP systems can perform unseen tasks in a zero-shot way, given a natural language description of
the task. It is an instantiation of our proposed framework "learning from task descriptions". The tasks include
classification, typed entity extraction and relationship extraction, and each task is paired with 20 different
annotated (input, output) examples. ZEST's structure allows us to systematically test whether models can generalize
in five different ways.
### Supported Tasks and Leaderboards
A [leaderboard](https://leaderboard.allenai.org/zest/submissions/public) is included with accepatbility metrics for
each of the four generalization types outlined in the paper. The metrics are novel acceptability metrics also
proposed by the authors.
### Languages
The dataset is in English.
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
To evaluate the ability of a model to generalize to unseen tasks based only on a task description in a zero-shot
manner.
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
Mechanical Turk crowdsource workers.
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
Mechanical Turk crowdsource workers.
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
The dataset emphasizes a model's ability to generalize to unseen tasks with only a natural language description of
the task. The long-term vision of this type of evaluation is to facilitate the creation of models which can perform
arbitrary tasks with only a prompt from a non-technical user. This could broaden the frontier of what a user can
ask something like a chatbot to do for them, but it is unclear how restrictions would be put in place to prevent
users from prompting a system to perform unethical tasks.
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
This dataset is licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).
### Citation Information
```
@inproceedings{weller-etal-2020-learning,
title = "Learning from Task Descriptions",
author = "Weller, Orion and
Lourie, Nicholas and
Gardner, Matt and
Peters, Matthew",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.emnlp-main.105",
pages = "1361--1375",
abstract = "Typically, machine learning systems solve new tasks by training on thousands of examples. In contrast, humans can solve new tasks by reading some instructions, with perhaps an example or two. To take a step toward closing this gap, we introduce a framework for developing NLP systems that solve new tasks after reading their descriptions, synthesizing prior work in this area. We instantiate this frame- work with a new English language dataset, ZEST, structured for task-oriented evaluation on unseen tasks. Formulating task descriptions as questions, we ensure each is general enough to apply to many possible inputs, thus comprehensively evaluating a model{'}s ability to solve each task. Moreover, the dataset{'}s structure tests specific types of systematic generalization. We find that the state-of-the-art T5 model achieves a score of 12% on ZEST, leaving a significant challenge for NLP researchers.",
}
```
### Contributions
Thanks to [@joeddav](https://github.com/joeddav) for adding this dataset. |
false |
# **CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society**
- **Github:** https://github.com/lightaime/camel
- **Website:** https://www.camel-ai.org/
- **Arxiv Paper:** https://arxiv.org/abs/2303.17760
## Dataset Summary
Biology dataset is composed of 20K problem-solution pairs obtained using gpt-4. The dataset problem-solutions pairs generating from 25 biology topics, 25 subtopics for each topic and 32 problems for each "topic,subtopic" pairs.
We provide the data in `biology.zip`.
## Data Fields
**The data fields for files in `biology.zip` are as follows:**
* `role_1`: assistant role
* `topic`: biology topic
* `sub_topic`: biology subtopic belonging to topic
* `message_1`: refers to the problem the assistant is asked to solve.
* `message_2`: refers to the solution provided by the assistant.
**Download in python**
```
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="camel-ai/biology", repo_type="dataset", filename="biology.zip",
local_dir="datasets/", local_dir_use_symlinks=False)
```
### Citation
```
@misc{li2023camel,
title={CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society},
author={Guohao Li and Hasan Abed Al Kader Hammoud and Hani Itani and Dmitrii Khizbullin and Bernard Ghanem},
year={2023},
eprint={2303.17760},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
```
## Disclaimer:
This data was synthetically generated by GPT4 and might contain incorrect information. The dataset is there only for research purposes.
---
license: cc-by-nc-4.0
---
|
true |
# Dataset Card for the Gutenberg Time dataset
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **[Repository](https://github.com/allenkim/what-time-is-it)**
- **[Paper](https://arxiv.org/abs/2011.04124)**
### Dataset Summary
A clean data resource containing all explicit time references in a dataset of 52,183 novels whose full text is available via Project Gutenberg.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
Time-of-the-day classification from excerpts.
## Dataset Structure
### Data Instances
```
{
"guten_id": 28999,
"hour_reference": 12,
"time_phrase": "midday",
"is_ambiguous": False,
"time_pos_start": 133,
"time_pos_end": 134,
"tok_context": "Sorrows and trials she had had in plenty in her life , but these the sweetness of her nature had transformed , so that from being things difficult to bear , she had built up with them her own character . Sorrow had increased her own power of sympathy ; out of trials she had learnt patience ; and failure and the gradual sinking of one she had loved into the bottomless slough of evil habit had but left her with an added dower of pity and tolerance . So the past had no sting left , and if iron had ever entered into her soul it now but served to make it strong . She was still young , too ; it was not near sunset with her yet , nor even midday , and the future that , humanly speaking , she counted to be hers was almost dazzling in its brightness . For love had dawned for her again , and no uncertain love , wrapped in the mists of memory , but one that had ripened through liking and friendship and intimacy into the authentic glory . He was in England , too ; she was going back to him . And before very long she would never go away from him again ."
}
```
### Data Fields
```
guten_id - Gutenberg ID number
hour_reference - hour from 0 to 23
time_phrase - the phrase corresponding to the referenced hour
is_ambiguous - boolean whether it is clear whether time is AM or PM
time_pos_start - token position where time_phrase begins
time_pos_end - token position where time_phrase ends (exclusive)
tok_context - context in which time_phrase appears as space-separated tokens
```
### Data Splits
No data splits.
## Dataset Creation
### Curation Rationale
The flow of time is an indispensable guide for our actions, and provides a framework in which to see a logical progression of events. Just as in real life,the clock provides the background against which literary works play out: when characters wake, eat,and act. In most works of fiction, the events of the story take place during recognizable time periods over the course of the day. Recognizing a story’s flow through time is essential to understanding the text.In this paper, we try to capture the flow of time through novels by attempting to recognize what time of day each event in the story takes place at.
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
Novel authors.
### Annotations
#### Annotation process
Manually annotated.
#### Who are the annotators?
Two of the authors.
### Personal and Sensitive Information
No Personal or sensitive information.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
Allen Kim, Charuta Pethe and Steven Skiena, Stony Brook University
### Licensing Information
[More Information Needed]
### Citation Information
```
@misc{kim2020time,
title={What time is it? Temporal Analysis of Novels},
author={Allen Kim and Charuta Pethe and Steven Skiena},
year={2020},
eprint={2011.04124},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@TevenLeScao](https://github.com/TevenLeScao) for adding this dataset. |
false |
# Dataset Card for TMU-GFM-Dataset
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [N/A]
- **Repository:** https://github.com/tmu-nlp/TMU-GFM-Dataset
- **Paper:** [SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction](https://www.aclweb.org/anthology/2020.coling-main.573.pdf)
- **Leaderboard:** [N/A]
- **Point of Contact:** Check the paper.
### Dataset Summary
Authors collected manual evaluations for the grammaticality, fluency, and meaning preservation of the system outputs of 1,381 sentences from CoNLL 2013.
To collect the manual evaluations for various system outputs, each source sentence was corrected by the following five typical systems: statistical machine translation (SMT) (Grundkiewicz and Junczys-Dowmunt, 2018), recurrent neural network (RNN) (Luong et al., 2015), convolutional neural network (CNN) (Chollampatt and Ng, 2018), self-attention network (SAN) (Vaswani et al., 2017), and SAN with copy mechanism (SAN+Copy) (Zhao et al., 2019).
Manual evaluation for the grammaticality, fluency, and meaning preservation were assigned to a total of 4,223 sentences.
### Supported Tasks and Leaderboards
Grammatical Error Correction
### Languages
English
## Dataset Structure
### Data Instances
An example from the TMU-GFM-Dataset looks as follows:
```
{'ave_f': 3.4000000953674316,
'ave_g': 3.4000000953674316,
'ave_m': 3.5999999046325684,
'fluency': [3, 4, 3, 4, 3],
'grammer': [3, 4, 3, 4, 3],
'meaning': [3, 4, 4, 4, 3],
'output': 'After all, there will be an endless battle between the technology and human mentality.',
'source': 'Afterall there will be an endless battle between the technology and human mentality.',
'system': 'lstm,cnn'}
```
### Data Fields
The are 9 columns in the tmu-gfm-dataset.
- source: source sentence.
- output: system output sentence.
- grammer: Grammaticaliry annotations by 5 annotators.
- fluency: Fluency annotations by 5 annotators.
- meaning: Meaning Preservation annotations by 5 annotators.
- system: Which system the output sentence is from.
- ave_g: Average grammer score.
- ave_f: Average fluency score.
- ave_m: Average meaning score.
### Data Splits
Authors divided the dataset into train/dev/test with 3,376/422/423 sentences and used for fine-tuning BERT in thier paper.
## Dataset Creation
### Curation Rationale
The authors proposed a reference-less metric trained on manual evaluations of system outputs for grammatical error correction (GEC).
They said that previous studies have shown that reference-less metrics are promising; however, existing metrics are not optimized for manual evaluation of the system output because there is no dataset of system output with manual evaluation.
To achieve a better correlation with manual evaluation, they created a dataset to optimize each sub-metric to the manual evaluation of GEC systems. Their annotators evaluated the output of five typical GEC systems.
### Source Data
#### Initial Data Collection and Normalization
Authors collected manual evaluations for the grammaticality, fluency, and meaning preservation of the system outputs of 1,381 sentences from CoNLL 2013.
To collect the manual evaluations for various system outputs, each source sentence was corrected by the following five typical systems: statistical machine translation (SMT) (Grundkiewicz and Junczys-Dowmunt, 2018), recurrent neural network (RNN) (Luong et al., 2015), convolutional neural network (CNN) (Chollampatt and Ng, 2018), self-attention network (SAN) (Vaswani et al., 2017), and SAN with copy mechanism (SAN+Copy) (Zhao et al., 2019).
#### Who are the source language producers?
machine-generated
### Annotations
#### Annotation process
By excluding duplicate corrected sentences, manual evaluation for the grammaticality, fluency, and meaning preservation were assigned to a total of 4,223 sentences, as follows:
- Grammaticality: Annotators evaluated the grammatical correctness of the system output. The authors followed the five-point scale evaluation criteria (4: Perfect, 3: Comprehensible, 2: Somewhat comprehensible, 1: Incomprehensible, and 0: Other) proposed by Heilman et al. (2014).
- Fluency: Annotators evaluated how natural the sentence sounds for native speakers. The authors followed the criteria (4: Extremely natural, 3: Somewhat natural, 2: Somewhat unnatural, and 1: Extremely unnatural) proposed by Lau et al. (2015).
- Meaning preservation: Annotators evaluated the extent to which the meaning of source sentences is preserved in system output. The authors followed the criteria (4: Identical, 3: Minor differences, 2: Moderate differences, 1: Sub- stantially different, and 0: Other) proposed by Xu et al. (2016).
Finally, the authors created a dataset with manual evaluations for a total of 4,221 sentences, excluding sentences in which three or more annotators answered “0: Other.”
#### Who are the annotators?
Five native English annotators reqruited by using Amazon Mechaincal turk
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
@inproceedings{yoshimura-etal-2020-reference,
title = "{SOME}: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction",
author = "Yoshimura, Ryoma and
Kaneko, Masahiro and
Kajiwara, Tomoyuki and
Komachi, Mamoru",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.coling-main.573",
pages = "6516--6522",
abstract = "We propose a reference-less metric trained on manual evaluations of system outputs for grammatical error correction (GEC). Previous studies have shown that reference-less metrics are promising; however, existing metrics are not optimized for manual evaluations of the system outputs because no dataset of the system output exists with manual evaluation. This study manually evaluates outputs of GEC systems to optimize the metrics. Experimental results show that the proposed metric improves correlation with the manual evaluation in both system- and sentence-level meta-evaluation. Our dataset and metric will be made publicly available.",
}
### Contributions
Thanks to [@forest1988](https://github.com/forest1988) for adding this dataset. |
false |
# Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering
## 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/amazon-science/mintaka
- **Repository:** https://github.com/amazon-science/mintaka
- **Paper:** https://aclanthology.org/2022.coling-1.138/
- **Point of Contact:** [GitHub](https://github.com/amazon-science/mintaka)
### Dataset Summary
Mintaka is a complex, natural, and multilingual question answering (QA) dataset composed of 20,000 question-answer pairs elicited from MTurk workers and annotated with Wikidata question and answer entities. Full details on the Mintaka dataset can be found in our paper: https://aclanthology.org/2022.coling-1.138/
To build Mintaka, we explicitly collected questions in 8 complexity types, as well as generic questions:
- Count (e.g., Q: How many astronauts have been elected to Congress? A: 4)
- Comparative (e.g., Q: Is Mont Blanc taller than Mount Rainier? A: Yes)
- Superlative (e.g., Q: Who was the youngest tribute in the Hunger Games? A: Rue)
- Ordinal (e.g., Q: Who was the last Ptolemaic ruler of Egypt? A: Cleopatra)
- Multi-hop (e.g., Q: Who was the quarterback of the team that won Super Bowl 50? A: Peyton Manning)
- Intersection (e.g., Q: Which movie was directed by Denis Villeneuve and stars Timothee Chalamet? A: Dune)
- Difference (e.g., Q: Which Mario Kart game did Yoshi not appear in? A: Mario Kart Live: Home Circuit)
- Yes/No (e.g., Q: Has Lady Gaga ever made a song with Ariana Grande? A: Yes.)
- Generic (e.g., Q: Where was Michael Phelps born? A: Baltimore, Maryland)
- We collected questions about 8 categories: Movies, Music, Sports, Books, Geography, Politics, Video Games, and History
Mintaka is one of the first large-scale complex, natural, and multilingual datasets that can be used for end-to-end question-answering models.
### Supported Tasks and Leaderboards
The dataset can be used to train a model for question answering.
To ensure comparability, please refer to our evaluation script here: https://github.com/amazon-science/mintaka#evaluation
### Languages
All questions were written in English and translated into 8 additional languages: Arabic, French, German, Hindi, Italian, Japanese, Portuguese, and Spanish.
## Dataset Structure
### Data Instances
An example of 'train' looks as follows.
```json
{
"id": "a9011ddf",
"lang": "en",
"question": "What is the seventh tallest mountain in North America?",
"answerText": "Mount Lucania",
"category": "geography",
"complexityType": "ordinal",
"questionEntity":
[
{
"name": "Q49",
"entityType": "entity",
"label": "North America",
"mention": "North America",
"span": [40, 53]
},
{
"name": 7,
"entityType": "ordinal",
"mention": "seventh",
"span": [12, 19]
}
],
"answerEntity":
[
{
"name": "Q1153188",
"label": "Mount Lucania",
}
],
}
```
### Data Fields
The data fields are the same among all splits.
`id`: a unique ID for the given sample.
`lang`: the language of the question.
`question`: the original question elicited in the corresponding language.
`answerText`: the original answer text elicited in English.
`category`: the category of the question. Options are: geography, movies, history, books, politics, music, videogames, or sports
`complexityType`: the complexity type of the question. Options are: ordinal, intersection, count, superlative, yesno comparative, multihop, difference, or generic
`questionEntity`: a list of annotated question entities identified by crowd workers.
```
{
"name": The Wikidata Q-code or numerical value of the entity
"entityType": The type of the entity. Options are:
entity, cardinal, ordinal, date, time, percent, quantity, or money
"label": The label of the Wikidata Q-code
"mention": The entity as it appears in the English question text. Will be empty for non-English samples.
"span": The start and end characters of the mention in the English question text. Will be empty for non-English samples.
}
```
`answerEntity`: a list of annotated answer entities identified by crowd workers.
```
{
"name": The Wikidata Q-code or numerical value of the entity
"label": The label of the Wikidata Q-code
}
```
### Data Splits
For each language, we split into train (14,000 samples), dev (2,000 samples), and test (4,000 samples) sets.
### Personal and Sensitive Information
The corpora is free of personal or sensitive information.
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
Amazon Alexa AI.
### Licensing Information
This project is licensed under the CC-BY-4.0 License.
### Citation Information
Please cite the following papers when using this dataset.
```latex
@inproceedings{sen-etal-2022-mintaka,
title = "Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering",
author = "Sen, Priyanka and
Aji, Alham Fikri and
Saffari, Amir",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.138",
pages = "1604--1619"
}
```
### Contributions
Thanks to [@afaji](https://github.com/afaji) for adding this dataset. |
false | # Multi30k
This dataset contains the "multi30k" dataset, which is the "task 1" dataset from [here](https://www.statmt.org/wmt16/multimodal-task.html).
Each example consists of an "en" and a "de" feature. "en" is an English sentence, and "de" is the German translation of the English sentence.
### Data Splits
The Multi30k dataset has 3 splits: _train_, _validation_, and _test_.
| Dataset Split | Number of Instances in Split |
| ------------- | ------------------------------------------- |
| Train | 29,000 |
| Validation | 1,014 |
| Test | 1,000 |
### Citation Information
```
@article{elliott-EtAl:2016:VL16,
author = {{Elliott}, D. and {Frank}, S. and {Sima'an}, K. and {Specia}, L.},
title = {Multi30K: Multilingual English-German Image Descriptions},
booktitle = {Proceedings of the 5th Workshop on Vision and Language},
year = {2016},
pages = {70--74},
year = 2016
}
``` |
false |
# Dataset Card for SharcModified
## 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:** [More info needed]
- **Repository:** [github](https://github.com/nikhilweee/neural-conv-qa)
- **Paper:** [Neural Conversational QA: Learning to Reason v.s. Exploiting Patterns](https://arxiv.org/abs/1909.03759)
- **Leaderboard:** [More info needed]
- **Point of Contact:** [More info needed]
### Dataset Summary
ShARC, a conversational QA task, requires a system to answer user questions based on rules expressed in natural language text.
However, it is found that in the ShARC dataset there are multiple spurious patterns that could be exploited by neural models.
SharcModified is a new dataset which reduces the patterns identified in the original dataset.
To reduce the sensitivity of neural models, for each occurence of an instance conforming to any of the patterns,
we automatically construct alternatives where we choose to either replace the current instance with an alternative
instance which does not exhibit the pattern; or retain the original instance.
The modified ShARC has two versions sharc-mod and history-shuffled.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
The dataset is in english (en).
## Dataset Structure
### Data Instances
Example of one instance:
```
{
"annotation": {
"answer": [
{
"paragraph_reference": {
"end": 64,
"start": 35,
"string": "syndactyly affecting the feet"
},
"sentence_reference": {
"bridge": false,
"end": 64,
"start": 35,
"string": "syndactyly affecting the feet"
}
}
],
"explanation_type": "single_sentence",
"referential_equalities": [
{
"question_reference": {
"end": 40,
"start": 29,
"string": "webbed toes"
},
"sentence_reference": {
"bridge": false,
"end": 11,
"start": 0,
"string": "Webbed toes"
}
}
],
"selected_sentence": {
"end": 67,
"start": 0,
"string": "Webbed toes is the common name for syndactyly affecting the feet . "
}
},
"example_id": 9174646170831578919,
"original_nq_answers": [
{
"end": 45,
"start": 35,
"string": "syndactyly"
}
],
"paragraph_text": "Webbed toes is the common name for syndactyly affecting the feet . It is characterised by the fusion of two or more digits of the feet . This is normal in many birds , such as ducks ; amphibians , such as frogs ; and mammals , such as kangaroos . In humans it is considered unusual , occurring in approximately one in 2,000 to 2,500 live births .",
"question": "what is the medical term for webbed toes",
"sentence_starts": [
0,
67,
137,
247
],
"title_text": "Webbed toes",
"url": "https: //en.wikipedia.org//w/index.php?title=Webbed_toes&oldid=801229780"
}
```
### Data Fields
- `example_id`: a unique integer identifier that matches up with NQ
- `title_text`: the title of the wikipedia page containing the paragraph
- `url`: the url of the wikipedia page containing the paragraph
- `question`: a natural language question string from NQ
- `paragraph_text`: a paragraph string from a wikipedia page containing the answer to question
- `sentence_starts`: a list of integer character offsets indicating the start of sentences in the paragraph
- `original_nq_answers`: the original short answer spans from NQ
- `annotation`: the QED annotation, a dictionary with the following items and further elaborated upon below:
- `referential_equalities`: a list of dictionaries, one for each referential equality link annotated
- `answer`: a list of dictionaries, one for each short answer span
- `selected_sentence`: a dictionary representing the annotated sentence in the passage
- `explanation_type`: one of "single_sentence", "multi_sentence", or "none"
### Data Splits
The dataset is split into training and validation splits.
| | train | validation |
|--------------|------:|-----------:|
| N. Instances | 7638 | 1355 |
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
Unknown.
### Citation Information
```
@misc{lamm2020qed,
title={QED: A Framework and Dataset for Explanations in Question Answering},
author={Matthew Lamm and Jennimaria Palomaki and Chris Alberti and Daniel Andor and Eunsol Choi and Livio Baldini Soares and Michael Collins},
year={2020},
eprint={2009.06354},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
Thanks to [@patil-suraj](https://github.com/patil-suraj) for adding this dataset. |
false | # Dataset Card for "Zhihu-KOL"
Zhihu data for training Open Assitant
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) |
true |
# Dataset Card for SemEval 2014 - Task 1
## 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:** [SemEval-2014 Task 1](https://alt.qcri.org/semeval2014/task1/)
- **Repository:**
- **Paper:** [Aclweb](https://www.aclweb.org/anthology/S14-2001/)
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@ashmeet13](https://github.com/ashmeet13) for adding this dataset. |
false |
# Dataset Card for Europa Education and Culture Translation Memory (EAC-TM)
## 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://ec.europa.eu/jrc/en/language-technologies/eac-translation-memory](https://ec.europa.eu/jrc/en/language-technologies/eac-translation-memory)
- **Paper:** [https://link.springer.com/article/10.1007/s10579-014-9277-0](https://link.springer.com/article/10.1007/s10579-014-9277-0)
- **Point of Contact:** [ralf.steinberg@jrc.ec.europa.eu](mailto:ralf.steinberg@jrc.ec.europa.eu)
### Dataset Summary
This dataset is a corpus of manually produced translations from english to up to 25 languages, released in 2012 by the European Union's Directorate General for Education and Culture (EAC).
To load a language pair that is not part of the config, just specify the language code as language pair. For example, if you want to translate Czech to Greek:
`dataset = load_dataset("europa_eac_tm", language_pair=("cs", "el"))`
### Supported Tasks and Leaderboards
- `text2text-generation`: the dataset can be used to train a model for `machine-translation`. Machine translation models are usually evaluated using metrics such as [BLEU](https://huggingface.co/metrics/bleu), [ROUGE](https://huggingface.co/metrics/rouge) or [SacreBLEU](https://huggingface.co/metrics/sacrebleu). You can use the [mBART](https://huggingface.co/facebook/mbart-large-cc25) model for this task. This task has active leaderboards which can be found at [https://paperswithcode.com/task/machine-translation](https://paperswithcode.com/task/machine-translation), which usually rank models based on [BLEU score](https://huggingface.co/metrics/bleu).
### Languages
The sentences in this dataset were originally written in English (source language is English) and then translated into the other languages. The sentences are extracted from electroniv forms: application and report forms for decentralised actions of EAC's Life-long Learning Programme (LLP) and the Youth in Action Programme. The contents in the electronic forms are technically split into two types: (a) the labels and contents of drop-down menus (referred to as 'Forms' Data) and (b) checkboxes (referred to as 'Reference Data').
The dataset contains traduction of English sentences or parts of sentences to Bulgarian, Czech, Danish, Dutch, Estonian, German, Greek, Finnish, French, Croatian, Hungarian, Icelandic, Italian, Latvian, Lithuanian, Maltese, Norwegian, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, Swedish and Turkish.
Language codes:
- `bg`
- `cs`
- `da`
- `de`
- `el`
- `en`
- `es`
- `et`
- `fi`
- `fr`
- `hr`
- `hu`
- `is`
- `it`
- `lt`
- `lv`
- `mt`
- `nl`
- `no`
- `pl`
- `pt`
- `ro`
- `sk`
- `sl`
- `sv`
- `tr`
## Dataset Structure
### Data Instances
```
{
"translation": {
"en":"Sentence to translate",
"<target_language>": "Phrase à traduire",
},
"sentence_type": 0
}
```
### Data Fields
- `translation`: Mapping of sentences to translate (in English) and translated sentences.
- `sentence_type`: Integer value, 0 if the sentence is a 'form data' (extracted from the labels and contents of drop-down menus of the source electronic forms) or 1 if the sentence is a 'reference data' (extracted from the electronic forms checkboxes).
### Data Splits
The data is not splitted (only the `train` split is available).
## Dataset Creation
### Curation Rationale
The EAC-TM is relatively small compared to the JRC-Acquis and to DGT-TM, but it has the advantage that it focuses on a very different domain, namely that of education and culture. Also, it includes translation units for the languages Croatian (HR), Icelandic (IS), Norwegian (Bokmål, NB or Norwegian, NO) and Turkish (TR).
### Source Data
#### Initial Data Collection and Normalization
EAC-TM was built in the context of translating electronic forms: application and report forms for decentralised actions of EAC's Life-long Learning Programme (LLP) and the Youth in Action Programme. All documents and sentences were originally written in English (source language is English) and then translated into the other languages.
The contents in the electronic forms are technically split into two types: (a) the labels and contents of drop-down menus (referred to as 'Forms' Data) and (b) checkboxes (referred to as 'Reference Data'). Due to the different types of data, the two collections are kept separate. For example, labels can be 'Country', 'Please specify your home country' etc., while examples for reference data are 'Germany', 'Basic/general programmes', 'Education and Culture' etc.
The data consists of translations carried out between the end of the year 2008 and July 2012.
#### Who are the source language producers?
The texts were translated by staff of the National Agencies of the Lifelong Learning and Youth in Action programmes. They are typically professionals in the field of education/youth and EU programmes. They are thus not professional translators, but they are normally native speakers of the target language.
### Annotations
#### Annotation process
Sentences were manually translated by humans.
#### Who are the annotators?
The texts were translated by staff of the National Agencies of the Lifelong Learning and Youth in Action programmes. They are typically professionals in the field of education/youth and EU programmes. They are thus not professional translators, but they are normally native speakers of the target language.
### 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
© European Union, 1995-2020
The Commission's reuse policy is implemented by the [Commission Decision of 12 December 2011 on the reuse of Commission documents](https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32011D0833).
Unless otherwise indicated (e.g. in individual copyright notices), content owned by the EU on this website is licensed under the [Creative Commons Attribution 4.0 International (CC BY 4.0) licence](http://creativecommons.org/licenses/by/4.0/). This means that reuse is allowed, provided appropriate credit is given and changes are indicated.
You may be required to clear additional rights if a specific content depicts identifiable private individuals or includes third-party works. To use or reproduce content that is not owned by the EU, you may need to seek permission directly from the rightholders. Software or documents covered by industrial property rights, such as patents, trade marks, registered designs, logos and names, are excluded from the Commission's reuse policy and are not licensed to you.
### Citation Information
```
@Article{Steinberger2014,
author={Steinberger, Ralf
and Ebrahim, Mohamed
and Poulis, Alexandros
and Carrasco-Benitez, Manuel
and Schl{\"u}ter, Patrick
and Przybyszewski, Marek
and Gilbro, Signe},
title={An overview of the European Union's highly multilingual parallel corpora},
journal={Language Resources and Evaluation},
year={2014},
month={Dec},
day={01},
volume={48},
number={4},
pages={679-707},
issn={1574-0218},
doi={10.1007/s10579-014-9277-0},
url={https://doi.org/10.1007/s10579-014-9277-0}
}
```
### Contributions
Thanks to [@SBrandeis](https://github.com/SBrandeis) for adding this dataset. |
false |
# Dataset Card for "squad_v1_pt"
## 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/nunorc/squad-v1.1-pt](https://github.com/nunorc/squad-v1.1-pt)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Size of downloaded dataset files:** 39.53 MB
- **Size of the generated dataset:** 96.72 MB
- **Total amount of disk used:** 136.25 MB
### Dataset Summary
Portuguese translation of the SQuAD dataset. The translation was performed automatically using the Google Cloud API.
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 39.53 MB
- **Size of the generated dataset:** 96.72 MB
- **Total amount of disk used:** 136.25 MB
An example of 'train' looks as follows.
```
This example was too long and was cropped:
{
"answers": {
"answer_start": [0],
"text": ["Saint Bernadette Soubirous"]
},
"context": "\"Arquitetonicamente, a escola tem um caráter católico. No topo da cúpula de ouro do edifício principal é uma estátua de ouro da ...",
"id": "5733be284776f41900661182",
"question": "A quem a Virgem Maria supostamente apareceu em 1858 em Lourdes, na França?",
"title": "University_of_Notre_Dame"
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `id`: a `string` feature.
- `title`: a `string` feature.
- `context`: a `string` feature.
- `question`: a `string` feature.
- `answers`: a dictionary feature containing:
- `text`: a `string` feature.
- `answer_start`: a `int32` feature.
### Data Splits
| name | train | validation |
| ------- | ----: | ---------: |
| default | 87599 | 10570 |
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
```
@article{2016arXiv160605250R,
author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev},
Konstantin and {Liang}, Percy},
title = "{SQuAD: 100,000+ Questions for Machine Comprehension of Text}",
journal = {arXiv e-prints},
year = 2016,
eid = {arXiv:1606.05250},
pages = {arXiv:1606.05250},
archivePrefix = {arXiv},
eprint = {1606.05250},
}
```
### Contributions
Thanks to [@thomwolf](https://github.com/thomwolf), [@albertvillanova](https://github.com/albertvillanova), [@lewtun](https://github.com/lewtun), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset. |
false |
# Dataset Card for The modified Winograd Schema Challenge (MWSC)
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [http://decanlp.com](http://decanlp.com)
- **Repository:** https://github.com/salesforce/decaNLP
- **Paper:** [The Natural Language Decathlon: Multitask Learning as Question Answering](https://arxiv.org/abs/1806.08730)
- **Point of Contact:** [Bryan McCann](mailto:bmccann@salesforce.com), [Nitish Shirish Keskar](mailto:nkeskar@salesforce.com)
- **Size of downloaded dataset files:** 19.20 kB
- **Size of the generated dataset:** 39.35 kB
- **Total amount of disk used:** 58.55 kB
### Dataset Summary
Examples taken from the Winograd Schema Challenge modified to ensure that answers are a single word from the context.
This Modified Winograd Schema Challenge (MWSC) ensures that scores are neither inflated nor deflated by oddities in phrasing.
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### default
- **Size of downloaded dataset files:** 0.02 MB
- **Size of the generated dataset:** 0.04 MB
- **Total amount of disk used:** 0.06 MB
An example looks as follows:
```
{
"sentence": "The city councilmen refused the demonstrators a permit because they feared violence.",
"question": "Who feared violence?",
"options": [ "councilmen", "demonstrators" ],
"answer": "councilmen"
}
```
### Data Fields
The data fields are the same among all splits.
#### default
- `sentence`: a `string` feature.
- `question`: a `string` feature.
- `options`: a `list` of `string` features.
- `answer`: a `string` feature.
### Data Splits
| name |train|validation|test|
|-------|----:|---------:|---:|
|default| 80| 82| 100|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
Our code for running decaNLP has been open sourced under BSD-3-Clause.
We chose to restrict decaNLP to datasets that were free and publicly accessible for research, but you should check their individual terms if you deviate from this use case.
From the [Winograd Schema Challenge](https://cs.nyu.edu/~davise/papers/WinogradSchemas/WS.html):
> Both versions of the collections are licenced under a [Creative Commons Attribution 4.0 International License](http://creativecommons.org/licenses/by/4.0/).
### Citation Information
If you use this in your work, please cite:
```
@article{McCann2018decaNLP,
title={The Natural Language Decathlon: Multitask Learning as Question Answering},
author={Bryan McCann and Nitish Shirish Keskar and Caiming Xiong and Richard Socher},
journal={arXiv preprint arXiv:1806.08730},
year={2018}
}
```
### Contributions
Thanks to [@thomwolf](https://github.com/thomwolf), [@lewtun](https://github.com/lewtun), [@ghomasHudson](https://github.com/ghomasHudson), [@lhoestq](https://github.com/lhoestq) for adding this dataset.
|
false |
# Dataset Card for GREAT
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** None
- **Repository:** https://github.com/google-research-datasets/great
- **Paper:** https://openreview.net/forum?id=B1lnbRNtwr
- **Leaderboard:** [More Information Needed]
- **Point of Contact:** [More Information Needed]
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
Here are some examples of questions and facts:
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
[More Information Needed]
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
[More Information Needed]
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset. |
false |
# Dataset Card for "search_qa"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Repository:** https://github.com/nyu-dl/dl4ir-searchQA
- **Paper:** [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://arxiv.org/abs/1704.05179)
- **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:** 6.46 GB
- **Size of the generated dataset:** 15.28 GB
- **Total amount of disk used:** 21.74 GB
### Dataset Summary
We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering. Unlike recently released datasets, such as DeepMind
CNN/DailyMail and SQuAD, the proposed SearchQA was constructed to reflect a full pipeline of general question-answering. That is, we start not from an existing article
and generate a question-answer pair, but start from an existing question-answer pair, crawled from J! Archive, and augment it with text snippets retrieved by Google.
Following this approach, we built SearchQA, which consists of more than 140k question-answer pairs with each pair having 49.6 snippets on average. Each question-answer-context
tuple of the SearchQA comes with additional meta-data such as the snippet's URL, which we believe will be valuable resources for future research. We conduct human evaluation
as well as test two baseline methods, one simple word selection and the other deep learning based, on the SearchQA. We show that there is a meaningful gap between the human
and machine performances. This suggests that the proposed dataset could well serve as a benchmark for question-answering.
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### raw_jeopardy
- **Size of downloaded dataset files:** 3.31 GB
- **Size of the generated dataset:** 7.77 GB
- **Total amount of disk used:** 11.09 GB
An example of 'train' looks as follows.
```
```
#### train_test_val
- **Size of downloaded dataset files:** 3.15 GB
- **Size of the generated dataset:** 7.51 GB
- **Total amount of disk used:** 10.66 GB
An example of 'validation' looks as follows.
```
```
### Data Fields
The data fields are the same among all splits.
#### raw_jeopardy
- `category`: a `string` feature.
- `air_date`: a `string` feature.
- `question`: a `string` feature.
- `value`: a `string` feature.
- `answer`: a `string` feature.
- `round`: a `string` feature.
- `show_number`: a `int32` feature.
- `search_results`: a dictionary feature containing:
- `urls`: a `string` feature.
- `snippets`: a `string` feature.
- `titles`: a `string` feature.
- `related_links`: a `string` feature.
#### train_test_val
- `category`: a `string` feature.
- `air_date`: a `string` feature.
- `question`: a `string` feature.
- `value`: a `string` feature.
- `answer`: a `string` feature.
- `round`: a `string` feature.
- `show_number`: a `int32` feature.
- `search_results`: a dictionary feature containing:
- `urls`: a `string` feature.
- `snippets`: a `string` feature.
- `titles`: a `string` feature.
- `related_links`: a `string` feature.
### Data Splits
#### raw_jeopardy
| |train |
|------------|-----:|
|raw_jeopardy|216757|
#### train_test_val
| |train |validation|test |
|--------------|-----:|---------:|----:|
|train_test_val|151295| 21613|43228|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
```
@article{DBLP:journals/corr/DunnSHGCC17,
author = {Matthew Dunn and
Levent Sagun and
Mike Higgins and
V. Ugur G{"{u}}ney and
Volkan Cirik and
Kyunghyun Cho},
title = {SearchQA: {A} New Q{\&}A Dataset Augmented with Context from a
Search Engine},
journal = {CoRR},
volume = {abs/1704.05179},
year = {2017},
url = {http://arxiv.org/abs/1704.05179},
archivePrefix = {arXiv},
eprint = {1704.05179},
timestamp = {Mon, 13 Aug 2018 16:47:09 +0200},
biburl = {https://dblp.org/rec/journals/corr/DunnSHGCC17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
### Contributions
Thanks to [@lewtun](https://github.com/lewtun), [@mariamabarham](https://github.com/mariamabarham), [@lhoestq](https://github.com/lhoestq), [@thomwolf](https://github.com/thomwolf) for adding this dataset. |
true |
# MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages
## 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)
- [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)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [No Warranty](#no-warranty)
- [Citation Information](#citation-information)
## Dataset Description
- **Homepage:** https://github.com/alexa/massive
- **Repository:** https://github.com/alexa/massive
- **Paper:** https://arxiv.org/abs/2204.08582
- **Leaderboard:** https://eval.ai/web/challenges/challenge-page/1697/overview
- **Point of Contact:** [GitHub](https://github.com/alexa/massive/issues)
### Dataset Summary
MASSIVE is a parallel dataset of > 1M utterances across 51 languages with annotations for the Natural Language Understanding tasks of intent prediction and slot annotation. Utterances span 60 intents and include 55 slot types. MASSIVE was created by localizing the SLURP dataset, composed of general Intelligent Voice Assistant single-shot interactions.
| Name | Lang | Utt/Lang | Domains | Intents | Slots |
|:-------------------------------------------------------------------------------:|:-------:|:--------------:|:-------:|:--------:|:------:|
| MASSIVE | 51 | 19,521 | 18 | 60 | 55 |
| SLURP (Bastianelli et al., 2020) | 1 | 16,521 | 18 | 60 | 55 |
| NLU Evaluation Data (Liu et al., 2019) | 1 | 25,716 | 18 | 54 | 56 |
| Airline Travel Information System (ATIS) (Price, 1990) | 1 | 5,871 | 1 | 26 | 129 |
| ATIS with Hindi and Turkish (Upadhyay et al., 2018) | 3 | 1,315-5,871 | 1 | 26 | 129 |
| MultiATIS++ (Xu et al., 2020) | 9 | 1,422-5,897 | 1 | 21-26 | 99-140 |
| Snips (Coucke et al., 2018) | 1 | 14,484 | - | 7 | 53 |
| Snips with French (Saade et al., 2019) | 2 | 4,818 | 2 | 14-15 | 11-12 |
| Task Oriented Parsing (TOP) (Gupta et al., 2018) | 1 | 44,873 | 2 | 25 | 36 |
| Multilingual Task-Oriented Semantic Parsing (MTOP) (Li et al., 2021) | 6 | 15,195-22,288 | 11 | 104-113 | 72-75 |
| Cross-Lingual Multilingual Task Oriented Dialog (Schuster et al., 2019) | 3 | 5,083-43,323 | 3 | 12 | 11 |
| Microsoft Dialog Challenge (Li et al., 2018) | 1 | 38,276 | 3 | 11 | 29 |
| Fluent Speech Commands (FSC) (Lugosch et al., 2019) | 1 | 30,043 | - | 31 | - |
| Chinese Audio-Textual Spoken Language Understanding (CATSLU) (Zhu et al., 2019) | 1 | 16,258 | 4 | - | 94 |
### Supported Tasks and Leaderboards
The dataset can be used to train a model for `natural-language-understanding` (NLU) :
- `intent-classification`
- `multi-class-classification`
- `natural-language-understanding`
### Languages
The corpora consists of parallel sentences from 51 languages :
- `Afrikaans - South Africa (af-ZA)`
- `Amharic - Ethiopia (am-ET)`
- `Arabic - Saudi Arabia (ar-SA)`
- `Azeri - Azerbaijan (az-AZ)`
- `Bengali - Bangladesh (bn-BD)`
- `Chinese - China (zh-CN)`
- `Chinese - Taiwan (zh-TW)`
- `Danish - Denmark (da-DK)`
- `German - Germany (de-DE)`
- `Greek - Greece (el-GR)`
- `English - United States (en-US)`
- `Spanish - Spain (es-ES)`
- `Farsi - Iran (fa-IR)`
- `Finnish - Finland (fi-FI)`
- `French - France (fr-FR)`
- `Hebrew - Israel (he-IL)`
- `Hungarian - Hungary (hu-HU)`
- `Armenian - Armenia (hy-AM)`
- `Indonesian - Indonesia (id-ID)`
- `Icelandic - Iceland (is-IS)`
- `Italian - Italy (it-IT)`
- `Japanese - Japan (ja-JP)`
- `Javanese - Indonesia (jv-ID)`
- `Georgian - Georgia (ka-GE)`
- `Khmer - Cambodia (km-KH)`
- `Korean - Korea (ko-KR)`
- `Latvian - Latvia (lv-LV)`
- `Mongolian - Mongolia (mn-MN)`
- `Malay - Malaysia (ms-MY)`
- `Burmese - Myanmar (my-MM)`
- `Norwegian - Norway (nb-NO)`
- `Dutch - Netherlands (nl-NL)`
- `Polish - Poland (pl-PL)`
- `Portuguese - Portugal (pt-PT)`
- `Romanian - Romania (ro-RO)`
- `Russian - Russia (ru-RU)`
- `Slovanian - Slovania (sl-SL)`
- `Albanian - Albania (sq-AL)`
- `Swedish - Sweden (sv-SE)`
- `Swahili - Kenya (sw-KE)`
- `Hindi - India (hi-IN)`
- `Kannada - India (kn-IN)`
- `Malayalam - India (ml-IN)`
- `Tamil - India (ta-IN)`
- `Telugu - India (te-IN)`
- `Thai - Thailand (th-TH)`
- `Tagalog - Philippines (tl-PH)`
- `Turkish - Turkey (tr-TR)`
- `Urdu - Pakistan (ur-PK)`
- `Vietnamese - Vietnam (vi-VN)`
- `Welsh - United Kingdom (cy-GB)`
## Load the dataset with HuggingFace
```python
from datasets import load_dataset
dataset = load_dataset("qanastek/MASSIVE", "en-US", split='train')
print(dataset)
print(dataset[0])
```
## Dataset Structure
### Data Instances
```json
{
"id": "1",
"locale": "fr-FR",
"partition": "train",
"scenario": 16,
"intent": 48,
"utt": "réveille-moi à neuf heures du matin le vendredi",
"annot_utt": "réveille-moi à [time : neuf heures du matin] le [date : vendredi]",
"tokens": [
"réveille-moi",
"à",
"neuf",
"heures",
"du",
"matin",
"le",
"vendredi"
],
"ner_tags": [0, 0, 71, 6, 6, 6, 0, 14],
"worker_id": "22",
"slot_method": {
"slot": ["time", "date"],
"method": ["translation", "translation"]
},
"judgments": {
"worker_id": ["11", "22", "0"],
"intent_score": [2, 1, 1],
"slots_score": [1, 1, 1],
"grammar_score": [3, 4, 4],
"spelling_score": [2, 2, 2],
"language_identification": ["target", "target", "target"]
}
}
```
### Data Fields (taken from Alexa Github)
`id`: maps to the original ID in the [SLURP](https://github.com/pswietojanski/slurp) collection. Mapping back to the SLURP en-US utterance, this utterance served as the basis for this localization.
`locale`: is the language and country code accoring to ISO-639-1 and ISO-3166.
`partition`: is either `train`, `dev`, or `test`, according to the original split in [SLURP](https://github.com/pswietojanski/slurp).
`scenario`: is the general domain, aka "scenario" in SLURP terminology, of an utterance
`intent`: is the specific intent of an utterance within a domain formatted as `{scenario}_{intent}`
`utt`: the raw utterance text without annotations
`annot_utt`: the text from `utt` with slot annotations formatted as `[{label} : {entity}]`
`worker_id`: The obfuscated worker ID from MTurk of the worker completing the localization of the utterance. Worker IDs are specific to a locale and do *not* map across locales.
`slot_method`: for each slot in the utterance, whether that slot was a `translation` (i.e., same expression just in the target language), `localization` (i.e., not the same expression but a different expression was chosen more suitable to the phrase in that locale), or `unchanged` (i.e., the original en-US slot value was copied over without modification).
`judgments`: Each judgment collected for the localized utterance has 6 keys. `worker_id` is the obfuscated worker ID from MTurk of the worker completing the judgment. Worker IDs are specific to a locale and do *not* map across locales, but *are* consistent across the localization tasks and the judgment tasks, e.g., judgment worker ID 32 in the example above may appear as the localization worker ID for the localization of a different de-DE utterance, in which case it would be the same worker.
```plain
intent_score : "Does the sentence match the intent?"
0: No
1: Yes
2: It is a reasonable interpretation of the goal
slots_score : "Do all these terms match the categories in square brackets?"
0: No
1: Yes
2: There are no words in square brackets (utterance without a slot)
grammar_score : "Read the sentence out loud. Ignore any spelling, punctuation, or capitalization errors. Does it sound natural?"
0: Completely unnatural (nonsensical, cannot be understood at all)
1: Severe errors (the meaning cannot be understood and doesn't sound natural in your language)
2: Some errors (the meaning can be understood but it doesn't sound natural in your language)
3: Good enough (easily understood and sounds almost natural in your language)
4: Perfect (sounds natural in your language)
spelling_score : "Are all words spelled correctly? Ignore any spelling variances that may be due to differences in dialect. Missing spaces should be marked as a spelling error."
0: There are more than 2 spelling errors
1: There are 1-2 spelling errors
2: All words are spelled correctly
language_identification : "The following sentence contains words in the following languages (check all that apply)"
1: target
2: english
3: other
4: target & english
5: target & other
6: english & other
7: target & english & other
```
### Data Splits
|Language|Train|Dev|Test|
|:---:|:---:|:---:|:---:|
|af-ZA|11514|2033|2974|
|am-ET|11514|2033|2974|
|ar-SA|11514|2033|2974|
|az-AZ|11514|2033|2974|
|bn-BD|11514|2033|2974|
|cy-GB|11514|2033|2974|
|da-DK|11514|2033|2974|
|de-DE|11514|2033|2974|
|el-GR|11514|2033|2974|
|en-US|11514|2033|2974|
|es-ES|11514|2033|2974|
|fa-IR|11514|2033|2974|
|fi-FI|11514|2033|2974|
|fr-FR|11514|2033|2974|
|he-IL|11514|2033|2974|
|hi-IN|11514|2033|2974|
|hu-HU|11514|2033|2974|
|hy-AM|11514|2033|2974|
|id-ID|11514|2033|2974|
|is-IS|11514|2033|2974|
|it-IT|11514|2033|2974|
|ja-JP|11514|2033|2974|
|jv-ID|11514|2033|2974|
|ka-GE|11514|2033|2974|
|km-KH|11514|2033|2974|
|kn-IN|11514|2033|2974|
|ko-KR|11514|2033|2974|
|lv-LV|11514|2033|2974|
|ml-IN|11514|2033|2974|
|mn-MN|11514|2033|2974|
|ms-MY|11514|2033|2974|
|my-MM|11514|2033|2974|
|nb-NO|11514|2033|2974|
|nl-NL|11514|2033|2974|
|pl-PL|11514|2033|2974|
|pt-PT|11514|2033|2974|
|ro-RO|11514|2033|2974|
|ru-RU|11514|2033|2974|
|sl-SL|11514|2033|2974|
|sq-AL|11514|2033|2974|
|sv-SE|11514|2033|2974|
|sw-KE|11514|2033|2974|
|ta-IN|11514|2033|2974|
|te-IN|11514|2033|2974|
|th-TH|11514|2033|2974|
|tl-PH|11514|2033|2974|
|tr-TR|11514|2033|2974|
|ur-PK|11514|2033|2974|
|vi-VN|11514|2033|2974|
|zh-CN|11514|2033|2974|
|zh-TW|11514|2033|2974|
## Dataset Creation
### Source Data
#### Who are the source language producers?
The corpus has been produced and uploaded by Amazon Alexa.
### Personal and Sensitive Information
The corpora is free of personal or sensitive information.
## Additional Information
### Dataset Curators
__MASSIVE__: Jack FitzGerald and Christopher Hench and Charith Peris and Scott Mackie and Kay Rottmann and Ana Sanchez and Aaron Nash and Liam Urbach and Vishesh Kakarala and Richa Singh and Swetha Ranganath and Laurie Crist and Misha Britan and Wouter Leeuwis and Gokhan Tur and Prem Natarajan.
__SLURP__: Bastianelli, Emanuele and Vanzo, Andrea and Swietojanski, Pawel and Rieser, Verena.
__Hugging Face__: Labrak Yanis (Not affiliated with the original corpus)
### Licensing Information
```plain
Copyright Amazon.com Inc. or its affiliates.
Attribution 4.0 International
=======================================================================
Creative Commons Corporation ("Creative Commons") is not a law firm and
does not provide legal services or legal advice. Distribution of
Creative Commons public licenses does not create a lawyer-client or
other relationship. Creative Commons makes its licenses and related
information available on an "as-is" basis. Creative Commons gives no
warranties regarding its licenses, any material licensed under their
terms and conditions, or any related information. Creative Commons
disclaims all liability for damages resulting from their use to the
fullest extent possible.
Using Creative Commons Public Licenses
Creative Commons public licenses provide a standard set of terms and
conditions that creators and other rights holders may use to share
original works of authorship and other material subject to copyright
and certain other rights specified in the public license below. The
following considerations are for informational purposes only, are not
exhaustive, and do not form part of our licenses.
Considerations for licensors: Our public licenses are
intended for use by those authorized to give the public
permission to use material in ways otherwise restricted by
copyright and certain other rights. Our licenses are
irrevocable. Licensors should read and understand the terms
and conditions of the license they choose before applying it.
Licensors should also secure all rights necessary before
applying our licenses so that the public can reuse the
material as expected. Licensors should clearly mark any
material not subject to the license. This includes other CC-
licensed material, or material used under an exception or
limitation to copyright. More considerations for licensors:
wiki.creativecommons.org/Considerations_for_licensors
Considerations for the public: By using one of our public
licenses, a licensor grants the public permission to use the
licensed material under specified terms and conditions. If
the licensor's permission is not necessary for any reason--for
example, because of any applicable exception or limitation to
copyright--then that use is not regulated by the license. Our
licenses grant only permissions under copyright and certain
other rights that a licensor has authority to grant. Use of
the licensed material may still be restricted for other
reasons, including because others have copyright or other
rights in the material. A licensor may make special requests,
such as asking that all changes be marked or described.
Although not required by our licenses, you are encouraged to
respect those requests where reasonable. More considerations
for the public:
wiki.creativecommons.org/Considerations_for_licensees
=======================================================================
Creative Commons Attribution 4.0 International Public License
By exercising the Licensed Rights (defined below), You accept and agree
to be bound by the terms and conditions of this Creative Commons
Attribution 4.0 International Public License ("Public License"). To the
extent this Public License may be interpreted as a contract, You are
granted the Licensed Rights in consideration of Your acceptance of
these terms and conditions, and the Licensor grants You such rights in
consideration of benefits the Licensor receives from making the
Licensed Material available under these terms and conditions.
Section 1 -- Definitions.
a. Adapted Material means material subject to Copyright and Similar
Rights that is derived from or based upon the Licensed Material
and in which the Licensed Material is translated, altered,
arranged, transformed, or otherwise modified in a manner requiring
permission under the Copyright and Similar Rights held by the
Licensor. For purposes of this Public License, where the Licensed
Material is a musical work, performance, or sound recording,
Adapted Material is always produced where the Licensed Material is
synched in timed relation with a moving image.
b. Adapter's License means the license You apply to Your Copyright
and Similar Rights in Your contributions to Adapted Material in
accordance with the terms and conditions of this Public License.
c. Copyright and Similar Rights means copyright and/or similar rights
closely related to copyright including, without limitation,
performance, broadcast, sound recording, and Sui Generis Database
Rights, without regard to how the rights are labeled or
categorized. For purposes of this Public License, the rights
specified in Section 2(b)(1)-(2) are not Copyright and Similar
Rights.
d. Effective Technological Measures means those measures that, in the
absence of proper authority, may not be circumvented under laws
fulfilling obligations under Article 11 of the WIPO Copyright
Treaty adopted on December 20, 1996, and/or similar international
agreements.
e. Exceptions and Limitations means fair use, fair dealing, and/or
any other exception or limitation to Copyright and Similar Rights
that applies to Your use of the Licensed Material.
f. Licensed Material means the artistic or literary work, database,
or other material to which the Licensor applied this Public
License.
g. Licensed Rights means the rights granted to You subject to the
terms and conditions of this Public License, which are limited to
all Copyright and Similar Rights that apply to Your use of the
Licensed Material and that the Licensor has authority to license.
h. Licensor means the individual(s) or entity(ies) granting rights
under this Public License.
i. Share means to provide material to the public by any means or
process that requires permission under the Licensed Rights, such
as reproduction, public display, public performance, distribution,
dissemination, communication, or importation, and to make material
available to the public including in ways that members of the
public may access the material from a place and at a time
individually chosen by them.
j. Sui Generis Database Rights means rights other than copyright
resulting from Directive 96/9/EC of the European Parliament and of
the Council of 11 March 1996 on the legal protection of databases,
as amended and/or succeeded, as well as other essentially
equivalent rights anywhere in the world.
k. You means the individual or entity exercising the Licensed Rights
under this Public License. Your has a corresponding meaning.
Section 2 -- Scope.
a. License grant.
1. Subject to the terms and conditions of this Public License,
the Licensor hereby grants You a worldwide, royalty-free,
non-sublicensable, non-exclusive, irrevocable license to
exercise the Licensed Rights in the Licensed Material to:
a. reproduce and Share the Licensed Material, in whole or
in part; and
b. produce, reproduce, and Share Adapted Material.
2. Exceptions and Limitations. For the avoidance of doubt, where
Exceptions and Limitations apply to Your use, this Public
License does not apply, and You do not need to comply with
its terms and conditions.
3. Term. The term of this Public License is specified in Section
6(a).
4. Media and formats; technical modifications allowed. The
Licensor authorizes You to exercise the Licensed Rights in
all media and formats whether now known or hereafter created,
and to make technical modifications necessary to do so. The
Licensor waives and/or agrees not to assert any right or
authority to forbid You from making technical modifications
necessary to exercise the Licensed Rights, including
technical modifications necessary to circumvent Effective
Technological Measures. For purposes of this Public License,
simply making modifications authorized by this Section 2(a)
(4) never produces Adapted Material.
5. Downstream recipients.
a. Offer from the Licensor -- Licensed Material. Every
recipient of the Licensed Material automatically
receives an offer from the Licensor to exercise the
Licensed Rights under the terms and conditions of this
Public License.
b. No downstream restrictions. You may not offer or impose
any additional or different terms or conditions on, or
apply any Effective Technological Measures to, the
Licensed Material if doing so restricts exercise of the
Licensed Rights by any recipient of the Licensed
Material.
6. No endorsement. Nothing in this Public License constitutes or
may be construed as permission to assert or imply that You
are, or that Your use of the Licensed Material is, connected
with, or sponsored, endorsed, or granted official status by,
the Licensor or others designated to receive attribution as
provided in Section 3(a)(1)(A)(i).
b. Other rights.
1. Moral rights, such as the right of integrity, are not
licensed under this Public License, nor are publicity,
privacy, and/or other similar personality rights; however, to
the extent possible, the Licensor waives and/or agrees not to
assert any such rights held by the Licensor to the limited
extent necessary to allow You to exercise the Licensed
Rights, but not otherwise.
2. Patent and trademark rights are not licensed under this
Public License.
3. To the extent possible, the Licensor waives any right to
collect royalties from You for the exercise of the Licensed
Rights, whether directly or through a collecting society
under any voluntary or waivable statutory or compulsory
licensing scheme. In all other cases the Licensor expressly
reserves any right to collect such royalties.
Section 3 -- License Conditions.
Your exercise of the Licensed Rights is expressly made subject to the
following conditions.
a. Attribution.
1. If You Share the Licensed Material (including in modified
form), You must:
a. retain the following if it is supplied by the Licensor
with the Licensed Material:
i. identification of the creator(s) of the Licensed
Material and any others designated to receive
attribution, in any reasonable manner requested by
the Licensor (including by pseudonym if
designated);
ii. a copyright notice;
iii. a notice that refers to this Public License;
iv. a notice that refers to the disclaimer of
warranties;
v. a URI or hyperlink to the Licensed Material to the
extent reasonably practicable;
b. indicate if You modified the Licensed Material and
retain an indication of any previous modifications; and
c. indicate the Licensed Material is licensed under this
Public License, and include the text of, or the URI or
hyperlink to, this Public License.
2. You may satisfy the conditions in Section 3(a)(1) in any
reasonable manner based on the medium, means, and context in
which You Share the Licensed Material. For example, it may be
reasonable to satisfy the conditions by providing a URI or
hyperlink to a resource that includes the required
information.
3. If requested by the Licensor, You must remove any of the
information required by Section 3(a)(1)(A) to the extent
reasonably practicable.
4. If You Share Adapted Material You produce, the Adapter's
License You apply must not prevent recipients of the Adapted
Material from complying with this Public License.
Section 4 -- Sui Generis Database Rights.
Where the Licensed Rights include Sui Generis Database Rights that
apply to Your use of the Licensed Material:
a. for the avoidance of doubt, Section 2(a)(1) grants You the right
to extract, reuse, reproduce, and Share all or a substantial
portion of the contents of the database;
b. if You include all or a substantial portion of the database
contents in a database in which You have Sui Generis Database
Rights, then the database in which You have Sui Generis Database
Rights (but not its individual contents) is Adapted Material; and
c. You must comply with the conditions in Section 3(a) if You Share
all or a substantial portion of the contents of the database.
For the avoidance of doubt, this Section 4 supplements and does not
replace Your obligations under this Public License where the Licensed
Rights include other Copyright and Similar Rights.
Section 5 -- Disclaimer of Warranties and Limitation of Liability.
a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
c. The disclaimer of warranties and limitation of liability provided
above shall be interpreted in a manner that, to the extent
possible, most closely approximates an absolute disclaimer and
waiver of all liability.
Section 6 -- Term and Termination.
a. This Public License applies for the term of the Copyright and
Similar Rights licensed here. However, if You fail to comply with
this Public License, then Your rights under this Public License
terminate automatically.
b. Where Your right to use the Licensed Material has terminated under
Section 6(a), it reinstates:
1. automatically as of the date the violation is cured, provided
it is cured within 30 days of Your discovery of the
violation; or
2. upon express reinstatement by the Licensor.
For the avoidance of doubt, this Section 6(b) does not affect any
right the Licensor may have to seek remedies for Your violations
of this Public License.
c. For the avoidance of doubt, the Licensor may also offer the
Licensed Material under separate terms or conditions or stop
distributing the Licensed Material at any time; however, doing so
will not terminate this Public License.
d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
License.
Section 7 -- Other Terms and Conditions.
a. The Licensor shall not be bound by any additional or different
terms or conditions communicated by You unless expressly agreed.
b. Any arrangements, understandings, or agreements regarding the
Licensed Material not stated herein are separate from and
independent of the terms and conditions of this Public License.
Section 8 -- Interpretation.
a. For the avoidance of doubt, this Public License does not, and
shall not be interpreted to, reduce, limit, restrict, or impose
conditions on any use of the Licensed Material that could lawfully
be made without permission under this Public License.
b. To the extent possible, if any provision of this Public License is
deemed unenforceable, it shall be automatically reformed to the
minimum extent necessary to make it enforceable. If the provision
cannot be reformed, it shall be severed from this Public License
without affecting the enforceability of the remaining terms and
conditions.
c. No term or condition of this Public License will be waived and no
failure to comply consented to unless expressly agreed to by the
Licensor.
d. Nothing in this Public License constitutes or may be interpreted
as a limitation upon, or waiver of, any privileges and immunities
that apply to the Licensor or You, including from the legal
processes of any jurisdiction or authority.
=======================================================================
Creative Commons is not a party to its public licenses.
Notwithstanding, Creative Commons may elect to apply one of its public
licenses to material it publishes and in those instances will be
considered the “Licensor.” The text of the Creative Commons public
licenses is dedicated to the public domain under the CC0 Public Domain
Dedication. Except for the limited purpose of indicating that material
is shared under a Creative Commons public license or as otherwise
permitted by the Creative Commons policies published at
creativecommons.org/policies, Creative Commons does not authorize the
use of the trademark "Creative Commons" or any other trademark or logo
of Creative Commons without its prior written consent including,
without limitation, in connection with any unauthorized modifications
to any of its public licenses or any other arrangements,
understandings, or agreements concerning use of licensed material. For
the avoidance of doubt, this paragraph does not form part of the public
licenses.
Creative Commons may be contacted at creativecommons.org.
```
### Citation Information
Please cite the following paper when using this dataset.
```latex
@misc{fitzgerald2022massive,
title={MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages},
author={Jack FitzGerald and Christopher Hench and Charith Peris and Scott Mackie and Kay Rottmann and Ana Sanchez and Aaron Nash and Liam Urbach and Vishesh Kakarala and Richa Singh and Swetha Ranganath and Laurie Crist and Misha Britan and Wouter Leeuwis and Gokhan Tur and Prem Natarajan},
year={2022},
eprint={2204.08582},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@inproceedings{bastianelli-etal-2020-slurp,
title = "{SLURP}: A Spoken Language Understanding Resource Package",
author = "Bastianelli, Emanuele and
Vanzo, Andrea and
Swietojanski, Pawel and
Rieser, Verena",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.588",
doi = "10.18653/v1/2020.emnlp-main.588",
pages = "7252--7262",
abstract = "Spoken Language Understanding infers semantic meaning directly from audio data, and thus promises to reduce error propagation and misunderstandings in end-user applications. However, publicly available SLU resources are limited. In this paper, we release SLURP, a new SLU package containing the following: (1) A new challenging dataset in English spanning 18 domains, which is substantially bigger and linguistically more diverse than existing datasets; (2) Competitive baselines based on state-of-the-art NLU and ASR systems; (3) A new transparent metric for entity labelling which enables a detailed error analysis for identifying potential areas of improvement. SLURP is available at https://github.com/pswietojanski/slurp."
}
```
|
false |
# Dataset Card for BioLang
## Table of Contents
- [Dataset Card for [Dataset Name]](#dataset-card-for-dataset-name)
- [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://sourcedata.embo.org
- **Repository:** https://github.com/source-data/soda-roberta
- **Paper:**
- **Leaderboard:**
- **Point of Contact:** thomas.lemberger@embo.org
- **Download Size:** 5_299_878_661
### Dataset Summary
BioLang is a dataset is based on abstracts from the open access section of EuropePubMed Central to train language models in the domain of biology. The dataset can be used for random masked language modeling or for language modeling using only specific part-of-speech maksing. More details on generation and use of the dataset at https://github.com/source-data/soda-roberta .
### Supported Tasks and Leaderboards
- `MLM`: masked language modeling
- `DET`: part-of-speach masked language model, with determinants (`DET`) tagged
- `SMALL`: part-of-speech masked language model, with "small" words (`DET`, `CCONJ`, `SCONJ`, `ADP`, `PRON`) tagged
- `VERB`: part-of-speach masked language model, with verbs (`VERB`) tagged
### Languages
English
## Dataset Structure
### Data Instances
```json
{
"input_ids":[
0, 2444, 6997, 46162, 7744, 35, 20632, 20862, 3457, 36, 500, 23858, 29, 43, 32, 3919, 716, 15, 49, 4476, 4, 1398, 6, 52, 1118, 5, 20862, 819, 9, 430, 23305, 248, 23858, 29, 4, 256, 40086, 104, 35, 1927, 1069, 459, 1484, 58, 4776, 13, 23305, 634, 16706, 493, 2529, 8954, 14475, 73, 34263, 6, 4213, 718, 833, 12, 24291, 4473, 22500, 14475, 73, 510, 705, 73, 34263, 6, 5143, 4313, 2529, 8954, 14475, 73, 34263, 6, 8, 5143, 4313, 2529, 8954, 14475, 248, 23858, 29, 23, 4448, 225, 4722, 2392, 11, 9341, 261, 4, 49043, 35, 96, 746, 6, 5962, 9, 38415, 4776, 408, 36, 3897, 4, 398, 8871, 56, 23305, 4, 20, 15608, 21, 8061, 6164, 207, 13, 70, 248, 23858, 29, 6, 150, 5, 42561, 21, 8061, 5663, 207, 13, 80, 3457, 4, 509, 1296, 5129, 21567, 3457, 36, 398, 23528, 8748, 22065, 11654, 35, 7253, 15, 49, 4476, 6, 70, 3457, 4682, 65, 189, 28, 5131, 13, 23305, 9726, 4, 2
],
"label_ids": [
"X", "NOUN", "NOUN", "NOUN", "NOUN", "PUNCT", "ADJ", "ADJ", "NOUN", "PUNCT", "PROPN", "PROPN", "PROPN", "PUNCT", "AUX", "VERB", "VERB", "ADP", "DET", "NOUN", "PUNCT", "ADV", "PUNCT", "PRON", "VERB", "DET", "ADJ", "NOUN", "ADP", "ADJ", "NOUN", "NOUN", "NOUN", "NOUN", "PUNCT", "ADJ", "ADJ", "ADJ", "PUNCT", "NOUN", "NOUN", "NOUN", "NOUN", "AUX", "VERB", "ADP", "NOUN", "VERB", "PROPN", "PROPN", "PROPN", "PROPN", "PROPN", "SYM", "PROPN", "PUNCT", "PROPN", "PROPN", "PROPN", "PUNCT", "PROPN", "PROPN", "PROPN", "PROPN", "SYM", "PROPN", "PROPN", "SYM", "PROPN", "PUNCT", "PROPN", "PROPN", "PROPN", "PROPN", "PROPN", "SYM", "PROPN", "PUNCT", "CCONJ", "ADJ", "PROPN", "PROPN", "PROPN", "PROPN", "NOUN", "NOUN", "NOUN", "ADP", "PROPN", "PROPN", "PROPN", "PROPN", "ADP", "PROPN", "PROPN", "PUNCT", "PROPN", "PUNCT", "ADP", "NOUN", "PUNCT", "NUM", "ADP", "NUM", "VERB", "NOUN", "PUNCT", "NUM", "NUM", "NUM", "NOUN", "AUX", "NOUN", "PUNCT", "DET", "NOUN", "AUX", "X", "NUM", "NOUN", "ADP", "DET", "NOUN", "NOUN", "NOUN", "PUNCT", "SCONJ", "DET", "NOUN", "AUX", "X", "NUM", "NOUN", "ADP", "NUM", "NOUN", "PUNCT", "NUM", "NOUN", "VERB", "ADJ", "NOUN", "PUNCT", "NUM", "NOUN", "NOUN", "NOUN", "NOUN", "PUNCT", "VERB", "ADP", "DET", "NOUN", "PUNCT", "DET", "NOUN", "SCONJ", "PRON", "VERB", "AUX", "VERB", "ADP", "NOUN", "NOUN", "PUNCT", "X"
],
"special_tokens_mask": [
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1
]
}
```
### Data Fields
`MLM`:
- `input_ids`: a `list` of `int32` features.
- `special_tokens_mask`: a `list` of `int8` features.
`DET`, `VERB`, `SMALL`:
- `input_ids`: a `list` of `int32` features.
- `tag_mask`: a `list` of `int8` features.
### Data Splits
- `train`:
- features: ['input_ids', 'special_tokens_mask'],
- num_rows: 12_005_390
- `test`:
- features: ['input_ids', 'special_tokens_mask'],
- num_rows: 37_112
- `validation`:
- features: ['input_ids', 'special_tokens_mask'],
- num_rows: 36_713
## Dataset Creation
### Curation Rationale
The dataset was assembled to train language models in the field of cell and molecular biology. To expand the size of the dataset and to include many examples with highly technical language, abstracts were complemented with figure legends (or figure 'captions').
### Source Data
#### Initial Data Collection and Normalization
The xml content of papers were downloaded in January 2021 from the open access section of [EuropePMC]("https://europepmc.org/downloads/openaccess"). Figure legends and abstracts were extracted from the JATS XML, tokenized with the `roberta-base` tokenizer and part-of-speech tagged with Spacy's `en_core_web_sm` model (https://spacy.io).
More details at https://github.com/source-data/soda-roberta
#### Who are the source language producers?
Experts scientists.
### Annotations
#### Annotation process
Part-of-speech was tagged automatically.
#### Who are the annotators?
Spacy's `en_core_web_sm` model (https://spacy.io) was used for part-of-speech tagging.
### 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
Thomas Lemberger
### Licensing Information
CC-BY 4.0
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@tlemberger](https://github.com/tlemberger) for adding this dataset.
|
false |
## 内容
包含约350万条由[BELLE](https://github.com/LianjiaTech/BELLE)项目生成的中文指令数据。
## 样例
```
{
"id":"66623028",
"conversations":[
{
"from":"human",
"value":"归纳介绍三种不同类型的电影题材"
},
{
"from":"assistant",
"value":"1. 动作片：动作片通常强调动作和战斗场面，故事情节紧凑，充满了紧张和兴奋的氛围。主角一般是具有超凡实力或特殊技能的英雄人物，往往会与反派角色进行一系列激烈的格斗，追逐和爆破等酷炫场面。例如《速度与激情》和《复仇者联盟》等。\n2. 爱情片：爱情片是以爱情为主题的电影，着重呈现角色之间的感情纠葛，展现了爱情的美好和悲壮。情节与角色之间的发展令人深思，增加了观众的感性体验。这种电影的故事情节主要以人类与人类之间的情感变化为主题。例如《泰坦尼克号》和《让子弹飞》等。\n3. 科幻片：科幻片是以未来科技和未知世界为主题的电影，通常包括时间旅行、外星人、虚拟现实、未来社会等各种奇幻的元素。这种电影描绘了一种比现实更加宏伟、更加神秘和惊奇的世界。例如《星际穿越》和《发条橙》等。"
}
]
}
{
"id":"18205437",
"conversations":[
{
"from":"human",
"value":"根据给定的食材，编写一道美食菜谱。\n鸡腿肉、蘑菇、洋葱"
},
{
"from":"assistant",
"value":"鸡肉炒蘑菇洋葱\n食材：\n- 鸡腿肉 400克，去骨去皮切成小块\n- 蘑菇 200克，切片\n- 洋葱 1个，切丝\n- 生姜 适量，切丝\n- 酱油 2勺\n- 料酒 1勺\n- 盐 适量\n- 白胡椒粉 适量\n- 植物油 适量\n做法：\n1. 在一个碗里放入切好的鸡腿肉块，加入酱油、料酒和适量的白胡椒粉，搅拌均匀，腌制10分钟。\n2. 热锅凉油，加入姜丝翻炒，放入腌好的鸡肉块翻炒至变色。\n3. 加入洋葱丝和蘑菇，翻炒2-3分钟至蘑菇变软。\n4. 加入适量的盐和少量的水，盖上锅盖焖煮5分钟直至鸡肉熟透。\n5. 最后翻炒几下，使汤汁变浓稠即可。\n温馨提示：\n1. 在腌制鸡肉时，如果想让肉质更嫩滑，可以加入少量的淀粉和蛋清。\n2. 可以根据个人口味加入其他调料，如蒜末、辣椒等。\n3. 洋葱和蘑菇可以用其他蔬菜代替，如青椒、胡萝卜等。"
},
{
"from":"human",
"value":"太好了，我会试着照着你教的做一次，但是我最近买了一部新相机，想让你推荐一些好的拍照地点。"
},
{
"from":"assistant",
"value":"当地的风景区、公园、景点等等都是比较适合拍照的地点。如果你想要一些特别的地方，可以考虑一些建筑群，街道巷子、咖啡馆、书店等具有文艺气息的地方。"
},
{
"from":"human",
"value":"嗯，这些地方都很不错，但是我还想找一些可以体验当地文化和风俗的地点，你有什么好的建议吗？"
},
{
"from":"assistant",
"value":"如果你想要更深入地了解当地文化和风俗，可以考虑参加一些游学活动，比如参观当地的博物馆、参加民俗节庆、尝试当地美食等等。此外，也可以去一些小城镇，感受那里的古朴风情。"
}
]
}
```
### 字段：
```
id: 数据id
conversations: 数据内容，以对话形式给出，包括多轮和单轮对话的数据
```
## 使用限制
仅允许将此数据集及使用此数据集生成的衍生物用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。
本数据集不代表任何一方的立场、利益或想法，无关任何团体的任何类型的主张。因使用本数据集带来的任何损害、纠纷，本项目不承担任何责任。 |
true |
# Dataset Card for peer_read
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://arxiv.org/abs/1804.09635
- **Repository:** https://github.com/allenai/PeerRead
- **Paper:** https://arxiv.org/pdf/1804.09635.pdf
- **Leaderboard:** [Needs More Information]
- **Point of Contact:** [Needs More Information]
### Dataset Summary
PearRead is a dataset of scientific peer reviews available to help researchers study this important artifact. The dataset consists of over 14K paper drafts and the corresponding accept/reject decisions in top-tier venues including ACL, NIPS and ICLR, as well as over 10K textual peer reviews written by experts for a subset of the papers.
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
en-English
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
#### parsed_pdfs
- `name`: `string` Filename in the dataset
- `metadata`: `dict` Paper metadata
- `source`: `string` Paper source
- `authors`: `list<string>` List of paper authors
- `title`: `string` Paper title
- `sections`: `list<dict>` List of section heading and corresponding description
- `heading`: `string` Section heading
- `text`: `string` Section description
- `references`: `string` List of references
- `title`: `string` Title of reference paper
- `author`: `list<string>` List of reference paper authors
- `venue`: `string` Reference venue
- `citeRegEx`: `string` Reference citeRegEx
- `shortCiteRegEx`: `string` Reference shortCiteRegEx
- `year`: `int` Reference publish year
- `referenceMentions`: `list<string>` List of reference mentions
- `referenceID`: `int` Reference mention ID
- `context`: `string` Reference mention context
- `startOffset`: `int` Reference startOffset
- `endOffset`: `int` Reference endOffset
- `year`: `int` Paper publish year
- `abstractText`: `string` Paper abstract
- `creator`: `string` Paper creator
#### reviews
- `id`: `int` Review ID
- `conference`: `string` Conference name
- `comments`: `string` Review comments
- `subjects`: `string` Review subjects
- `version`: `string` Review version
- `date_of_submission`: `string` Submission date
- `title`: `string` Paper title
- `authors`: `list<string>` List of paper authors
- `accepted`: `bool` Paper accepted flag
- `abstract`: `string` Paper abstract
- `histories`: `list<string>` Paper details with link
- `reviews`: `dict` Paper reviews
- `date`: `string` Date of review
- `title`: `string` Paper title
- `other_keys`: `string` Reviewer other details
- `originality`: `string` Originality score
- `comments`: `string` Reviewer comments
- `is_meta_review`: `bool` Review type flag
- `recommendation`: `string` Reviewer recommendation
- `replicability`: `string` Replicability score
- `presentation_format`: `string` Presentation type
- `clarity`: `string` Clarity score
- `meaningful_comparison`: `string` Meaningful comparison score
- `substance`: `string` Substance score
- `reviewer_confidence`: `string` Reviewer confidence score
- `soundness_correctness`: `string` Soundness correctness score
- `appropriateness`: `string` Appropriateness score
- `impact`: `string` Impact score
### 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
Dongyeop Kang, Waleed Ammar, Bhavana Dalvi Mishra, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard Hovy, Roy Schwartz
### Licensing Information
[More Information Needed]
### Citation Information
@inproceedings{kang18naacl,
title = {A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications},
author = {Dongyeop Kang and Waleed Ammar and Bhavana Dalvi and Madeleine van Zuylen and Sebastian Kohlmeier and Eduard Hovy and Roy Schwartz},
booktitle = {Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL)},
address = {New Orleans, USA},
month = {June},
url = {https://arxiv.org/abs/1804.09635},
year = {2018}
}
### Contributions
Thanks to [@vinaykudari](https://github.com/vinaykudari) for adding this dataset. |
false |
# Dataset Card for "KULLM-v2"
## Dataset Summary
Korean translation of GPT4ALL, Dolly, and Vicuna data.
repository: [nlpai-lab/KULLM](https://github.com/nlpai-lab/KULLM)
huggingface: [nlpai-lab/kullm-v2](https://huggingface.co/nlpai-lab/kullm-polyglot-12.8b-v2)
#### Translate dataset
Translated 'instruction', 'input', and 'output' in the dataset via the DeepL API
## Lisence
Apache-2.0
```python
>>> from datasets import load_dataset
>>> ds = load_dataset("nlpai-lab/kullm-v2", split="train")
>>> ds
DatasetDict({
train: Dataset({
features: ['id', 'instruction', 'input', 'output'],
num_rows: 152630
})
})
```
```python
>>> ds[0]
{'id': 'alpaca_{idx}',
'instruction': '3원색이란 무엇인가요?',
'input': '',
'output': '세 가지 기본 색은 빨강, 파랑, 노랑입니다. 이 색은 다른 색을 혼합하여 만들 수 없고 다른 모든 색은 다양한 비율로 조합하여 만들 수 있기 때문에 원색이라고 부릅니다. 빛에 사용되는 첨가제 색상 시스템에서 원색은 빨강, 녹색, 파랑(RGB)입니다.'}
``` |
false |
# Dataset Card for KorQuAD v2.1
## 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://korquad.github.io/)
- [**Repository**](https://github.com/korquad/korquad.github.io/tree/master/dataset)
- [**Paper**](https://korquad.github.io/dataset/KorQuAD_2.0/KorQuAD_2.0_paper.pdf)
### Dataset Summary
KorQuAD 2.0 is a Korean question and answering dataset consisting of a total of 100,000+ pairs. There are three major differences from KorQuAD 1.0, which is the standard Korean Q & A data. The first is that a given document is a whole Wikipedia page, not just one or two paragraphs. Second, because the document also contains tables and lists, it is necessary to understand the document structured with HTML tags. Finally, the answer can be a long text covering not only word or phrase units, but paragraphs, tables, and lists.
### Supported Tasks and Leaderboards
`question-answering`
### Languages
Korean
## Dataset Structure
Follows the standart SQuAD format. There is only 1 answer per question
### Data Instances
An example from the data set looks as follows:
```py
{'answer': {'answer_start': 3873,
'html_answer_start': 16093,
'text': '20,890 표'},
'context': '<!DOCTYPE html>\n<html>\n<head>\n<meta>\n<title>심규언 - 위키백과, 우리 모두의 백과사전</title>\n\n\n<link>\n.....[omitted]',
'id': '36615',
'question': '심규언은 17대 지방 선거에서 몇 표를 득표하였는가?',
'raw_html': '<!DOCTYPE html>\n<html c ...[omitted]',
'title': '심규언',
'url': 'https://ko.wikipedia.org/wiki/심규언'}
```
### Data Fields
```py
{'id': Value(dtype='string', id=None),
'title': Value(dtype='string', id=None),
'context': Value(dtype='string', id=None),
'question': Value(dtype='string', id=None),
'answer': {'text': Value(dtype='string', id=None),
'answer_start': Value(dtype='int32', id=None),
'html_answer_start': Value(dtype='int32', id=None)},
'url': Value(dtype='string', id=None),
'raw_html': Value(dtype='string', id=None)}
```
### Data Splits
- Train : 83486
- Validation: 10165
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
Wikipedia
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[CC BY-ND 2.0 KR](https://creativecommons.org/licenses/by-nd/2.0/kr/deed.en)
### Citation Information
```
@article{NODE09353166,
author={Youngmin Kim,Seungyoung Lim;Hyunjeong Lee;Soyoon Park;Myungji Kim},
title={{KorQuAD 2.0: Korean QA Dataset for Web Document Machine Comprehension}},
booltitle={{Journal of KIISE 제47권 제6호}},
journal={{Journal of KIISE}},
volume={{47}},
issue={{6}},
publisher={The Korean Institute of Information Scientists and Engineers},
year={2020},
ISSN={{2383-630X}},
pages={577-586},
url={http://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE09353166}}
```
### Contributions
Thanks to [@cceyda](https://github.com/cceyda) for adding this dataset. |
false | # Dataset Card for "code_x_glue_tt_text_to_text"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits-sample-size)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://github.com/microsoft/CodeXGLUE/tree/main/Text-Text/text-to-text
### Dataset Summary
CodeXGLUE text-to-text dataset, available at https://github.com/microsoft/CodeXGLUE/tree/main/Text-Text/text-to-text
The dataset we use is crawled and filtered from Microsoft Documentation, whose document located at https://github.com/MicrosoftDocs/.
### Supported Tasks and Leaderboards
- `machine-translation`: The dataset can be used to train a model for translating Technical documentation between languages.
### Languages
da_en, lv_en, no_en, zh_en
## Dataset Structure
### Data Instances
#### da_en
An example of 'test' looks as follows.
```
{
"id": 0,
"source": "4 . K\u00f8r modellen , og udgiv den som en webtjeneste .\n",
"target": "4 . Run the model , and publish it as a web service .\n"
}
```
#### lv_en
An example of 'train' looks as follows.
```
{
"id": 0,
"source": "title : Pakalpojumu objektu izveide\n",
"target": "title : Create service objects\n"
}
```
#### no_en
An example of 'validation' looks as follows.
```
{
"id": 0,
"source": "2 . \u00c5pne servicevaren du vil definere komponenter fra en stykkliste for .\n",
"target": "2 . Open the service item for which you want to set up components from a BOM .\n"
}
```
#### zh_en
An example of 'validation' looks as follows.
```
{
"id": 0,
"source": "& # 124 ; MCDUserNotificationReadStateFilterAny & # 124 ; 0 & # 124 ; \u5305\u62ec \u901a\u77e5 , \u800c \u4e0d \u8003\u8651 \u8bfb\u53d6 \u72b6\u6001 \u3002 & # 124 ;\n",
"target": "| MCDUserNotificationReadStateFilterAny | 0 | Include notifications regardless of read state . |\n"
}
```
### Data Fields
In the following each data field in go is explained for each config. The data fields are the same among all splits.
#### da_en, lv_en, no_en, zh_en
|field name| type | description |
|----------|------|----------------------------------------|
|id |int32 | The index of the sample |
|source |string| The source language version of the text|
|target |string| The target language version of the text|
### Data Splits
|name |train|validation|test|
|-----|----:|---------:|---:|
|da_en|42701| 1000|1000|
|lv_en|18749| 1000|1000|
|no_en|44322| 1000|1000|
|zh_en|50154| 1000|1000|
## 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
https://github.com/microsoft, https://github.com/madlag
### Licensing Information
Computational Use of Data Agreement (C-UDA) License.
### Citation Information
```
@article{CodeXGLUE,
title={CodeXGLUE: A Benchmark Dataset and Open Challenge for Code Intelligence},
year={2020},}
```
### Contributions
Thanks to @madlag (and partly also @ncoop57) for adding this dataset. |
false |
## Dataset Summary
FaithDial is a faithful knowledge-grounded dialogue benchmark, composed of **50,761** turns spanning **5649** conversations. It was curated through Amazon Mechanical Turk by asking annotators to amend hallucinated utterances in [Wizard of Wikipedia](https://parl.ai/projects/wizard_of_wikipedia/) (WoW). In our dialogue setting, we simulate interactions between two speakers: **an information seeker** and **a bot wizard**. The seeker has a large degree of freedom as opposed to the wizard bot which is more restricted on what it can communicate. In fact, it must abide by the following rules:
- **First**, it should be truthful by providing information that is attributable to the source knowledge *K*.
- **Second**, it should provide information conversationally, i.e., use naturalistic phrasing of *K*, support follow-on discussion with questions, and prompt user's opinions.
- **Third**, it should acknowledge its ignorance of the answer in those cases where *K* does not include it while still moving the conversation forward using *K*.
## Dataset Description
- **Homepage:** [FaithDial](https://mcgill-nlp.github.io/FaithDial/)
- **Repository:** [GitHub](https://github.com/McGill-NLP/FaithDial)
- **Point of Contact:** [Nouha Dziri](mailto:dziri@ualberta.ca)
## Language
English
## Data Instance
An example of 'train' looks as follows:
```text
[
{
"utterances": [
... // prior utterances,
{
"history": [
"Have you ever been to a concert? They're so fun!",
"No I cannot as a bot. However, have you been to Madonna's? Her 10th concert was used to help her 13th album called \"Rebel Heart\".",
"Yeah I've heard of it but never went or what it was for. Can you tell me more about it?"
],
"speaker": "Wizard",
"knowledge": "It began on September 9, 2015, in Montreal, Canada, at the Bell Centre and concluded on March 20, 2016, in Sydney, Australia at Allphones Arena.",
"original_response": "It started in September of 2015 and ran all the way through March of 2016. Can you imagine being on the road that long?",
"response": "Sure. The concert started in September 9th of 2015 at Montreal, Canada. It continued till 20th of March of 2016, where it ended at Sydney, Australia.",
"BEGIN": [
"Hallucination",
"Entailment"
],
"VRM": [
"Disclosure",
"Question"
]
},
... // more utterances
]
},
... // more dialogues
]
```
If the `original_response` is empty, it means that the response is faithful to the source and we consider it as a FaithDial response. Faithful responses in WoW are also edited slightly if they are found to have some grammatical issues or typos.
## Data Fields
- `history`: `List[string]`. The dialogue history.
- `knowledge`: `string`. The source knowkedge on which the bot wizard should ground its response.
- `speaker`: `string`. The current speaker.
- `original response`: `string`. The WoW original response before editing it.
- `response`: `string`. The new Wizard response.
- `BEGIN`: `List[string]`. The BEGIN labels for the Wizard response.
- `VRM`: `List[string]`. The VRM labels for the wizard response.
## Data Splits
- `Train`: 36809 turns
- `Valid`: 6851 turns
- `Test`: 7101 turns
`Valid` includes both the `seen` and the `unseen` data splits from WoW. The same applies to `Test`. We also include those splits for FaithDial valid and test data.
## Annotations
Following the guidelines for ethical crowdsourcing outlined in [Sheehan. 2018](https://www.tandfonline.com/doi/abs/10.1080/03637751.2017.1342043),
we hire Amazon Mechanical Turk (AMT) workers to edit utterances in WoW dialogues that were found to exhibit unfaithful responses. To ensure clarity in the task definition, we provided detailed examples for our terminology. Moreover, we performed several staging rounds over the course of several months.
# Who are the annotators?
To be eligible for the task, workers have to be located in the United States and Canada and have to answer successfully 20 questions as part of a qualification test. Before launching the main annotation task, we perform a small pilot round (60 HITS) to check the performance of the workers. We email workers who commit errors, providing them with examples on how to fix their mistakes in future HITS.
## Personal and Sensitive Information
Seeker utterances in FaithDial may contain personal and sensitive information.
## Social Impact of Dataset
In recent years, the conversational AI market has seen
a proliferation of a variety of applications—which are powered by large pre-trained LMs—that span
across a broad range of domains, such as customer
support, education, e-commerce, health, entertainment, etc. Ensuring that
these systems are trustworthy is key to deploy systems safely at a large scale in real-world application, especially in high-stake domain. FaithDial holds promise to encourage faithfulness in information-seeking dialogue and make virtual assistants both safer and more reliable.
## Licensing Information
MIT
## Citation Information
```bibtex
@article{dziri2022faithdial,
title={FaithDial: A Faithful Benchmark for Information-Seeking Dialogue},
author={Dziri, Nouha and Kamalloo, Ehsan and Milton, Sivan and Zaiane, Osmar and Yu, Mo and Ponti, Edoardo and Reddy, Siva},
journal={arXiv preprint, arXiv:2204.10757},
year={2022},
url={https://arxiv.org/abs/2204.10757}
}
```
|
true |
# Offensive language dataset of Croatian comments FRENK 1.0
English subset of the [FRENK dataset](http://hdl.handle.net/11356/1433). Also available on HuggingFace dataset hub: [Croatian subset](https://huggingface.co/datasets/5roop/FRENK-hate-hr), [Slovenian subset](https://huggingface.co/datasets/5roop/FRENK-hate-sl).
## Dataset Description
- **Homepage:** http://hdl.handle.net/11356/1433
- **Repository:** http://hdl.handle.net/11356/1433
- **Paper:** https://arxiv.org/abs/1906.02045
- **Project page** https://nl.ijs.si/frenk/
## Description of the original dataset
The original FRENK dataset consists of comments to Facebook posts (news articles) of mainstream media outlets from Croatia, Great Britain, and Slovenia, on the topics of migrants and LGBT. The dataset contains whole discussion threads. Each comment is annotated by the type of socially unacceptable discourse (e.g., inappropriate, offensive, violent speech) and its target (e.g., migrants/LGBT, commenters, media). The annotation schema is described in detail in [https://arxiv.org/pdf/1906.02045.pdf]. Usernames in the metadata are pseudo-anonymised and removed from the comments.
The data in each language (Croatian (hr), English (en), Slovenian (sl), and topic (migrants, LGBT) is divided into a training and a testing portion. The training and testing data consist of separate discussion threads, i.e., there is no cross-discussion-thread contamination between training and testing data. The sizes of the splits are the following: Croatian, migrants: 4356 training comments, 978 testing comments; Croatian LGBT: 4494 training comments, 1142 comments; English, migrants: 4540 training comments, 1285 testing comments; English, LGBT: 4819 training comments, 1017 testing comments; Slovenian, migrants: 5145 training comments, 1277 testing comments; Slovenian, LGBT: 2842 training comments, 900 testing comments.
For this dataset only the English data was used. Training segment has been split into beginning 90% (published here as training split) and end 10% (published here as dev split).
## Usage in `Transformers`
```python
import datasets
ds = datasets.load_dataset("classla/FRENK-hate-en","binary")
```
For binary classification the following encoding is used:
```python
_CLASS_MAP_BINARY = {
'Acceptable': 0,
'Offensive': 1,
}
```
The original labels are available if the dataset is loaded with the `multiclass` option:
```python
import datasets
ds = datasets.load_dataset("5roop/FRENK-hate-en","multiclass").
```
In this case the encoding used is:
```python
_CLASS_MAP_MULTICLASS = {
'Acceptable speech': 0,
'Inappropriate': 1,
'Background offensive': 2,
'Other offensive': 3,
'Background violence': 4,
'Other violence': 5,
}
```
The original labels are available if the dataset is loaded with the `multiclass` option:
```python
import datasets
ds = datasets.load_dataset("classla/FRENK-hate-en","multiclass").
```
In this case the encoding used is:
```python
_CLASS_MAP_MULTICLASS = {
'Acceptable speech': 0,
'Inappropriate': 1,
'Background offensive': 2,
'Other offensive': 3,
'Background violence': 4,
'Other violence': 5,
}
```
## Data structure
* `text`: text
* `target`: who is the target of the hate-speech text ("no target", "commenter", "target" (migrants or LGBT, depending on the topic), or "related to" (again, the topic))
* `topic`: whether the text relates to lgbt or migrants hate-speech domains
* `label`: label of the text instance, see above.
## Data instance
```
{'text': "Not everyone has the option of a rainbow reaction; I don't but wish I did.",
'target': 'No target',
'topic': 'lgbt',
'label': 0}
```
## Licensing information
CLARIN.SI Licence ACA ID-BY-NC-INF-NORED 1.0
## Citation information
When using this dataset please cite the following paper:
```
@misc{ljubešić2019frenk,
title={The FRENK Datasets of Socially Unacceptable Discourse in Slovene and English},
author={Nikola Ljubešić and Darja Fišer and Tomaž Erjavec},
year={2019},
eprint={1906.02045},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/1906.02045}
}
```
The original dataset can be cited as
```
@misc{11356/1433,
title = {Offensive language dataset of Croatian, English and Slovenian comments {FRENK} 1.0},
author = {Ljube{\v s}i{\'c}, Nikola and Fi{\v s}er, Darja and Erjavec, Toma{\v z}},
url = {http://hdl.handle.net/11356/1433},
note = {Slovenian language resource repository {CLARIN}.{SI}},
copyright = {{CLARIN}.{SI} Licence {ACA} {ID}-{BY}-{NC}-{INF}-{NORED} 1.0},
year = {2021} }
```
|
false | # Dataset Card for "wikiner_fr"
Dataset Description:
- **Homepage:** https://metatext.io/datasets/wikiner
- **Repository:**
- **Paper:** https://www.sciencedirect.com/science/article/pii/S0004370212000276?via%3Dihub
- **Leaderboard:**
- **Point of Contact:** |
true | # NewsMTSC dataset
NewsMTSC is a high-quality dataset consisting of more than 11k manually labeled sentences sampled from English news articles. Each sentence was labeled by five human coders (the dataset contains only examples where the five coders assessed same or similar sentiment). The dataset is published as a [full paper at EACL 2021: *NewsMTSC: (Multi-)Target-dependent Sentiment Classification in News Articles*](https://aclanthology.org/2021.eacl-main.142.pdf).
## Subsets and splits
The dataset consists of two subsets (`rw` and `mt`), each consisting of three splits (train, validation, and test). We recommend to use the `rw` subset, which is also the default subset. Both subsets share the same train set, in which the three sentiment classes have similar frequency since we applied class boosting. The two subsets differ in their validation and test sets: `rw` contains validation and test sets that resemble real-world distribution of sentiment in news articles. In contrast, `mt`'s validation and test sets contain only sentences that each have two or more (different) targets, where each target's sentiment was labeled individually.
More information on the subsets can be found in our [paper](https://aclanthology.org/2021.eacl-main.142.pdf).
## Format
Each split is stored in a JSONL file. In JSONL, each line represents one JSON object. In our dataset, each JSON object consists of the following attributes. When using the dataset, you most likely will need (only) the attributes highlighted in **bold**.
1. `mention`: text of the mention within `sentence`
2. **`polarity`: sentiment of the sentence concerning the target's mention (-1 = negative, 0 = neutral, 1 = positive)**
3. **`from`: character-based, 0-indexed position of the first character of the target's mention within `sentence`**
4. **`to`: last character of the target's mention**
5. **`sentence`: sentence**
6. `id`: identifier that is unique within NewsMTSC
## Contact
If you find an issue with the dataset or model or have a question concerning either, please open an issue in the repository.
* Repository: [https://github.com/fhamborg/NewsMTSC](https://github.com/fhamborg/NewsMTSC)
* Web: [https://felix.hamborg.eu/](https://felix.hamborg.eu/)
## How to cite
If you use the dataset or parts of it, please cite our paper:
```
@InProceedings{Hamborg2021b,
author = {Hamborg, Felix and Donnay, Karsten},
title = {NewsMTSC: (Multi-)Target-dependent Sentiment Classification in News Articles},
booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021)},
year = {2021},
month = {Apr.},
location = {Virtual Event},
}
```
|
false |
# Dataset Card for few_rel
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [GitHub Page](https://thunlp.github.io/)
- **Repository:** [GitHub](https://github.com/thunlp/FewRel)
- **Paper:** [FewRel](https://arxiv.org/abs/1810.10147), [FewRel 2.0](https://arxiv.org/abs/1910.07124)
- **Leaderboard:** [GitHub Leaderboard](https://thunlp.github.io/fewrel.html)
- **Point of Contact:** [Needs More Information]
### Dataset Summary
FewRel is a large-scale few-shot relation extraction dataset, which contains more than one hundred relations and tens of thousands of annotated instances cross different domains.
### Supported Tasks and Leaderboards
[Needs More Information]
### Languages
The dataset contaings English text, as used by writers on Wikipedia, and crowdsourced English annotations.
## Dataset Structure
### Data Instances
An instance from `train_wiki` split:
```
{'head': {'indices': [[16]], 'text': 'tjq', 'type': 'Q1331049'}, 'names': ['place served by transport hub', 'territorial entity or entities served by this transport hub (airport, train station, etc.)'], 'relation': 'P931', 'tail': {'indices': [[13, 14]], 'text': 'tanjung pandan', 'type': 'Q3056359'}, 'tokens': ['Merpati', 'flight', '106', 'departed', 'Jakarta', '(', 'CGK', ')', 'on', 'a', 'domestic', 'flight', 'to', 'Tanjung', 'Pandan', '(', 'TJQ', ')', '.']}
```
### Data Fields
For `default`:
- `relation`: a `string` feature containing PID of the relation.
- `tokens`: a `list` of `string` features containing tokens for the text.
- `head`: a dictionary containing:
- `text`: a `string` feature representing the head entity.
- `type`: a `string` feature representing the type of the head entity.
- `indices`: a `list` containing `list` of token indices.
- `tail`: a dictionary containing:
- `text`: a `string` feature representing the tail entity.
- `type`: a `string` feature representing the type of the tail entity.
- `indices`: a `list` containing `list` of token indices.
- `names`: a `list` of `string` features containing relation names. For `pubmed_unsupervised` split, this is set to a `list` with an empty `string`. For `val_semeval` and `val_pubmed` split, this is set to a `list` with the `string` from the `relation` field.
### Data Splits
`train_wiki`: 44800
`val_nyt`: 2500
`val_pubmed`: 1000
`val_semeval`: 8851
`val_wiki`: 11200
`pubmed_unsupervised`: 2500
## 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
For FewRel:
Han, Xu and Zhu, Hao and Yu, Pengfei and Wang, Ziyun and Yao, Yuan and Liu, Zhiyuan and Sun, Maosong
For FewRel 2.0:
Gao, Tianyu and Han, Xu and Zhu, Hao and Liu, Zhiyuan and Li, Peng and Sun, Maosong and Zhou, Jie
### Licensing Information
```
MIT License
Copyright (c) 2018 THUNLP
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
```
### Citation Information
```
@inproceedings{han-etal-2018-fewrel,
title = "{F}ew{R}el: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation",
author = "Han, Xu and Zhu, Hao and Yu, Pengfei and Wang, Ziyun and Yao, Yuan and Liu, Zhiyuan and Sun, Maosong",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D18-1514",
doi = "10.18653/v1/D18-1514",
pages = "4803--4809"
}
```
```
@inproceedings{gao-etal-2019-fewrel,
title = "{F}ew{R}el 2.0: Towards More Challenging Few-Shot Relation Classification",
author = "Gao, Tianyu and Han, Xu and Zhu, Hao and Liu, Zhiyuan and Li, Peng and Sun, Maosong and Zhou, Jie",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D19-1649",
doi = "10.18653/v1/D19-1649",
pages = "6251--6256"
}
```
### Contributions
Thanks to [@gchhablani](https://github.com/gchhablani) for adding this dataset. |
false |
# Dataset Card for Dynabench.QA
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-instances)
- [Data Splits](#data-instances)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Dynabench.QA](https://dynabench.org/tasks/2#overall)
- **Paper:** [Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension](https://arxiv.org/abs/2002.00293)
- **Leaderboard:** [Dynabench QA Round 1 Leaderboard](https://dynabench.org/tasks/2#overall)
- **Point of Contact:** [Max Bartolo](max.bartolo@ucl.ac.uk)
### Dataset Summary
Dynabench.QA is an adversarially collected Reading Comprehension dataset spanning over multiple rounds of data collect.
For round 1, it is identical to the [adversarialQA dataset](https://adversarialqa.github.io/), where we have created three new Reading Comprehension datasets constructed using an adversarial model-in-the-loop.
We use three different models; BiDAF (Seo et al., 2016), BERT-Large (Devlin et al., 2018), and RoBERTa-Large (Liu et al., 2019) in the annotation loop and construct three datasets; D(BiDAF), D(BERT), and D(RoBERTa), each with 10,000 training examples, 1,000 validation, and 1,000 test examples.
The adversarial human annotation paradigm ensures that these datasets consist of questions that current state-of-the-art models (at least the ones used as adversaries in the annotation loop) find challenging. The three AdversarialQA round 1 datasets provide a training and evaluation resource for such methods.
### Supported Tasks and Leaderboards
`extractive-qa`: The dataset can be used to train a model for Extractive Question Answering, which consists in selecting the answer to a question from a passage. Success on this task is typically measured by achieving a high word-overlap [F1 score](https://huggingface.co/metrics/f1). The [RoBERTa-Large](https://huggingface.co/roberta-large) model trained on all the data combined with [SQuAD](https://arxiv.org/abs/1606.05250) currently achieves 64.35% F1. This task has an active leaderboard and is available as round 1 of the QA task on [Dynabench](https://dynabench.org/tasks/2#overall) and ranks models based on F1 score.
### Languages
The text in the dataset is in English. The associated BCP-47 code is `en`.
## Dataset Structure
### Data Instances
Data is provided in the same format as SQuAD 1.1. An example is shown below:
```
{
"data": [
{
"title": "Oxygen",
"paragraphs": [
{
"context": "Among the most important classes of organic compounds that contain oxygen are (where \"R\" is an organic group): alcohols (R-OH); ethers (R-O-R); ketones (R-CO-R); aldehydes (R-CO-H); carboxylic acids (R-COOH); esters (R-COO-R); acid anhydrides (R-CO-O-CO-R); and amides (R-C(O)-NR2). There are many important organic solvents that contain oxygen, including: acetone, methanol, ethanol, isopropanol, furan, THF, diethyl ether, dioxane, ethyl acetate, DMF, DMSO, acetic acid, and formic acid. Acetone ((CH3)2CO) and phenol (C6H5OH) are used as feeder materials in the synthesis of many different substances. Other important organic compounds that contain oxygen are: glycerol, formaldehyde, glutaraldehyde, citric acid, acetic anhydride, and acetamide. Epoxides are ethers in which the oxygen atom is part of a ring of three atoms.",
"qas": [
{
"id": "22bbe104aa72aa9b511dd53237deb11afa14d6e3",
"question": "In addition to having oxygen, what do alcohols, ethers and esters have in common, according to the article?",
"answers": [
{
"answer_start": 36,
"text": "organic compounds"
}
]
},
{
"id": "4240a8e708c703796347a3702cf1463eed05584a",
"question": "What letter does the abbreviation for acid anhydrides both begin and end in?",
"answers": [
{
"answer_start": 244,
"text": "R"
}
]
},
{
"id": "0681a0a5ec852ec6920d6a30f7ef65dced493366",
"question": "Which of the organic compounds, in the article, contains nitrogen?",
"answers": [
{
"answer_start": 262,
"text": "amides"
}
]
},
{
"id": "2990efe1a56ccf81938fa5e18104f7d3803069fb",
"question": "Which of the important classes of organic compounds, in the article, has a number in its abbreviation?",
"answers": [
{
"answer_start": 262,
"text": "amides"
}
]
}
]
}
]
}
]
}
```
### Data Fields
- title: the title of the Wikipedia page from which the context is sourced
- context: the context/passage
- id: a string identifier for each question
- answers: a list of all provided answers (one per question in our case, but multiple may exist in SQuAD) with an `answer_start` field which is the character index of the start of the answer span, and a `text` field which is the answer text
### Data Splits
For round 1, the dataset is composed of three different datasets constructed using different models in the loop: BiDAF, BERT-Large, and RoBERTa-Large. Each of these has 10,000 training examples, 1,000 validation examples, and 1,000 test examples for a total of 30,000/3,000/3,000 train/validation/test examples.
## Dataset Creation
### Curation Rationale
This dataset was collected to provide a more challenging and diverse Reading Comprehension dataset to state-of-the-art models.
### Source Data
#### Initial Data Collection and Normalization
The source passages are from Wikipedia and are the same as those used in [SQuAD v1.1](https://arxiv.org/abs/1606.05250).
#### Who are the source language producers?
The source language produces are Wikipedia editors for the passages, and human annotators on Mechanical Turk for the questions.
### Annotations
#### Annotation process
The dataset is collected through an adversarial human annotation process which pairs a human annotator and a reading comprehension model in an interactive setting. The human is presented with a passage for which they write a question and highlight the correct answer. The model then tries to answer the question, and, if it fails to answer correctly, the human wins. Otherwise, the human modifies or re-writes their question until the successfully fool the model.
#### Who are the annotators?
The annotators are from Amazon Mechanical Turk, geographically restricted the the USA, UK and Canada, having previously successfully completed at least 1,000 HITs, and having a HIT approval rate greater than 98%. Crowdworkers undergo intensive training and qualification prior to annotation.
### Personal and Sensitive Information
No annotator identifying details are provided.
## Considerations for Using the Data
### Social Impact of Dataset
The purpose of this dataset is to help develop better question answering systems.
A system that succeeds at the supported task would be able to provide an accurate extractive answer from a short passage. This dataset is to be seen as a test bed for questions which contemporary state-of-the-art models struggle to answer correctly, thus often requiring more complex comprehension abilities than say detecting phrases explicitly mentioned in the passage with high overlap to the question.
It should be noted, however, that the the source passages are both domain-restricted and linguistically specific, and that provided questions and answers do not constitute any particular social application.
### Discussion of Biases
The dataset may exhibit various biases in terms of the source passage selection, annotated questions and answers, as well as algorithmic biases resulting from the adversarial annotation protocol.
### Other Known Limitations
N/a
## Additional Information
### Dataset Curators
This dataset was initially created by Max Bartolo, Alastair Roberts, Johannes Welbl, Sebastian Riedel, and Pontus Stenetorp, during work carried out at University College London (UCL).
### Licensing Information
This dataset is distributed under [CC BY-SA 3.0](https://creativecommons.org/licenses/by-sa/3.0/).
### Citation Information
```
@article{bartolo2020beat,
author = {Bartolo, Max and Roberts, Alastair and Welbl, Johannes and Riedel, Sebastian and Stenetorp, Pontus},
title = {Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension},
journal = {Transactions of the Association for Computational Linguistics},
volume = {8},
number = {},
pages = {662-678},
year = {2020},
doi = {10.1162/tacl\_a\_00338},
URL = { https://doi.org/10.1162/tacl_a_00338 },
eprint = { https://doi.org/10.1162/tacl_a_00338 },
abstract = { Innovations in annotation methodology have been a catalyst for Reading Comprehension (RC) datasets and models. One recent trend to challenge current RC models is to involve a model in the annotation process: Humans create questions adversarially, such that the model fails to answer them correctly. In this work we investigate this annotation methodology and apply it in three different settings, collecting a total of 36,000 samples with progressively stronger models in the annotation loop. This allows us to explore questions such as the reproducibility of the adversarial effect, transfer from data collected with varying model-in-the-loop strengths, and generalization to data collected without a model. We find that training on adversarially collected samples leads to strong generalization to non-adversarially collected datasets, yet with progressive performance deterioration with increasingly stronger models-in-the-loop. Furthermore, we find that stronger models can still learn from datasets collected with substantially weaker models-in-the-loop. When trained on data collected with a BiDAF model in the loop, RoBERTa achieves 39.9F1 on questions that it cannot answer when trained on SQuAD—only marginally lower than when trained on data collected using RoBERTa itself (41.0F1). }
}
```
### Contributions
Thanks to [@maxbartolo](https://github.com/maxbartolo) for adding this dataset. |
false |
# Dataset Card for Arabic POS Dialect
## 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://alt.qcri.org/resources/da_resources/
- **Repository:** https://github.com/qcri/dialectal_arabic_resources
- **Paper:** http://www.lrec-conf.org/proceedings/lrec2018/pdf/562.pdf
- **Contacts:**
- Ahmed Abdelali < aabdelali @ hbku dot edu dot qa >
- Kareem Darwish < kdarwish @ hbku dot edu dot qa >
- Hamdy Mubarak < hmubarak @ hbku dot edu dot qa >
### Dataset Summary
This dataset was created to support part of speech (POS) tagging in dialects of Arabic. It contains sets of 350 manually segmented and POS tagged tweets for each of four dialects: Egyptian, Levantine, Gulf, and Maghrebi.
### Supported Tasks and Leaderboards
The dataset can be used to train a model for Arabic token segmentation and part of speech tagging in Arabic dialects. Success on this task is typically measured by achieving a high accuracy over a held out dataset. Darwish et al. (2018) train a CRF model across all four dialects and achieve an average accuracy of 89.3%.
### Languages
The BCP-47 code is ar-Arab. The dataset consists of four dialects of Arabic, Egyptian (EGY), Levantine (LEV), Gulf (GLF), and Maghrebi (MGR), written in Arabic script.
## Dataset Structure
### Data Instances
Below is a partial example from the Egyptian set:
```
- `Fold`: 4
- `SubFold`: A
- `Word`: [ليه, لما, تحب, حد, من, قلبك, ...]
- `Segmentation`: [ليه, لما, تحب, حد, من, قلب+ك, ...]
- `POS`: [PART, PART, V, NOUN, PREP, NOUN+PRON, ...]
```
### Data Fields
The `fold` and the `subfold` fields refer to the crossfold validation splits used by Darwish et al., which can be generated using this [script](https://github.com/qcri/dialectal_arabic_resources/blob/master/generate_splits.sh).
- `fold`: An int32 indicating which fold the instance was in for the crossfold validation
- `subfold`: A string, either 'A' or 'B', indicating which subfold the instance was in for the crossfold validation
- `words`: A sequence of strings of the unsegmented token
- `segments`: A sequence of strings consisting of the segments of the word separated by '+' if there is more than one segment
- `pos_tags`: A sequence of strings of the part of speech tags of the segments separated by '+' if there is more than one segment
The POS tags consist of a set developed by [Darwish et al. (2017)](https://www.aclweb.org/anthology/W17-1316.pdf) for Modern Standard Arabic (MSA) plus an additional 6 tags (2 dialect-specific tags and 4 tweet-specific tags).
| Tag | Purpose | Description |
| ----- | ------ | ----- |
| ADV | MSA | Adverb |
| ADJ | MSA | Adjective |
| CONJ | MSA | Conjunction |
| DET | MSA | Determiner |
| NOUN | MSA | Noun |
| NSUFF | MSA | Noun suffix |
| NUM | MSA | Number |
| PART | MSA | Particle |
| PREP | MSA | Preposition |
| PRON | MSA | Pronoun |
| PUNC | MSA | Preposition |
| V | MSA | Verb |
| ABBREV | MSA | Abbreviation |
| CASE | MSA | Alef of tanween fatha |
| JUS | MSA | Jussification attached to verbs |
| VSUFF | MSA | Verb Suffix |
| FOREIGN | MSA | Non-Arabic as well as non-MSA words |
| FUR_PART | MSA | Future particle "s" prefix and "swf" |
| PROG_PART | Dialect | Progressive particle |
| NEG_PART | Dialect | Negation particle |
| HASH | Tweet | Hashtag |
| EMOT | Tweet | Emoticon/Emoji |
| MENTION | Tweet | Mention |
| URL | Tweet | URL |
### Data Splits
The dataset is split by dialect.
| Dialect | Tweets | Words |
| ----- | ------ | ----- |
| Egyptian (EGY) | 350 | 7481 |
| Levantine (LEV) | 350 | 7221 |
| Gulf (GLF) | 350 | 6767 |
| Maghrebi (MGR) | 350 | 6400 |
## Dataset Creation
### Curation Rationale
This dataset was created to address the lack of computational resources available for dialects of Arabic. These dialects are typically used in speech, while written forms of the language are typically in Modern Standard Arabic. Social media, however, has provided a venue for people to use dialects in written format.
### Source Data
This dataset builds off of the work of [Eldesouki et al. (2017)](https://arxiv.org/pdf/1708.05891.pdf) and [Samih et al. (2017b)](https://www.aclweb.org/anthology/K17-1043.pdf) who originally collected the tweets.
#### Initial Data Collection and Normalization
They started with 175 million Arabic tweets returned by the Twitter API using the query "lang:ar" in March 2014. They then filtered this set using author-identified locations and tokens that are unique to each dialect. Finally, they had native speakers of each dialect select 350 tweets that were heavily accented.
#### Who are the source language producers?
The source language producers are people who posted on Twitter in Arabic using dialectal words from countries where the dialects of interest were spoken, as identified in [Mubarak and Darwish (2014)](https://www.aclweb.org/anthology/W14-3601.pdf).
### Annotations
#### Annotation process
The segmentation guidelines are available at https://alt.qcri.org/resources1/da_resources/seg-guidelines.pdf. The tagging guidelines are not provided, but Darwish at al. note that there were multiple rounds of quality control and revision.
#### Who are the annotators?
The POS tags were annotated by native speakers of each dialect. Further information is not known.
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
Darwish et al find that the accuracy on the Maghrebi dataset suffered the most when the training set was from another dialect, and conversely training on Maghrebi yielded the worst results for all the other dialects. They suggest that Egyptian, Levantine, and Gulf may be more similar to each other and Maghrebi the most dissimilar to all of them. They also find that training on Modern Standard Arabic (MSA) and testing on dialects yielded significantly lower results compared to training on dialects and testing on MSA. This suggests that dialectal variation should be a significant consideration for future work in Arabic NLP applications, particularly when working with social media text.
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
This dataset was curated by Kareem Darwish, Hamdy Mubarak, Mohamed Eldesouki and Ahmed Abdelali with the Qatar Computing Research Institute (QCRI), Younes Samih and Laura Kallmeyer with the University of Dusseldorf, Randah Alharbi and Walid Magdy with the University of Edinburgh, and Mohammed Attia with Google. No funding information was included.
### Licensing Information
This dataset is licensed under the [Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0).
### Citation Information
Kareem Darwish, Hamdy Mubarak, Ahmed Abdelali, Mohamed Eldesouki, Younes Samih, Randah Alharbi, Mohammed Attia, Walid Magdy and Laura Kallmeyer (2018) Multi-Dialect Arabic POS Tagging: A CRF Approach. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), May 7-12, 2018. Miyazaki, Japan.
```
@InProceedings{DARWISH18.562,
author = {Kareem Darwish ,Hamdy Mubarak ,Ahmed Abdelali ,Mohamed Eldesouki ,Younes Samih ,Randah Alharbi ,Mohammed Attia ,Walid Magdy and Laura Kallmeyer},
title = {Multi-Dialect Arabic POS Tagging: A CRF Approach},
booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
year = {2018},
month = {may},
date = {7-12},
location = {Miyazaki, Japan},
editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga},
publisher = {European Language Resources Association (ELRA)},
address = {Paris, France},
isbn = {979-10-95546-00-9},
language = {english}
}
```
### Contributions
Thanks to [@mcmillanmajora](https://github.com/mcmillanmajora) for adding this dataset. |
true |
# Dataset Card for HeadlineCause
## 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://github.com/IlyaGusev/HeadlineCause
- **Paper:** [HeadlineCause: A Dataset of News Headlines for Detecting Causalities](https://arxiv.org/abs/2108.12626)
- **Point of Contact:** [Ilya Gusev](ilya.gusev@phystech.edu)
### Dataset Summary
A dataset for detecting implicit causal relations between pairs of news headlines. The dataset includes over 5000 headline pairs from English news and over 9000 headline pairs from Russian news labeled through crowdsourcing. The pairs vary from totally unrelated or belonging to the same general topic to the ones including causation and refutation relations.
### Usage
Loading Russian Simple task:
```python
from datasets import load_dataset
dataset = load_dataset("IlyaGusev/headline_cause", "ru_simple")
```
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
This dataset consists of two parts, Russian and English.
## Dataset Structure
### Data Instances
There is an URL, a title, and a timestamp for each of the two headlines in every data instance. A label is presented in three fields. 'Result' field is a textual label, 'label' field is a numeric label, and the 'agreement' field shows the majority vote agreement between annotators. Additional information includes instance ID and the presence of the link between two articles.
```
{
'left_url': 'https://www.kommersant.ru/doc/4347456',
'right_url': 'https://tass.ru/kosmos/8488527',
'left_title': 'NASA: информация об отказе сотрудничать с Россией по освоению Луны некорректна',
'right_title': 'NASA назвало некорректными сообщения о нежелании США включать РФ в соглашение по Луне',
'left_timestamp': datetime.datetime(2020, 5, 15, 19, 46, 20),
'right_timestamp': datetime.datetime(2020, 5, 15, 19, 21, 36),
'label': 0,
'result': 'not_cause',
'agreement': 1.0,
'id': 'ru_tg_101',
'has_link': True
}
```
### Data Splits
| Dataset | Split | Number of Instances |
|:---------|:---------|:---------|
| ru_simple | train | 7,641 |
| | validation | 955 |
| | test | 957 |
| en_simple | train | 4,332 |
| | validation | 542 |
| | test | 542 |
| ru_full | train | 5,713 |
| | validation | 715 |
| | test | 715 |
| en_full | train | 2,009 |
| | validation | 251 |
| | test | 252 |
## 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
Every candidate pair was annotated with [Yandex Toloka](https://toloka.ai/), a crowdsourcing platform. The task was to determine a relationship between two headlines, A and B. There were seven possible options: titles are almost the same, A causes B, B causes A, A refutes B, B refutes A, A linked with B in another way, A is not linked to B. An annotation guideline was in Russian for Russian news and in English for English news.
Guidelines:
* Russian: [link](https://ilyagusev.github.io/HeadlineCause/toloka/ru/instruction.html)
* English: [link](https://ilyagusev.github.io/HeadlineCause/toloka/en/instruction.html)
Ten workers annotated every pair. The total annotation budget was 870$, with the estimated hourly wage paid to participants of 45 cents. Annotation management was semi-automatic. Scripts are available in the [Github repository](https://github.com/IlyaGusev/HeadlineCause).
#### Who are the annotators?
Yandex Toloka workers were the annotators, 457 workers for the Russian part, 180 workers for the English part.
### Personal and Sensitive Information
The dataset is not anonymized, so individuals' names can be found in the dataset. Information about the original author is not included in the dataset. No information about annotators is included except a platform worker ID.
## Considerations for Using the Data
### Social Impact of Dataset
We do not see any direct malicious applications of our work. The data probably do not contain offensive content, as news agencies usually do not produce it, and a keyword search returned nothing. However, there are news documents in the dataset on several sensitive topics.
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
The data was collected by Ilya Gusev.
### Licensing Information
[More Information Needed]
### Citation Information
```bibtex
@misc{gusev2021headlinecause,
title={HeadlineCause: A Dataset of News Headlines for Detecting Causalities},
author={Ilya Gusev and Alexey Tikhonov},
year={2021},
eprint={2108.12626},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
### Contributions
[N/A] |
true |
# Dataset Card for DBRD
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** [Dutch Book Review Dataset (DBRD) homepage](https://benjaminvdb.github.io/DBRD)
- **Repository:** https://github.com/benjaminvdb/DBRD
- **Paper:** [The merits of Universal Language Model Fine-tuning for Small Datasets - a case with Dutch book reviews](https://arxiv.org/abs/1910.00896)
- **Leaderboard:**
- **Point of Contact:** [Benjamin van der Burgh](mailto:benjaminvdb@gmail.com)
### Dataset Summary
The DBRD (pronounced *dee-bird*) dataset contains over 110k book reviews of which 22k have associated binary sentiment polarity labels. It is intended as a benchmark for sentiment classification in Dutch and was created due to a lack of annotated datasets in Dutch that are suitable for this task.
### Supported Tasks and Leaderboards
- `text-generation`: The dataset can be used to train a model for sequence modeling, more specifically language modeling.
- `text-classification`: The dataset can be used to train a model for text classification, more specifically sentiment classification, using the provided positive/negative sentiment polarity labels.
### Languages
Non-Dutch reviews were filtered out using [langdetect](https://github.com/Mimino666/langdetect), and all reviews should therefore be in Dutch (nl). They are written by reviewers on [Hebban](https://www.hebban.nl), a Dutch website for book reviews.
## Dataset Structure
### Data Instances
The dataset contains three subsets: train, test, and unsupervised. The `train` and `test` sets contain labels, while the `unsupervised` set doesn't (the label value is -1 for each instance in `unsupervised`). Here's an example of a positive review, indicated with a label value of `1`.
```
{
'label': 1,
'text': 'Super om te lezen hoe haar leven is vergaan.\nBijzonder dat ze zo openhartig is geweest.'
}
```
### Data Fields
- `label`: either 0 (negative) or 1 (positive) in the supervised sets `train` and `test`. These are always -1 for the unsupervised set.
- `text`: book review as a utf-8 encoded string.
### Data Splits
The `train` and `test` sets were constructed by extracting all non-neutral reviews because we want to assign either a positive or negative polarity label to each instance. Furthermore, the positive (pos) and negative (neg) labels were balanced in both train and test sets. The remainder was added to the unsupervised set.
| | Train | Test | Unsupervised |
| ----- | ------ | ----- | ----------- |
| # No. texts | 20028 | 2224 | 96264 |
| % of total | 16.9% | 1.9% | 81.2% |
## Dataset Creation
### Curation Rationale
This dataset was created due to a lack of annotated Dutch text that is suitable for sentiment classification. Non-Dutch texts were therefore removed, but other than that, no curation was done.
### Source Data
The book reviews were taken from [Hebban](https://www.hebban.nl), a Dutch platform for book reviews.
#### Initial Data Collection and Normalization
The source code of the scraper and preprocessing process can be found in the [DBRD GitHub repository](https://github.com/benjaminvdb/DBRD).
#### Who are the source language producers?
The reviews are written by users of [Hebban](https://www.hebban.nl) and are of varying quality. Some are short, others long, and many contain spelling mistakes and other errors.
### Annotations
Each book review was accompanied by a 1 to 5-star rating. The annotations are produced by mapping the user-provided ratings to either a positive or negative label. 1 and 2-star ratings are given the negative label `0` and 4 and 5-star ratings the positive label `1`. Reviews with a rating of 3 stars are considered neutral and left out of the `train`/`test` sets and added to the unsupervised set.
#### Annotation process
Users of [Hebban](https://www.hebban.nl) were unaware that their reviews would be used in the creation of this dataset.
#### Who are the annotators?
The annotators are the [Hebban](https://www.hebban.nl) users who wrote the book reviews associated with the annotation. Anyone can register on [Hebban](https://www.hebban.nl) and it's impossible to know the demographics of this group.
### Personal and Sensitive Information
The book reviews and ratings are publicly available on [Hebban](https://www.hebban.nl) and no personal or otherwise sensitive information is contained in this dataset.
## Considerations for Using the Data
### Social Impact of Dataset
While predicting sentiment of book reviews in itself is not that interesting, the value of this dataset lies in its usage for benchmarking models. The dataset contains some challenges that are common to outings on the internet, such as spelling mistakes and other errors. It is therefore very useful for validating models for their real-world performance. These datasets are abundant for English but are harder to find for Dutch, making them a valuable resource for ML tasks in this language.
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
Reviews on [Hebban](https://www.hebban.nl) are usually written in Dutch, but some have been written in English and possibly in other languages. While we've done our best to filter out non-Dutch texts, it's hard to do this without errors. For example, some reviews are in multiple languages, and these might slip through. Also be aware that some commercial outings can appear in the text, making them different from other reviews and influencing your models. While this doesn't pose a major issue in most cases, we just wanted to mention it briefly.
## Additional Information
### Dataset Curators
This dataset was created by [Benjamin van der Burgh](mailto:benjaminvdb@gmail.com), who was working at [Leiden Institute of Advanced Computer Science (LIACS)](https://liacs.leidenuniv.nl/) at the time.
### Licensing Information
The dataset is licensed under a [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-nc-sa/4.0/).
### Citation Information
Please use the following citation when making use of this dataset in your work.
```
@article{DBLP:journals/corr/abs-1910-00896,
author = {Benjamin van der Burgh and
Suzan Verberne},
title = {The merits of Universal Language Model Fine-tuning for Small Datasets
- a case with Dutch book reviews},
journal = {CoRR},
volume = {abs/1910.00896},
year = {2019},
url = {http://arxiv.org/abs/1910.00896},
archivePrefix = {arXiv},
eprint = {1910.00896},
timestamp = {Fri, 04 Oct 2019 12:28:06 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-00896.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
### Contributions
Thanks to [@benjaminvdb](https://github.com/benjaminvdb) for adding this dataset. |
false |
# Dataset Card for StaQC (A Systematically Mined Question-Code Dataset from Stack Overflow)
## Dataset Description
- **Homepage: [GitHub](https://github.com/LittleYUYU/StackOverflow-Question-Code-Dataset)**
- **Paper: [StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow](https://arxiv.org/abs/1803.09371)**
### Dataset Summary
StaQC (Stack Overflow Question-Code pairs) is a large dataset of around 148K Python and 120K SQL domain question-code pairs,
which are automatically mined from Stack Overflow using a Bi-View Hierarchical Neural Network. StaQC is collected from three sources: multi-code answer posts, single-code answer posts, and manual annotations on multi-code answer posts.
The dataset was originally released by the main authors on [GitHub](https://github.com/LittleYUYU/StackOverflow-Question-Code-Dataset). This version is a *non-modified* redistributed copy (under the [license](#licensing-information) permission) made available on the hub for easier access.
#### Standalone solutions
As noted in the paper, the authors *define a code snippet as a code solution when the
questioner can solve the problem solely based on it (also named as
“standalone” solution).*
#### Manual annotations
The manual annotations are the collection of multi-code answer posts for which each code snippet was annotated with a boolean indicating whether or not the snippet is a *standalone solution* to the question.
#### Multi-code answer posts
A *Multi-code answer post* is an (accepted) answer post that contains multiple code snippets,
some of which may not be a *standalone* code solution to the question (see Section 1 in [paper](http://web.cse.ohio-state.edu/~sun.397/docs/StaQC-www18.pdf)).
For example, in [this multi-code answer post](https://stackoverflow.com/a/5996949),
the third code snippet is not a code solution to the question "How to limit a number to be within a specified range? (Python)".
Note: the multi-code answer posts contain also the manual annotations.
#### Single-code answer posts
A *Single-code answer post* is an (accepted) answer post that contains only one code snippet.
We pair such code snippets with the question title as a question-code pair.
### Supported Tasks and Leaderboards
This dataset can be used for Natural Language to Code Generation tasks.
### Languages
Python, SQL, English
## Dataset Structure
### Data Instances
Each configuration correspond to one of the three parts, in a given programming language.
There are three parts for the dataset:
- mca (Multi-code answer posts)
- sca (Single-code answer posts)
- man (Manual annotations)
And two programming/query languages:
- python
- sql
One can obtain obtain a configuration as a combination of a part in a programing language. For instance, one can obtain the automatically mined multi-code answers in python using:
```python
dataset = load_dataset("koutch/staqc", 'mca_python')
DatasetDict({
train: Dataset({
features: ['id', 'question_id', 'question', 'snippet'],
num_rows: 40391
})
})
```
or the manual annotations using:
```python
dataset = load_dataset("koutch/staqc", 'man_sql')
DatasetDict({
train: Dataset({
features: ['id', 'question_id', 'question', 'snippet'],
num_rows: 1587
})
})
```
#### Manual annotations
The manual annotations contain, for a given stackoverflow questions, for each individual code block in the accepted answer of that post, information on whether or not the given code block is a *standalone* solution to the question asked (the question title).
```
{
'question_id': 5947137,
'question': 'How can I use a list comprehension to extend a list in python?',
'snippet': {'text': ['import itertools as it\n\nreturn sum(it.imap(doSomething, originalList), [])\n',
'return sum(map(doSomething, originalList), [])\n',
'return sum((doSomething(x) for x in originalList), [])\n',
'accumulationList = []\nfor x in originalList:\n accumulationList.extend(doSomething(x))\nreturn accumulationList\n'],
'is_sda': [True, True, True, True]}
}
```
#### Multi-code answer posts
```
{
'question_id': 35349290,
'question': 'Python: Generating YYMM string between two dates',
'snippet': ['start_year = 2005\nend_year = 2007\nstart_month = 3\nend_month = 2\nyymm = [(yy, mm) for yy in range(start_year, end_year + 1) for mm in range(1, 13)\n if (start_year, start_month) <= (yy, mm) <= (end_year, end_month)]\n',
"formatted_yymm = ['{:>02}{:>02}.mat'.format(yy % 100, mm) for yy, mm in yymm]\n"]
}
```
#### Single-code answer posts
```
{
'question_id': 19387200,
'question': 'Python: get OS language',
'snippet': "import locale\nloc = locale.getlocale() # get current locale\nlocale.getdefaultlocale() # Tries to determine the default locale settings and returns them as a tuple of the form (language code, encoding); e.g, ('en_US', 'UTF-8').\n"
}
```
### Data Fields
- `question_id`: id of the stackoverflow question
- `question`: title of the stackoverflow question repurposed as the natural language intent
- `snippet`: mined or annotated standalone solution(s) (potentially) answerring the question
- `is_sda`: for the manual annotations, whether or not the given code snippet is a standalone solution to the question.
### Data Splits
Each configuration of the dataset contains only a training split.
## Dataset Creation
### Source Data
StackOverflow data dump.
### Annotations
See section 2.3 "Annotating QC Pairs for Model Training" of the [paper](https://arxiv.org/abs/1803.09371)
## Additional Information
### Licensing Information
<a rel="license" href="http://creativecommons.org/licenses/by/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a>.
### Citation Information
If you use the dataset or the code in your research, please cite the following paper:
```
@inproceedings{yao2018staqc,
title={StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow},
author={Yao, Ziyu and Weld, Daniel S and Chen, Wei-Peng and Sun, Huan},
booktitle={Proceedings of the 2018 World Wide Web Conference on World Wide Web},
pages={1693--1703},
year={2018},
organization={International World Wide Web Conferences Steering Committee}
}
```
### Contributions information
I did *not* contribute to the *creation* of this dataset, only to the redistribution. All credits should be attributed to the original authors. |
false |
# Dataset Card for "arcd"
## 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/husseinmozannar/SOQAL/tree/master/data](https://github.com/husseinmozannar/SOQAL/tree/master/data)
- **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
- **Size of downloaded dataset files:** 1.94 MB
- **Size of the generated dataset:** 1.70 MB
- **Total amount of disk used:** 3.64 MB
### Dataset Summary
Arabic Reading Comprehension Dataset (ARCD) composed of 1,395 questions posed by crowdworkers on Wikipedia articles.
### Supported Tasks and Leaderboards
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Languages
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Dataset Structure
### Data Instances
#### plain_text
- **Size of downloaded dataset files:** 1.94 MB
- **Size of the generated dataset:** 1.70 MB
- **Total amount of disk used:** 3.64 MB
An example of 'train' looks as follows.
```
This example was too long and was cropped:
{
"answers": "{\"answer_start\": [34], \"text\": [\"صحابي من صحابة رسول الإسلام محمد، وعمُّه وأخوه من الرضاعة وأحد وزرائه الأربعة عشر،\"]}...",
"context": "\"حمزة بن عبد المطلب الهاشمي القرشي صحابي من صحابة رسول الإسلام محمد، وعمُّه وأخوه من الرضاعة وأحد وزرائه الأربعة عشر، وهو خير أع...",
"id": "621723207492",
"question": "من هو حمزة بن عبد المطلب؟",
"title": "حمزة بن عبد المطلب"
}
```
### Data Fields
The data fields are the same among all splits.
#### plain_text
- `id`: a `string` feature.
- `title`: a `string` feature.
- `context`: a `string` feature.
- `question`: a `string` feature.
- `answers`: a dictionary feature containing:
- `text`: a `string` feature.
- `answer_start`: a `int32` feature.
### Data Splits
| name | train | validation |
| ---------- | ----: | ---------: |
| plain_text | 693 | 702 |
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
```
@inproceedings{mozannar-etal-2019-neural,
title = "Neural {A}rabic Question Answering",
author = "Mozannar, Hussein and
Maamary, Elie and
El Hajal, Karl and
Hajj, Hazem",
booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/W19-4612",
doi = "10.18653/v1/W19-4612",
pages = "108--118",
abstract = "This paper tackles the problem of open domain factual Arabic question answering (QA) using Wikipedia as our knowledge source. This constrains the answer of any question to be a span of text in Wikipedia. Open domain QA for Arabic entails three challenges: annotated QA datasets in Arabic, large scale efficient information retrieval and machine reading comprehension. To deal with the lack of Arabic QA datasets we present the Arabic Reading Comprehension Dataset (ARCD) composed of 1,395 questions posed by crowdworkers on Wikipedia articles, and a machine translation of the Stanford Question Answering Dataset (Arabic-SQuAD). Our system for open domain question answering in Arabic (SOQAL) is based on two components: (1) a document retriever using a hierarchical TF-IDF approach and (2) a neural reading comprehension model using the pre-trained bi-directional transformer BERT. Our experiments on ARCD indicate the effectiveness of our approach with our BERT-based reader achieving a 61.3 F1 score, and our open domain system SOQAL achieving a 27.6 F1 score.",
}
```
### Contributions
Thanks to [@albertvillanova](https://github.com/albertvillanova), [@lewtun](https://github.com/lewtun), [@mariamabarham](https://github.com/mariamabarham), [@thomwolf](https://github.com/thomwolf), [@tayciryahmed](https://github.com/tayciryahmed) for adding this dataset. |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.