{
 "id": "SEACrowd/cc100",
 "owner": "SEACrowd",
 "name": "cc100",
 "downloads": 129,
 "likes": 3,
 "last_modified": "2024-06-24T13:27:18.000Z",
 "stated_licence": null,
 "stated_from": "none",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "self-supervised-pretraining"
 ],
 "citation": "@inproceedings{conneau-etal-2020-unsupervised,\n    title = \"Unsupervised Cross-lingual Representation Learning at Scale\",\n    author = \"Conneau, Alexis  and\n      Khandelwal, Kartikay  and\n      Goyal, Naman  and\n      Chaudhary, Vishrav  and\n      Wenzek, Guillaume  and\n      Guzm{'a}n, Francisco  and\n      Grave, Edouard  and\n      Ott, Myle  and\n      Zettlemoyer, Luke  and\n      Stoyanov, Veselin\",\n    booktitle = \"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics\",\n    month = jul,\n    year = \"2020\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://www.aclweb.org/anthology/2020.acl-main.747\",\n    doi = \"10.18653/v1/2020.acl-main.747\",\n    pages = \"8440--8451\",\n    abstract = \"This paper shows that pretraining multilingual language models\n    at scale leads to significant performance gains for a wide range of\n    cross-lingual transfer tasks. We train a Transformer-based masked language\n    model on one hundred languages, using more than two terabytes of filtered\n    CommonCrawl data. Our model, dubbed XLM-R, significantly outperforms\n    multilingual BERT (mBERT) on a variety of cross-lingual benchmarks,\n    including +14.6{%} average accuracy on XNLI, +13{%} average F1 score on\n    MLQA, and +2.4{%} F1 score on NER. XLM-R performs particularly well on\n    low-resource languages, improving 15.7{%} in XNLI accuracy for Swahili and\n    11.4{%} for Urdu over previous XLM models. We ",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "b9c955b6b45251d079869cc63ac508f9deb8abb9",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/cc100/blob/b9c955b6b45251d079869cc63ac508f9deb8abb9/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/cc100/blob/b9c955b6b45251d079869cc63ac508f9deb8abb9/LICENSE",
 "card_nc": false
}