{
 "id": "statmt/cc100",
 "owner": "statmt",
 "name": "cc100",
 "downloads": 985,
 "likes": 107,
 "last_modified": "2024-03-05T12:15:34.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "fill-mask"
 ],
 "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    editor = \"Jurafsky, Dan  and\n      Chai, Joyce  and\n      Schluter, Natalie  and\n      Tetreault, Joel\",\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://aclanthology.org/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 at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer-based masked language model on one hundred languages, using more than two terabytes of filtered CommonCrawl data. Our model, dubbed XLM-R, significantly outperforms multilingual BERT (mBERT) on a variety of cross-lingual benchmarks, including +14.6{\\%} average accuracy on XNLI, +13{\\%} average F1 score on MLQA, and +2.4{\\%} F1 score on NER. XLM-R performs particularly well on low-resource languages, improving 15.7{\\%} in XNLI a",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "8c658c983d32eab9170d77d416252cfaa0c23e96",
 "stated_evidence": "https://huggingface.co/datasets/statmt/cc100/blob/8c658c983d32eab9170d77d416252cfaa0c23e96/README.md",
 "file_evidence": "https://huggingface.co/datasets/statmt/cc100/tree/8c658c983d32eab9170d77d416252cfaa0c23e96",
 "card_nc": false
}