{
 "id": "SEACrowd/oscar_2201",
 "owner": "SEACrowd",
 "name": "oscar_2201",
 "downloads": 48,
 "likes": 0,
 "last_modified": "2024-06-24T13:30:05.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc0-1.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "self-supervised-pretraining"
 ],
 "citation": "@inproceedings{abadji2022cleaner,\n    author    = {Julien Abadji and\n                Pedro Javier Ortiz Su{'{a}}rez and\n                Laurent Romary and\n                Beno{\\^{\\i}}t Sagot},\n    title     = {Towards a Cleaner Document-Oriented Multilingual Crawled Corpus},\n    booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference,\n                {LREC} 2022, Marseille, France, 20-25 June 2022},\n    pages     = {4344--4355},\n    publisher = {European Language Resources Association},\n    year      = {2022},\n    url       = {https://aclanthology.org/2022.lrec-1.463},\n}\n\n@inproceedings{abadji2021ungoliant,\n    author    = {Julien Abadji and\n                Pedro Javier Ortiz Su{'a}rez and\n                Laurent Romary and\n                Beno{\\^i}t Sagot},\n    title     = {Ungoliant: An optimized pipeline for the generation of a very large-scale multilingual web corpus},\n    series    = {Proceedings of the Workshop on Challenges in the Management of Large Corpora\n                (CMLC-9) 2021. Limerick, 12 July 2021 (Online-Event)},\n    editor    = {Harald L{\"u}ngen and\n                Marc Kupietz and\n                Piotr Bański and\n                Adrien Barbaresi and\n                Simon Clematide and\n                Ines Pisetta},\n    publisher = {Leibniz-Institut f{\"u}r Deutsche Sprache},\n    address   = {Mannheim},\n    doi       = {10.14618/ids-pub-10468},\n    url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104688},\n    pag",
 "signal": "permissive",
 "reason": "The declared licence (cc0-1.0) is classified as permissive.",
 "revision": "6d0e5b07b10228eaaf08ab49369ddc46229a5018",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/oscar_2201/blob/6d0e5b07b10228eaaf08ab49369ddc46229a5018/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/oscar_2201/blob/6d0e5b07b10228eaaf08ab49369ddc46229a5018/LICENSE",
 "card_nc": false
}