{
 "id": "oscar-corpus/oscar-2301-hpc",
 "owner": "oscar-corpus",
 "name": "oscar-2301-hpc",
 "downloads": 9,
 "likes": 7,
 "last_modified": "2023-04-18T09:10:18.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "fill-mask",
  "text-generation"
 ],
 "citation": "@ARTICLE{2022arXiv221210440J,\n       author = {{Jansen}, Tim and {Tong}, Yangling and {Zevallos}, Victoria and {Ortiz Suarez}, Pedro},\n        title = \"{Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web Data}\",\n      journal = {arXiv e-prints},\n     keywords = {Computer Science - Computation and Language},\n         year = 2022,\n        month = dec,\n          eid = {arXiv:2212.10440},\n        pages = {arXiv:2212.10440},\n          doi = {10.48550/arXiv.2212.10440},\narchivePrefix = {arXiv},\n       eprint = {2212.10440},\n primaryClass = {cs.CL},\n       adsurl = {https://ui.adsabs.harvard.edu/abs/2022arXiv221210440J},\n      adsnote = {Provided by the SAO/NASA Astrophysics Data System}\n}\n\n@inproceedings{abadji-etal-2022-towards,\n    title = \"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus\",\n    author = \"Abadji, Julien  and\n      Ortiz Suarez, Pedro  and\n      Romary, Laurent  and\n      Sagot, Beno{\\^\\i}t\",\n    booktitle = \"Proceedings of the Thirteenth Language Resources and Evaluation Conference\",\n    month = jun,\n    year = \"2022\",\n    address = \"Marseille, France\",\n    publisher = \"European Language Resources Association\",\n    url = \"https://aclanthology.org/2022.lrec-1.463\",\n    pages = \"4344--4355\",\n    abstract = \"The need for large corpora raw corpora has dramatically increased in recent years with the introduction of transfer learning and semi-supervised learning methods to Natural Lang",
 "signal": "permissive",
 "reason": "The declared licence (cc0-1.0) is classified as permissive.",
 "revision": "7f17d6e8954a6466b12248dd29582f67a330431f",
 "stated_evidence": "https://huggingface.co/datasets/oscar-corpus/oscar-2301-hpc/blob/7f17d6e8954a6466b12248dd29582f67a330431f/README.md",
 "file_evidence": "https://huggingface.co/datasets/oscar-corpus/oscar-2301-hpc/tree/7f17d6e8954a6466b12248dd29582f67a330431f",
 "card_nc": false
}