{
 "id": "castorini/wura",
 "owner": "castorini",
 "name": "wura",
 "downloads": 877,
 "likes": 15,
 "last_modified": "2023-12-11T16:06:49.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@inproceedings{oladipo-etal-2023-better,\n    title = \"Better Quality Pre-training Data and T5 Models for {A}frican Languages\",\n    author = \"Oladipo, Akintunde  and\n      Adeyemi, Mofetoluwa  and\n      Ahia, Orevaoghene  and\n      Owodunni, Abraham  and\n      Ogundepo, Odunayo  and\n      Adelani, David  and\n      Lin, Jimmy\",\n    editor = \"Bouamor, Houda  and\n      Pino, Juan  and\n      Bali, Kalika\",\n    booktitle = \"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing\",\n    month = dec,\n    year = \"2023\",\n    address = \"Singapore\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.emnlp-main.11\",\n    pages = \"158--168\",\n    abstract = \"In this study, we highlight the importance of enhancing the quality of pretraining data in multilingual language models. Existing web crawls have demonstrated quality issues, particularly in the context of low-resource languages. Consequently, we introduce a new multilingual pretraining corpus for 16 African languages, designed by carefully auditing existing pretraining corpora to understand and rectify prevalent quality issues. To compile this dataset, we undertake a rigorous examination of current data sources for thirteen languages within one of the most extensive multilingual web crawls, mC4, and extract cleaner data through meticulous auditing and improved web crawling strategies. Subsequently, we pretrain a new T5-based model on this dataset and evalua",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "1d4bcb87775ff906c19c01a42a3190cd43ca3742",
 "stated_evidence": "https://huggingface.co/datasets/castorini/wura/blob/1d4bcb87775ff906c19c01a42a3190cd43ca3742/README.md",
 "file_evidence": "https://huggingface.co/datasets/castorini/wura/tree/1d4bcb87775ff906c19c01a42a3190cd43ca3742",
 "card_nc": false
}