{
 "id": "SEACrowd/ccmatrix",
 "owner": "SEACrowd",
 "name": "ccmatrix",
 "downloads": 80,
 "likes": 0,
 "last_modified": "2024-06-24T13:23:40.000Z",
 "stated_licence": "bsd",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "machine-translation"
 ],
 "citation": "@inproceedings{schwenk-etal-2021-ccmatrix,\n    title = \"{CCM}atrix: Mining Billions of High-Quality Parallel Sentences on the Web\",\n    author = \"Schwenk, Holger  and\n      Wenzek, Guillaume  and\n      Edunov, Sergey  and\n      Grave, Edouard  and\n      Joulin, Armand  and\n      Fan, Angela\",\n    editor = \"Zong, Chengqing  and\n      Xia, Fei  and\n      Li, Wenjie  and\n      Navigli, Roberto\",\n    booktitle = \"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)\",\n    month = aug,\n    year = \"2021\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2021.acl-long.507\",\n    doi = \"10.18653/v1/2021.acl-long.507\",\n    pages = \"6490--6500\",\n    abstract = \"We show that margin-based bitext mining in a multilingual sentence space can be successfully scaled to operate on monolingual corpora of billions of sentences. We use 32 snapshots of a curated common crawl corpus (Wenzel et al, 2019) totaling 71 billion unique sentences. Using one unified approach for 90 languages, we were able to mine 10.8 billion parallel sentences, out of which only 2.9 billions are aligned with English. We illustrate the capability of our scalable mining system to create high quality training sets from one language to any other by training hundreds of different machine translation models and evaluating them ",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "b7164d1b6483d1e064a1a102ba9147d4facdd91e",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/ccmatrix/blob/b7164d1b6483d1e064a1a102ba9147d4facdd91e/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/ccmatrix/blob/b7164d1b6483d1e064a1a102ba9147d4facdd91e/LICENSE",
 "card_nc": false
}