{
 "id": "SEACrowd/wikimatrix",
 "owner": "SEACrowd",
 "name": "wikimatrix",
 "downloads": 76,
 "likes": 1,
 "last_modified": "2024-06-24T13:24:20.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-sa-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "machine-translation"
 ],
 "citation": "@inproceedings{schwenk-etal-2021-wikimatrix,\n    title = \"{W}iki{M}atrix: Mining 135{M} Parallel Sentences in 1620 Language Pairs from {W}ikipedia\",\n    author = \"Schwenk, Holger  and\n      Chaudhary, Vishrav  and\n      Sun, Shuo  and\n      Gong, Hongyu  and\n      Guzm{'a}n, Francisco\",\n    editor = \"Merlo, Paola  and\n      Tiedemann, Jorg  and\n      Tsarfaty, Reut\",\n    booktitle = \"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume\",\n    month = apr,\n    year = \"2021\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2021.eacl-main.115\",\n    doi = \"10.18653/v1/2021.eacl-main.115\",\n    pages = \"1351--1361\",\n    abstract = \"We present an approach based on multilingual sentence embeddings to automatically extract parallel sentences from the content\n    of Wikipedia articles in 96 languages, including several dialects or low-resource languages. We do not limit the extraction process to\n    alignments with English, but we systematically consider all possible language pairs. In total, we are able to extract 135M parallel sentences\n    for 16720 different language pairs, out of which only 34M are aligned with English. This corpus is freely available. To get an indication\n    on the quality of the extracted bitexts, we train neural MT baseline systems on the mined data only for 1886 languages pairs, and evaluate\n    them on the TED corpus, ac",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "e93e74bd02177656696c4864b0fee6d5902a4c56",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/wikimatrix/blob/e93e74bd02177656696c4864b0fee6d5902a4c56/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/wikimatrix/blob/e93e74bd02177656696c4864b0fee6d5902a4c56/LICENSE",
 "card_nc": false
}