{
 "id": "mteb/FloresBitextMining",
 "owner": "mteb",
 "name": "FloresBitextMining",
 "downloads": 681,
 "likes": 1,
 "last_modified": "2026-03-05T12:46:36.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [
  {
   "id": "mteb/flores",
   "licence": "cc-by-sa-4.0",
   "found": true,
   "evidence": "https://huggingface.co/datasets/mteb/flores/blob/69edd3336d102dd184dd531b57defac6c9c60c8f/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "translation"
 ],
 "citation": "@inproceedings{goyal2022flores,\n  author = {Goyal, Naman and Gao, Cynthia and Chaudhary, Vishrav and Chen, Peng-Jen and Wenzek, Guillaume and Ju, Da and Krishnan, Sanjana and Ranzato, Marc'Aurelio and Guzm{\\'a}n, Francisco},\n  booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},\n  pages = {19--35},\n  title = {The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation},\n  year = {2022},\n}\n\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n  title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Micha",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "863ac039b06990daec7190e6af00ea12ec854cfa",
 "stated_evidence": "https://huggingface.co/datasets/mteb/FloresBitextMining/blob/863ac039b06990daec7190e6af00ea12ec854cfa/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/FloresBitextMining/tree/863ac039b06990daec7190e6af00ea12ec854cfa",
 "card_nc": false
}