{
 "id": "mteb/NusaTranslationBitextMining",
 "owner": "mteb",
 "name": "NusaTranslationBitextMining",
 "downloads": 356,
 "likes": 1,
 "last_modified": "2025-05-07T19:42:08.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation"
 ],
 "citation": "@inproceedings{cahyawijaya2023nusawrites,\n  author = {Cahyawijaya, Samuel and Lovenia, Holy and Koto, Fajri and Adhista, Dea and Dave, Emmanuel and Oktavianti, Sarah and Akbar, Salsabil and Lee, Jhonson and Shadieq, Nuur and Cenggoro, Tjeng Wawan and others},\n  booktitle = {Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},\n  pages = {921--945},\n  title = {NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages},\n  year = {2023},\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 Konr",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "d08eca02c75a0b2ea9bfaaed1e42b7679588fa59",
 "stated_evidence": "https://huggingface.co/datasets/mteb/NusaTranslationBitextMining/blob/d08eca02c75a0b2ea9bfaaed1e42b7679588fa59/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/NusaTranslationBitextMining/tree/d08eca02c75a0b2ea9bfaaed1e42b7679588fa59",
 "card_nc": false
}