{
 "id": "eherra/MuPLeR-retrieval",
 "owner": "eherra",
 "name": "MuPLeR-retrieval",
 "downloads": 156,
 "likes": 2,
 "last_modified": "2026-04-15T19:26:11.000Z",
 "stated_licence": "eupl-1.2",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@article{steinberger2014overview,\n  author = {Steinberger, Ralf and Ebrahim, Mohamed and Poulis, Alexandros and {Carrasco-Benitez}, Manuel and Schl{\\\"u}ter, Patrick and Przybyszewski, Marek and Gilbro, Signe},\n  doi = {10.1007/s10579-014-9277-0},\n  issn = {1574-0218},\n  journal = {Language Resources and Evaluation},\n  keywords = {DCEP,DGT-Acquis,DGT-TM,EAC-TM,ECDC-TM,Eur-Lex,European Union,EuroVoc,Highly multilingual,JRC EuroVoc Indexer JEX,JRC-Acquis,Linguistic resources,Parallel corpora,Translation memory},\n  langid = {english},\n  language = {en},\n  month = dec,\n  number = {4},\n  pages = {679--707},\n  title = {An Overview of the {{European Union}}'s Highly Multilingual Parallel Corpora},\n  urldate = {2026-03-29},\n  volume = {48},\n  year = {2014},\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 Isabe",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "5b011e904f56d91e6ee8855000f4496bacf0d0b5",
 "stated_evidence": "https://huggingface.co/datasets/eherra/MuPLeR-retrieval/blob/5b011e904f56d91e6ee8855000f4496bacf0d0b5/README.md",
 "file_evidence": "https://huggingface.co/datasets/eherra/MuPLeR-retrieval/tree/5b011e904f56d91e6ee8855000f4496bacf0d0b5",
 "card_nc": false
}