{
 "id": "mteb/IndicLangClassification",
 "owner": "mteb",
 "name": "IndicLangClassification",
 "downloads": 282,
 "likes": 0,
 "last_modified": "2025-05-06T12:28:41.000Z",
 "stated_licence": "cc0-1.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{madhani-etal-2023-bhasa,\n  address = {Toronto, Canada},\n  author = {Madhani, Yash  and\nKhapra, Mitesh M.  and\nKunchukuttan, Anoop},\n  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},\n  doi = {10.18653/v1/2023.acl-short.71},\n  editor = {Rogers, Anna  and\nBoyd-Graber, Jordan  and\nOkazaki, Naoaki},\n  month = jul,\n  pages = {816--826},\n  publisher = {Association for Computational Linguistics},\n  title = {Bhasa-Abhijnaanam: Native-script and romanized Language Identification for 22 {I}ndic languages},\n  url = {https://aclanthology.org/2023.acl-short.71},\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 ",
 "signal": "permissive",
 "reason": "The declared licence (cc0-1.0) is classified as permissive.",
 "revision": "36d9c05b5a4ba276554abc4eaaae87666d1e9c61",
 "stated_evidence": "https://huggingface.co/datasets/mteb/IndicLangClassification/blob/36d9c05b5a4ba276554abc4eaaae87666d1e9c61/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/IndicLangClassification/tree/36d9c05b5a4ba276554abc4eaaae87666d1e9c61",
 "card_nc": false
}