{
 "id": "mteb/NordicLangClassification",
 "owner": "mteb",
 "name": "NordicLangClassification",
 "downloads": 606,
 "likes": 0,
 "last_modified": "2026-02-24T21:18:27.000Z",
 "stated_licence": "cc-by-sa-3.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{haas-derczynski-2021-discriminating,\n  abstract = {Automatic language identification is a challenging problem. Discriminating between closely related languages is especially difficult. This paper presents a machine learning approach for automatic language identification for the Nordic languages, which often suffer miscategorisation by existing state-of-the-art tools. Concretely we will focus on discrimination between six Nordic languages: Danish, Swedish, Norwegian (Nynorsk), Norwegian (Bokm{\\aa}l), Faroese and Icelandic.},\n  address = {Kiyv, Ukraine},\n  author = {Haas, Ren{\\'e}  and\nDerczynski, Leon},\n  booktitle = {Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects},\n  editor = {Zampieri, Marcos  and\nNakov, Preslav  and\nLjube{\\v{s}}i{\\'c}, Nikola  and\nTiedemann, J{\\\"o}rg  and\nScherrer, Yves  and\nJauhiainen, Tommi},\n  month = apr,\n  pages = {67--75},\n  publisher = {Association for Computational Linguistics},\n  title = {Discriminating Between Similar {N}ordic Languages},\n  url = {https://aclanthology.org/2021.vardial-1.8},\n  year = {2021},\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 an",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-3.0) is classified as share-alike.",
 "revision": "fbf57441f3675193092970651373815aaea3ef35",
 "stated_evidence": "https://huggingface.co/datasets/mteb/NordicLangClassification/blob/fbf57441f3675193092970651373815aaea3ef35/README.md",
 "file_evidence": "https://huggingface.co/datasets/mteb/NordicLangClassification/tree/fbf57441f3675193092970651373815aaea3ef35",
 "card_nc": false
}