{
 "id": "HPLT/OpenLID-v3",
 "owner": "HPLT",
 "name": "OpenLID-v3",
 "downloads": 284,
 "likes": 0,
 "last_modified": "2026-06-18T08:24:56.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "@inproceedings{fedorova-etal-2026-openlid,\n    title = \"{O}pen{LID}-v3: Improving the Precision of Closely Related Language Identification {--} An Experience Report\",\n    author = \"Fedorova, Mariia  and\n      Arefyev, Nikolay  and\n      Buljan, Maja  and\n      Helcl, Jind{\\v{r}}ich  and\n      Oepen, Stephan  and\n      R{\\o}nningstad, Egil  and\n      Scherrer, Yves\",\n    editor = {Scherrer, Yves  and\n      Aepli, No{\\\"e}mi  and\n      Blaschke, Verena  and\n      Jauhiainen, Tommi  and\n      Ljube{\\v{s}}i{\\'c}, Nikola  and\n      Nakov, Preslav  and\n      Tiedemann, J{\\\"o}rg  and\n      Zampieri, Marcos},\n    booktitle = \"Proceedings of the 13th Workshop on {NLP} for Similar Languages, Varieties and Dialects\",\n    month = mar,\n    year = \"2026\",\n    address = \"Rabat, Morocco\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.vardial-1.23/\",\n    doi = \"10.18653/v1/2026.vardial-1.23\",\n    pages = \"275--292\",\n    abstract = \"Language identification (LID) is an essential step in building high-quality multilingual datasets from web data. Existing LID tools (such as OpenLID or GlotLID) often struggle to identify closely related languages and to distinguish valid natural language from noise, which contaminates language-specific subsets, especially for low-resource languages. In this work we extend the OpenLID classifier by adding more training data, merging problematic language variant clusters, and introducing a special label for mark",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "f1d299cf94df009e25bea88664753fb4dbcad1bc",
 "stated_evidence": "https://huggingface.co/datasets/HPLT/OpenLID-v3/blob/f1d299cf94df009e25bea88664753fb4dbcad1bc/README.md",
 "file_evidence": "https://huggingface.co/datasets/HPLT/OpenLID-v3/tree/f1d299cf94df009e25bea88664753fb4dbcad1bc",
 "card_nc": false
}