{
 "id": "BorisovMaksim/kk_ru_csw",
 "owner": "BorisovMaksim",
 "name": "kk_ru_csw",
 "downloads": 9,
 "likes": 1,
 "last_modified": "2025-06-30T11:19:03.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "translation"
 ],
 "citation": "@inproceedings{borisov-etal-2025-low,\n    title = \"Low-resource Machine Translation for Code-switched {K}azakh-{R}ussian Language Pair\",\n    author = \"Borisov, Maksim  and\n      Kozhirbayev, Zhanibek  and\n      Malykh, Valentin\",\n    editor = \"Ebrahimi, Abteen  and\n      Haider, Samar  and\n      Liu, Emmy  and\n      Haider, Sammar  and\n      Leonor Pacheco, Maria  and\n      Wein, Shira\",\n    booktitle = \"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)\",\n    month = apr,\n    year = \"2025\",\n    address = \"Albuquerque, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.naacl-srw.7/\",\n    doi = \"10.18653/v1/2025.naacl-srw.7\",\n    pages = \"66--76\",\n    ISBN = \"979-8-89176-192-6\",\n    abstract = \"Machine translation for low-resource language pairs is a challenging task. This task could become extremely difficult once a speaker uses code switching. We present the first code-switching Kazakh-Russian parallel corpus.Additionally, we propose a method to build a machine translation model for code-switched Kazakh-Russian language pair with no labeled data. Our method is basing on generation of synthetic data. This method results in a model beating an existing commercial system by human evaluation.\"\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "2f28809e509d949c0cc2628de49ea3457828a735",
 "stated_evidence": "https://huggingface.co/datasets/BorisovMaksim/kk_ru_csw/blob/2f28809e509d949c0cc2628de49ea3457828a735/README.md",
 "file_evidence": "https://huggingface.co/datasets/BorisovMaksim/kk_ru_csw/tree/2f28809e509d949c0cc2628de49ea3457828a735",
 "card_nc": false
}