@inproceedings{borisov-etal-2025-low,
    title = "Low-resource Machine Translation for Code-switched {K}azakh-{R}ussian Language Pair",
    author = "Borisov, Maksim  and
      Kozhirbayev, Zhanibek  and
      Malykh, Valentin",
    editor = "Ebrahimi, Abteen  and
      Haider, Samar  and
      Liu, Emmy  and
      Haider, Sammar  and
      Leonor Pacheco, Maria  and
      Wein, Shira",
    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)",
    month = apr,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.naacl-srw.7/",
    pages = "66--76",
    ISBN = "979-8-89176-192-6",
    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."
}