@inproceedings{sterner-2024-multilingual,
    title = "Multilingual Identification of {E}nglish Code-Switching",
    author = "Sterner, Igor",
    editor = {Scherrer, Yves  and
      Jauhiainen, Tommi  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Zampieri, Marcos  and
      Nakov, Preslav  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.vardial-1.14/",
    doi = "10.18653/v1/2024.vardial-1.14",
    pages = "163--173",
    abstract = "Code-switching research depends on fine-grained language identification. In this work, we study existing corpora used to train token-level language identification systems. We aggregate these corpora with a consistent labelling scheme and train a system to identify English code-switching in multilingual text. We show that the system identifies code-switching in unseen language pairs with absolute measure 2.3-4.6{\%} better than language-pair-specific SoTA. We also analyse the correlation between typological similarity of the languages and difficulty in recognizing code-switching."
}