@inproceedings{vaidya-kane-2023-two,
    title = "Two-stage Pipeline for Multilingual Dialect Detection",
    author = "Vaidya, Ankit  and
      Kane, Aditya",
    editor = {Scherrer, Yves  and
      Jauhiainen, Tommi  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Nakov, Preslav  and
      Tiedemann, J{\"o}rg  and
      Zampieri, Marcos},
    booktitle = "Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.vardial-1.22/",
    doi = "10.18653/v1/2023.vardial-1.22",
    pages = "222--229",
    abstract = "Dialect Identification is a crucial task for localizing various Large Language Models. This paper outlines our approach to the VarDial 2023 shared task. Here we have to identify three or two dialects from three languages each which results in a 9-way classification for Track-1 and 6-way classification for Track-2 respectively. Our proposed approach consists of a two-stage system and outperforms other participants' systems and previous works in this domain. We achieve a score of 58.54{\%} for Track-1 and 85.61{\%} for Track-2. Our codebase is available publicly (\url{https://github.com/ankit-vaidya19/EACL_VarDial2023})."
}