@inproceedings{riyadh-kondrak-2019-joint,
    title = "Joint Approach to Deromanization of Code-mixed Texts",
    author = "Riyadh, Rashed Rubby  and
      Kondrak, Grzegorz",
    editor = {Zampieri, Marcos  and
      Nakov, Preslav  and
      Malmasi, Shervin  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Ali, Ahmed},
    booktitle = "Proceedings of the Sixth Workshop on {NLP} for Similar Languages, Varieties and Dialects",
    month = jun,
    year = "2019",
    address = "Ann Arbor, Michigan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-1403/",
    doi = "10.18653/v1/W19-1403",
    pages = "26--34",
    abstract = "The conversion of romanized texts back to the native scripts is a challenging task because of the inconsistent romanization conventions and non-standard language use. This problem is compounded by code-mixing, i.e., using words from more than one language within the same discourse. In this paper, we propose a novel approach for handling these two problems together in a single system. Our approach combines three components: language identification, back-transliteration, and sequence prediction. The results of our experiments on Bengali and Hindi datasets establish the state of the art for the task of deromanization of code-mixed texts."
}