@inproceedings{kunchukuttan-etal-2021-large,
    title = "A Large-scale Evaluation of Neural Machine Transliteration for {I}ndic Languages",
    author = "Kunchukuttan, Anoop  and
      Jain, Siddharth  and
      Kejriwal, Rahul",
    editor = "Merlo, Paola  and
      Tiedemann, Jorg  and
      Tsarfaty, Reut",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.eacl-main.303/",
    doi = "10.18653/v1/2021.eacl-main.303",
    pages = "3469--3475",
    abstract = "We take up the task of large-scale evaluation of neural machine transliteration between English and Indic languages, with a focus on multilingual transliteration to utilize orthographic similarity between Indian languages. We create a corpus of 600K word pairs mined from parallel translation corpora and monolingual corpora, which is the largest transliteration corpora for Indian languages mined from public sources. We perform a detailed analysis of multilingual transliteration and propose an improved multilingual training recipe for Indic languages. We analyze various factors affecting transliteration quality like language family, transliteration direction and word origin."
}