@inproceedings{rao-gopinath-2023-sanskrit,
    title = "A {S}anskrit grammar-based approach to identify and address gaps in {G}oogle {T}ranslate`s {S}anskrit-{E}nglish zero-shot {NMT}",
    author = "Rao, Amit  and
      Gopinath, Kanchi",
    editor = "Breitholtz, Ellen  and
      Lappin, Shalom  and
      Loaiciga, Sharid  and
      Ilinykh, Nikolai  and
      Dobnik, Simon",
    booktitle = "Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)",
    month = sep,
    year = "2023",
    address = "Gothenburg, Sweden",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.clasp-1.16/",
    pages = "141--166",
    abstract = "In this work, we test the working of Google Translate`s recently introduced Sanskrit-English translation system using a relatively small set of probe test cases designed to focus on those areas that we expect, based on a knowledge of Sanskrit and English grammar, to pose a challenge for translation between Sanskrit and English. We summarize the findings that point to significant gaps in the current Zero-Shot Neural Multilingual Translation (Zero-Shot NMT) approach to Sanskrit-English translation. We then suggest an approach based on Sanskrit grammar to create a differential parallel corpus as a corrective training data to address such gaps. This approach should also generalize to other pairs of languages that have low availability of learning resources, but a good grammar theory."
}