kasunw/sinhala-transliterator

• This is the trained model of the seq2seq approach of our Sinhala Transliteration solution that was submitted to the Shared Task of IndoNLPWorkshop 2025 collocated with COLING2025.
• The official codebase can be accessed from https://github.com/kasunw22/Sinhala-Transliterator
• Please be kind enough to cite our paper and don't hesitate to rate our original repository

@inproceedings{de-mel-etal-2025-sinhala,
    title = "{S}inhala Transliteration: A Comparative Analysis Between Rule-based and {S}eq2{S}eq Approaches",
    author = "De Mel, Yomal  and
      Wickramasinghe, Kasun  and
      de Silva, Nisansa  and
      Ranathunga, Surangika",
    editor = "Weerasinghe, Ruvan  and
      Anuradha, Isuri  and
      Sumanathilaka, Deshan",
    booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages",
    month = jan,
    year = "2025",
    address = "Abu Dhabi",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.indonlp-1.19/",
    pages = "166--173",
    abstract = "Due to reasons of convenience and lack of tech literacy, transliteration (i.e., Romanizing native scripts instead of using localization tools) is eminently prevalent in the context of low-resource languages such as Sinhala, which have their own writing script. In this study, our focus is on Romanized Sinhala transliteration. We propose two methods to address this problem: Our baseline is a rule-based method, which is then compared against our second method where we approach the transliteration problem as a sequence-to-sequence task akin to the established Neural Machine Translation (NMT) task. For the latter, we propose a Transformer based Encode-Decoder solution. We witnessed that the Transformer-based method could grab many ad-hoc patterns within the Romanized scripts compared to the rule-based method."
}