@inproceedings{de2024sinhala,
  title={{Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches}},
  author={De Mel, Yomal and Wickramasinghe, Kasun and de Silva, Nisansa and Ranathunga, Surangika},
  booktitle={Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages},
  pages={166--173},
  year={2025},
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. The code base associated with this paper is available on GitHub - https://github.com/kasunw22/Sinhala-Transliterator/},
url={https://aclanthology.org/2025.indonlp-1.19.pdf},
misc={https://arxiv.org/abs/2501.00529,NLP:SIN,https://goo.gl/iY6aTr}
}