Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches

Yomal De Mel, Kasun Wickramasinghe, Nisansa de Silva, Surangika Ranathunga
12/31/2024
cs.CL

Official code: kasunw22/Sinhala-Transliterator (1 star, MIT, last commit 2025-04-29).

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/

View on arXivView PDF

Code Implementations(1)

kasunw22/Sinhala-TransliteratorOfficial100%
MIT

Introduce Transliteration Solutions for Sinhala Language

10Jupyter NotebookDec 9, 20241 years agoMIT
llm-transliteratormachine-transliterationrule-based-transliterationseq2seqsinglish+9 more

Similar Papers

Swa-bhasha Resource Hub: Romanized Sinhala to Sinhala Transliteration Systems and Data Resources

84% match2025

IndoNLP 2025: Shared Task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages

83% match2025

AyutthayaAlpha: A Thai-Latin Script Transliteration Transformer

82% match2024

Romanized to Native Malayalam Script Transliteration Using an Encoder-Decoder Framework

81% match1 repo12024

Low-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models

81% match2025

ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration

80% match2024

Cite this paper

@article{mel2024sinhala,
  title  = {Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches},
  author = {Yomal De Mel and Kasun Wickramasinghe and Nisansa de Silva and Surangika Ranathunga},
  year   = {2024},
  eprint = {2501.00529},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.00529v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.00529.svg)](https://codeofpaper.com/paper/2501.00529)

Discussion