Swa-bhasha Resource Hub: Romanized Sinhala to Sinhala Transliteration Systems and Data Resources
Computation and Language
2026-04-28 v2
Abstract
The Swa-bhasha Resource Hub provides a comprehensive collection of data resources and algorithms developed for Romanized Sinhala to Sinhala transliteration between 2020 and 2025. These resources have played a significant role in advancing research in Sinhala Natural Language Processing (NLP), particularly in training transliteration models and developing applications involving Romanized Sinhala. The current openly accessible data sets and corresponding tools are made publicly available through this hub. This paper presents a detailed overview of the resources contributed by the authors and includes a comparative analysis of existing transliteration applications in the domain.
Keywords
Cite
@article{arxiv.2507.09245,
title = {Swa-bhasha Resource Hub: Romanized Sinhala to Sinhala Transliteration Systems and Data Resources},
author = {Deshan Sumanathilaka and Sameera Perera and Sachithya Dharmasiri and Maneesha Athukorala and Anuja Dilrukshi Herath and Rukshan Dias and Pasindu Gamage and Ruvan Weerasinghe and Y. H. P. P. Priyadarshana},
journal= {arXiv preprint arXiv:2507.09245},
year = {2026}
}
Comments
15 pages, 5 Tables, 3 figures