Welcome to my home page!
I am a Computational Linguist focusing on understanding and modeling natural languages, with a special focus on Tamil and other low-resource languages, using computational methods.
I am a Senior Lecturer in Computer Science at the University of Jaffna, Sri Lanka. Additionally, I am a visiting researcher and a member of the Computational Linguistics Group in the Department of Linguistics at the University of Konstanz, Germany.
| Education | Professional |
|---|---|
|
|
Ongoing Projects (Open for Collaboration)
- Building a Sri Lankan Tamil corpus
- OCR/TTS for Tamil
- Thirukkural Treebank
- Building a Linguistically-Aware Tamil LLM
Recent news
- Published a paper on pre-tokenization/tokenization at COLING 2025 - Find it here
- Successfully organised a workshop on Challenges in Processing South Asian Languages (CHiPSAL-2025) on Jan 19, 2025 at COLING 2025 - Proceedings is here
( Some news from 2024) )
- Led an exchange visit to the University of Engineering and Technology, Lahore, Pakistan, from December 5 to 12, 2024.
- Attended and presented a poster at the DAAD Project Leader Meeting: Advancing Higher Education Partnerships, held in Indonesia from October 14 to 17, 2024.
- Organising a workshop at COLING on Challenges in Processing South Asian Languages (CHiPSAL-2025). Please help us to spread the word.
- Had the privilege of delivering a five-day course on the Challenges of Processing South Asian Languages at the 34th European Summer School in Logic, Language and Information (ESSLLI) held from 5 - 9 August 2024 at KU Leuven, Belgium. Course materials can be found here
- Published an article on GenAI and Creative literature (Tamil) in Gnanam Monthly magazine.
- Recruting Research assistants - apply here: https://www.csc.jfn.ac.lk/vacancies/
- Assumed the position of President of the Jaffna Science Association from June 2024. I look forward to supporting the development of the region.
- Delivered a keynote address at the International Conference on Tamil Computing and Information Technology to be held at the University of Texas at Dallas, USA, on June 14-16, 2024.
- Looking for PhD/Masters students to work on corpus building and low-resource language resource development.
- Secured a Google grant to develop a Sri Lankan Tamil Corpus (Speech and Text).
- Visited as researcher the Department of Linguistics, University of Konstanz, Germany, from April to the 14 of June 2024.
- Secured a DAAD-SDG grant to develop resources for South Asian languages together with my PhD supervisors, evaluators, and their team from the University of Konstanz, the University of Moratuwa, and the University of Engineering and Technology, Pakistan. I will lead the development of resources for the Tamil language.
Kengatharaiyer Sarveswaran
sarves at univ.jfn.ac.lk
Department of Computer Science
University of Jaffna
Sri Lanka