🧑‍🔬 Kengatharaiyer Sarveswaran

🏛️ Affiliations

🎓University of JaffnaJaffna · Sri Lanka2011–2026 · 22 papersEmployment since 2011 · Senior Lecturer, Computer Sciencecurrent🎓University of MoratuwaMoratuwa · Sri Lanka2007–2022 · 8 papersEducation 2007–2011 · Master of Science in Computer ScienceEducation 2017–2022 · PhD, Computer Science and EngineeringEmployment 2007–2009 · Systems Engineeer, Computer science and engineering

🏛️University of Peradeniya Faculty of SciencePeradeniya · Sri Lanka2002–2006Education 2002–2006 · Bachelor of a science (hons) in Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models (2023 · 33 citations)
   Most large-scale LLM benchmarks, such as HELM and BIG-bench, focus on English. Southeast Asian (SEA) languages get little systematic evaluation. BHASA addresses this gap with an evaluation suite in three parts:
2. Findings of the Second Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2026) (2026 · 12 citations)
   This report covers the second CHiPSAL workshop, held with LREC 2026. The workshop addresses the weak coverage of South Asian languages in NLP resources and LLMs. The region has about 700 languages written in more than 25 scripts. Progress is held back by scarce curated data, rich morphology, code-mixing, script…
3. Multimodal Hate and Sentiment Understanding in Low-Resource Text-Embedded Images for Online Safety and Digital Well-being (2026 · 12 citations)
   This overview paper reports on a CHiPSAL 2026 shared task, held at LREC 2026, on moderating memes in Nepali, a widely spoken language with few resources.
4. Egalitarian Language Representation in Language Models: It All Begins with Tokenizers (2025 · 11 citations)
   Tokenizers from English-centric LLMs handle complex abugida scripts such as Tamil, Sinhala and Hindi poorly.
5. A Feature-Fusion Ensemble Approach for Tamil Hate Speech Detection (2026 · 1 citation)
   The paper addresses automatic detection of offensive and hateful content in Tamil social media text. The task is difficult because Tamil is low-resource and agglutinative, and online users mix it with English, Romanized spellings and slang. Standard subword tokenizers can split such insults into pieces that weaken…
6. Evaluating Linguistic Knowledge of LLMs in Tamil: The ILAKKANAM Benchmark (2026 · 1 citation)
   Tamil is agglutinative and computationally low-resource, yet LLM evaluation for it relies mostly on multilingual suites that are often translated from English or cover few phenomena.
7. Aalamaram: A Large-Scale Linguistically Annotated Treebank for the Tamil Language (2024 · 1 citation)
   Tamil still has little high-quality linguistically annotated data. Raw corpora and datasets for NLU and NLG tasks are growing, but there are only two UD treebanks for Tamil: TTB and MWTT. Each contains roughly 600 sentences drawn from a single source, and neither has named entity annotation. The authors built…
8. TaLK-Corpus: A Regionally Diverse Evaluation Set for Sri Lankan Tamil Speech (2026)
   Sri Lankan Tamil has no benchmark for evaluating speech recognition. Existing Tamil ASR datasets mostly capture Indian Tamil, and the main Sri Lankan resource, EmoTa, targets emotion recognition. The authors present TaLK-Corpus, a small evaluation set organised by geography. It has one native speaker from each of 22…

🤝 Co-authors here

12 of 18 co-authors with a page, the most papers together first.

• Bal Krishna Bal ×2
• Hamsawardhini Rengarajan ×2
• Menan Velayuthan ×2
• Surendrabikram Thapa ×2
• Wei Qi Leong ×2
• William Chandra Tjhi ×2
• Ashwini Vaidya
• Jian Gang Ngui
• Kristina T Johnson
• Kritesh Rauniyar
• Laxmi Thapa
• Rajiv Ratn Shah

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• workshop on Challenges in Processing South Asian Languages ×4: workshop on Challenges in Processing South Asian Languages 2026 ×4
• International Conference on Computational Linguistics (COLING): COLING 2025
• Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC: Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026
• Workshop on Indian Language Data: Resources and Evaluation: Workshop on Indian Language Data: Resources and Evaluation 2024

🔗 Cited by

Papers of our library cite their works 68 times (of the 149,439 papers whose bibliographies we read); 16 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/kengatharaiyer-sarveswaran/