Elamur Research⌕
☰
home / papers / 2026 / Kelvi: A Morphological Parser to Support Tamil Literacy

Kelvi: A Morphological Parser to Support Tamil Literacy

Paper · 2026 · Shankhalika Srikanth, Sabrina Yu, Sophia Chan et al.

Summary

Tamil packs much of its grammar into chains of suffixes, but standard dictionaries list only base forms. Learners therefore often cannot identify the stem they need to look up. This is especially hard for diaspora heritage speakers, who know colloquial spoken Tamil but struggle with the fuller formal written register. The authors present Kelvi (kelvi.ca), a free, open-source web dictionary and morphological parser. For any entered word, it returns the stem and its definition, plus plain-language explanations of each attached suffix, so users gradually learn to recognize Tamil morphology themselves.

The design followed community-based and user-centered methods. The team tested a Figma prototype in interviews with 10 adult speakers, which produced three requirements:

  • intuitive breakdowns even for L2 learners,
  • nothing overwhelming for beginners,
  • usability on phones.

Dictionary content comes from Tamil Wiktionary data and Vasuki's dictionaries. The suffix inventory was authored in Gramble and exported as JSON. Seven of ten interviewees said they would use the tool. The authors offer Kelvi as an adaptable template for other underserved agglutinative or polysynthetic languages.

Key points

  • Participants: 3 native speakers, 6 heritage speakers and 1 beginner L2 learner. Their oral fluency and literacy were not correlated. Google Translate was the most common lookup method (8 mentions), though several distrusted its translations.
  • Responses to "would you use it": 7 yes, 1 maybe, 2 no.
  • Data and resources: Tamil Wiktionary (Ylonen, 2022) and Vasuki dictionaries for definitions. The suffix database was built with Gramble (NRC Canada), with entries holding attributes such as text, gloss, display and add-back.
  • Scope: Only formal written Tamil is covered, with academic-style romanization in the output. Front-end and back-end code is public on GitHub.
  • Limitations: Kelvi is still at MVP stage and not fully accurate. Test data was created by hand and limited to a few hundred inputs because of budget and volunteer constraints. The provided text omits the evaluation section, so no accuracy figures are reported here.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksPsychology · 1,552 worksDevelopmental and Educational Psychology · 499 works

🧭 Topics 1Research subjects and languages the work is about.Morphology · 405 works

Cite

Cite as Shankhalika Srikanth, Sabrina Yu, Sophia Chan and Madeline Solis de Ovando. 2026. Kelvi: A Morphological Parser to Support Tamil Literacy. Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.bea-1.21

@inproceedings{srikanth2026kelvi,
  title = {{Kelvi: A Morphological Parser to Support Tamil Literacy}},
  author = {Shankhalika Srikanth, Sabrina Yu, Sophia Chan and Madeline Solis {de Ovando}},
  booktitle = {Proceedings of the 21st Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.bea-1.21},
  url = {https://doi.org/10.18653/v1/2026.bea-1.21}
}

References

34 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. E. Annamalai. 2011. Social dimensions of modern Tamil, 1st edition. Cre-A:, Chennai. find
  2. E. Annamalai. 2019. Modern Tamil. In Sanford B. Steever, editor, The Dravidian languages, 2 edition. Routledge. Num Pages: 27. find
  3. E. Annamalai and R. E. Asher. 2002. Colloquial Tamil: The Complete Course for Beginners. Taylor & Francis Group, London, UNITED KINGDOM. find
  4. Albert Henry Arden. 1910. A progressive grammar of common Tamil. Madras : Society for Promoting Christian Knowledge. find
  5. Nathan Thanyehténhas Brinklow, Patrick Littell, Delaney Lothian, Aidan Pine, and Heather Souter. 2020. Indigenous Language Technologies & Language Reclamation in Canada. In International Conference Language Technologies for All (LT4All): Enabling Linguistic Diversity and Multilingualism Worldwide. U… find
  6. Mary Bucholtz. 2021. Community-Centered Collaboration in Applied Linguistics. Applied Linguistics, 42(6):1153–1161. find
  7. Elango Cheran. 2001. Learn Tamil. find
  8. Anna Kazantseva, Aidan Pine, Owennatekha Brian Maracle, and Ronkwe’tiyohstha Joe Maracle. 2018. Kawennón:nis: the Wordmaker for Kanyen’kéha (Ohsweken Mohawk). In COLING: The 27th International Conference on Computational Linguistics. find
  9. Wesley Y. Leonard. 2021. Toward an Anti-Racist Linguistic Anthropology: An Indigenous Response to White Supremacy. Journal of Linguistic Anthropology, 31(2):218–237. find
  10. Patrick Littell, Aidan Pine, and Henry Davis. 2017. Waldayu and Waldayu Mobile: Modern digital dictionary interfaces for endangered languages. In Proceedings of the 2nd Workshop on the Use of Computational Methods in the Study of Endangered Languages, pages 141–150, Honolulu. Association for Computa… find
  11. Patrick Littell, Darlene Stewart, Fineen Davis, Aidan Pine, and Roland Kuhn. 2024. Gramble: A Tabular Programming Language for Collaborative Linguistic Modeling. In LREC-COLING 2024. ACL. find
  12. Yanfei Lu, Patrick Littell, and Keren Rice. 2024. Empowering Oneida language revitalization: Development of an Oneida verb conjugator. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5757– 5767, Torin… find
  13. Megan Lukaniec and Martin Holmes. 2023. Modern Wendat Lexicography: Using XML to Reflect the Grammar and Lexicon of an Iroquoian Language. Dictionaries: Journal of the Dictionary Society of North America, 44(2):75–105. find
  14. Yash Madhani, Sushane Parthan, Priyanka Bedekar, Gokul Nc, Ruchi Khapra, Anoop Kunchukuttan, Pratyush Kumar, and Mitesh Khapra. 2023. Aksharantar: Open Indic-language transliteration datasets and models for the next billion users. In Findings of the Association for Computational Linguistics: EMNLP 2… find
  15. Irbha Magotra, Jyoti Sharma, and Supran Kumar Sharma. 2016. Assessing personal disposition of individuals towards technology adoption. Future Business Journal, 2(1):81–101. find
  16. Ahrane Mahaganapathy and Kengatharaiyer Sarveswaran. 2025. A survey and evaluation of text-to-speech systems for the tamil language. Natural Language Processing Journal, 12:100171. find
  17. Silvina Montrul. 2016. Heritage languages and heritage speakers. In The Acquisition of Heritage Languages, pages 13–40. Cambridge University Press, Cambridge. find
  18. Aidan Pine, Erica Cooper, David Guzmán, Eric Joanis, Anna Kazantseva, Ross Krekoski, Roland Kuhn, Samuel Larkin, Patrick Littell, Delaney Lothian, Akwiratékha’ Martin, Korin Richmond, Marc Tessier, Cassia Valentini-Botinhao, Dan Wells, and Junichi Yamagishi. 2025a. Speech generation for indigenous l… find
  19. Aidan Pine, David Huggins-Daines, Carmen Leeming, Patrick Littell, Timothy Montler, Heather Souter, and Mark Turin. 2025b. Zero-shot query generation for approximate search algorithm evaluation. In Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Langu… find
  20. Aidan Pine, Patrick Littell, Eric Joanis, David Huggins-Daines, Christopher Cox, Fineen Davis, Eddie Antonio Santos, Shankhalika Srikanth, Delasie Torkornoo, and Sabrina Yu. 2022. Gi2Pi: Rule-based, index-preserving grapheme-to-phoneme transformations. In 5th Workshop on the Use of Computational Met… find
  21. Maria Polinsky and Olga Kagan. 2007. Heritage Languages: In the ’Wild’ and in the Classroom. Language and Linguistics Compass, 1(5):368–395. find
  22. Arun Prasad. 2025. Tamil for Beginners. find
  23. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python natural language processing toolkit for many human languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations.
  24. Damodharan Rajalingam. 2025. rdamodharan/tamil-stemmer. Original-date: 2010-12-27T17:37:49Z. find
  25. Vasu Renganathan. 2019. Heritage language environment (HLE) and its implications upon language curriculum: a case of Tamil heritage students and designing a differentiated curriculum. In Langues de l’Inde en diasporas : maintiens et transmissions, Paris. find
  26. The following tasks were given to the participants to complete using the prototype. Note that the Tamil words were presented in text; no romanization was given and facilitators did not read out the words. find
  27. Kengatharaiyer Sarveswaran, Gihan Dias, and Miriam Butt. 2021. ThamizhiMorph: A morphological parser for the Tamil language. Machine Translation, 35(1):37–70. 1. Find the meaning of ெபரியவர்களுக்கு using the prototype interface. Try entering the word using Tanglish 8 / English letters. find
  28. Harold F. Schiffman, Vasu Renganathan, Prathima Christdas, S. Palanisamy, Thanam Baba, K. Karunakaran, Ganesh Krishnamurti, C.M. Pradeep, and S. Radhakrishnan, editors. 2009. An English dictionary of the Tamil verb. South Asia Studies Dept. University of Pennsylvania, Philadelphia, Pa. 2. Find the m… find
  29. Muditha Tissera and Hassaan Saadhiq. 2025. Natural Language Processing Resources for Tamil Language: A Systematic Review. Journal of Information and Communication Convergence Engineering, 23(4):236–258. 4. Find the meaning of சிதற விடும் using your preferred input method from the previous tasks. find
  30. Vishas Vasuki. n.d. Dharma Via Vishvas. find
  31. Anne Wallisch, Olga Sankowski, Dieter Krause, and Kristin Paetzold. 2019. Overcoming fuzzy design practice: revealing potentials of user-centered design research and methodological concepts related to user involvement. In 2019 IEEE International Conference on Engineering, Technology and Innovation (… find
  32. World Population Review. 2026. Official use of Tamil by country 2026. find
  33. Olcay Taner Yıldız, Begüm Avar, and Gökhan Ercan. 2019. An open, extendible, and fast Turkish morphological analyzer. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1364– 1372, Varna, Bulgaria. INCOMA Ltd. find
  34. Tatu Ylonen. 2022. Wiktextract: Wiktionary as Machine-Readable Structured Data. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1317–1325, Marseille, France. European Language Resources Association. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/srikanth-2026-kelvi-morphological-parser-support-tamil/