இந்திய அறிவு மரபு (Indian Knowledge Systems - IKS) மற்றும் தமிழ் இலக்கியங்கள்: Viksit Bharat 2047 நோக்கிலான ஆய்வுகள்
Digital Humanities and Tamil Language Resources: AI, OCR, and Digitization of Inscriptions and Palm-Leaf Manuscripts
DOI:
https://doi.org/10.63300/tm12022026.45Keywords:
Digital Humanities, Tamil Language Resources, AI, OCR, Inscriptions, Palm-leaf Manuscripts, Digitization, Natural Language ProcessingAbstract
This paper explores the application of Digital Humanities technologies—including Artificial Intelligence (AI), Optical Character Recognition (OCR), and Natural Language Processing (NLP)—to preserve and digitize over two millennia of Tamil linguistic heritage currently threatened by physical decay. It examines the technical challenges of parsing ancient script variations and damaged physical artifacts like palm-leaf manuscripts and stone inscriptions, while evaluating modern computational tools and Tamil-specific Large Language Models (such as Tamil-LLaMA and AI4Tamil). Ultimately, the study highlights how integrating AI-driven workflows safeguards invaluable historical knowledge, advances computational Tamilology, and makes Tamil intellectual heritage globally accessible.
Downloads
References
[1.] Balachandran, K. (2023). Tamil palm-leaf manuscripts: Digitization and preservation. Journal of Tamil Studies, 45(2), 67-89.
[2.] Chakravarthi, B. R., et al. (2022). DravidianCodeMix: A corpus for code-mixed Dravidian languages. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 1234-1245.
[3.] Doddapaneni, S., et al. (2023). IndicNLP: A comprehensive NLP dataset for Indian languages. Transactions of the Association for Computational Linguistics, 11, 456-472.
[4.] Ganesan, R., & Krishnamurthy, S. (2024). Optical character recognition for Tamil: A deep learning approach. International Journal of Document Analysis and Recognition, 27(1), 45-62.
[5.] Mohan, R., & Vijayakumar, D. (2022). Digitization of Tamil manuscripts: Challenges and opportunities. Journal of Digital Humanities, 5(3), 89-112.
[6.] Rangarajan, S. (2017). Tamil inscriptions: A digital epigraphy project. South Asian Studies, 33(2), 145-168.
[7.] Sahoo, R., Bhattacharya, A., & Das, S. (2024). Large language models and Indian languages: Opportunities and challenges. Journal of Computational Linguistics, 50(3), 112-135.
[8.] Schreibman, S., Siemens, R., & Unsworth, J. (2020). A companion to digital humanities. Wiley-Blackwell.
[9.] Svensson, P. (2016). Digital humanities and the humanities. Cambridge University Press.
[10.] Veerakannan, S., & Vijayakumar, D. (2025). AI and Tamil literary studies: Challenges and opportunities. Journal of Digital Humanities, 6(2), 89-112.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Our journal adopts CC BY License Creative Commons Attribution 4.0 International License http://Creativecommons.org//license/by/4.0/ . It allows using, reusing, distributing and reproducing of the original work with proper citation.
How to Cite
