The Natural Language Processing Axioms in Classical Tamil for Zonal Dialects using Machine Learning
Perumal Sivarman1, Prabaharan G2, Senthil Kumar R3
1Perumal Sivaraman, Department of Information Technology, UTAS – Nizwa, Oman (Nizwa), Oman.
2Dr. Prabaharan G, Department of Computer Science and Engineering, Vel Tech Rangarajan, Dr. Sagunthala R and D Institute of Science and Technology, Morai (Tamil Nadu), India.
3Dr. Senthil Kumar R, Department of Computer Science and Engineering, Jain Deemed University, Bengaluru (Karnataka), India.
Manuscript received on 19 April 2025 | First Revised Manuscript received on 24 April 2025 | Second Revised Manuscript received on 04 May 2025 | Manuscript Accepted on 15 May 2025 | Manuscript published on 30 May 2025 | PP: 36-44 | Volume-14 Issue-6, May 2025 | Retrieval Number: 100.1/ijitee.F109614060525 | DOI: 10.35940/ijitee.F1096.14060525
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Studying Natural Language Processing (NLP) for Classical Tamil and its Zonal Dialects using Machine Learning (ML) involves unique challenges and opportunities. Classical Tamil, one of the oldest languages with a rich literary heritage, differs significantly in syntax, semantics, and phonetics from its modern dialects. Addressing these differences requires incorporating linguistic axioms and cultural nuances into NLP systems. This deals with Tamil letters, Challenges, Future directions, and Lexical Differences. It also includes parsers and tokenisation. Lists the differences between Morphemes, Bounded Morphemes in terms of Tamil as a Natural Language processing—dictionary form of the words used in Lemmatizations. Stemming reduces the words, and Tamil is represented as a short sentence, comparing the differences in the Tamil dialect taken and represented. The methodology used is Clustering algorithms, which can group zonal dialects based on phonetic and semantic similarities using a Naïve Bayes classifier. We are using speechto-text to identify the Tamil dialect. This zonal dialect is essential in entertainment, education, information, and business. More Exploration can be done using Zonal dialects in Classical Tamil. Machine learning plays a role in classification, Grouping, and Segmenting Natural Language processing. We have different dialects in the Single Language Tamil for a single word in Natural Language Processing. Encourages local people to communicate fluently in terms of transactions. Preserving local traditions and customs is one of the advantages of Zonal Dialects. It can be used in interviews, recordings, written and spoken texts, as well as debates. Linguistic Diversity, preservation of History, and cultural identity are significant concerns in Zonal dialects that use classical Tamil.
Keywords: (must be 3-5), Zonal Dialects, Machine Learning, Naïve Bayes.
Scope of the Article: Artificial Intelligence and Methods