A Review of Tamil Epigraphy Data Analysis Through Machine Learning

Machine learning is an important and growing area in the field of Artificial intelligence. in which the machine identifies the next task to perform by analyzing the sample data given. Tamil epigraphy and corpora contain huge amount of data. The data contain varieties of Tamil language and different grammatical structures of the different generations of Tamil speakers. Previous methods of analyzing the synchronic study of Tamil language and the diachronic comparison of words in texts used rule based POS (Parts of Speech) tags Database mapping. In this paper, I review and compare various machine learning methods to improve the corpus analysis to identify different varieties of Tamil epigraphy and understand the grammatical structure of each generation of Tamil.