A NATURAL LANGUAGE APPLICATION TO DETERMINE 'CHANDASSU' (GRAMMAR) & PREDICT THE RIGHT WORD IN TELUGU POETRY.

This paper describes an intelligent predictive modeling algorithm to find grammar ('Chandassu') of a given poem and enables right prediction of words, while building a new poem in Telugu literature. The key steps in this algorithm include - Parsing, building a lexicon, syntactic analysis, with the help of predefined rule base, determine 'chandassu (grammar) of a given poem. It also, builds a lexicon of all the words derived from a poem. The prediction techniques include leveraging statistical techniques to help the poet in finding an appropriate word, while constructing a new poem. An intelligent hashing function is used for faster searching. These techniques and algorithms will help the linguists to analyze ancient texts, poetic patterns, language study, civilization and culture. [ABSTRACT FROM AUTHOR]