Using Machine Learning Algorithm for Proverb Retrieval and Expansion for Indian Languages

Many philosophical thinkers, research scholars and poets have expatiate their knowledge and experiences in the form of a proverb since ancient days. A proverb is short and known sentence that expresses the perceived truth based on the experience, moral values, wisdom and traditional aspects, symbolic and noteworthy form in different languages as they inherit from their culture and languages. The research paper focuses on developing a digital archive for Indian proverbs in twenty two official languages. The online Cross Lingual Proverb Retrieval and Expansion (CLPRE) digital archive is built by using Machine Learning Algorithm, currently digital archive focuses on four Indian languages such as English, Hindi, Kannada and Marathi. The supervised digital archive has currently corpus size of 250 proverbs for each language. The online digital proverb can be mainly used for education.