TEXT BASED SANSKRIT LANGUAGE IDENTIFICATION

Abstract

Text Based Identification of a language is the process of automatically detecting a certain language based on the text given in an article or document. Language identification is an established domain of research that has received considerable attention in the past. Language identification is a crucial initial step in various other works of Natural language processing, language translation, performing language specific AI models etc. It is somewhat easier to differentiate languages which do not belong to same language family or not having same script because the characteristics features seldom overlap each other and due to different script, the symbols used to express the text are different. In this paper, we will devise method to identify Sanskrit language among various languages having same Devanagari script.