Study on Similarity among Indian Languages Using Language Verification Framework

[摘要] Majority of Indian languages have originated from two language families, namely, Indo-Europeanand Dravidian. Therefore, certain kind of similarity among languages of a particular family canbe expected to exist. Also, languages spoken in neighboring regions show certain similaritysince there happens to be a lot of intermingling between population of neighboring regions. Thispaper develops a technique to measure similarity among Indian languages in a novel way, usinglanguage verification framework. Four verification systems are designed for each language. Acceptance of one language as another, which relates to false acceptance in language verificationframework, is used as a measure of similarity. If languageAshows false acceptance more than apredefined threshold with languageB, in at least three out of the four systems, then languagesAandBare considered to be similar in this work. It is expected that the languages belonging to the same family should manifest their similarity in experimental results. Also, similaritybetween neighboring languages should be detected through experiments. Any deviation fromsuch fact should be due to specific linguistic or historical reasons. This work analyzes any suchscenario.

[学科分类] 人工智能