Stemmer for resource scarce language using string similarity measure

This paper a work in progress describes a stemming of Kokborok language using a statistical approach. Stemming study of Kokborok is a new topic of research. Many stemming algorithms have been proposed for various languages. But the major work has been done only for English language. In recent times we have seen interest for non English languages too. However, very limited or no computational work has been observed for Kokborok language, a dialect spoken in the Tripura, India. Kokborok is a highly inflectional language. Linguistic knowledge and resources forms one of the basic requirement in building rule based stemmer. Kokborok a new language in this area of computational study suffer from this limitation. This work tries to build a Kokborok stemmer using a statistical approach based on string measure.