Bangla grammar pattern recognition using shift reduce parser

Parser plays a very important role in computational linguistics. In this paper, here we describe a parsing technique for Bangla grammar recognition. The parser is, by nature, a shift reduce parser and constructs a parse table based on LR strategy. It takes the Context Free Grammar (CFG) of the Bangla language as input and constructs parser table from the grammar. The parse table is visited on bottom-up approach. This parser is free from the problem of the left factoring and left recursion. To avoid the inflection (BIVOKTI) of Bangla we describe a new approach. Hence only the main form of the Bangla word is stored in the repository. Our experiment shows that the scheme can detect all forms of Bangla sentences even for nontraditional forms.