Developing an automated Bangla parts of speech tagged dictionary

This paper develops an algorithm for making an automated Bangla Parts Of Speech (POS) tagged dictionary. Natural Language Processing is one of the most vigorous research areas of computer science. It enables to communicate and retrieve information form computer based system more effectively and efficiently. Researches on Bangla language processing have started long back. However, this research area still suffers from resource scarcity. A POS tagged corpus is a cardinal element for language processing. POS tagging is the process of categorizing a particular word to a particular part of speech or syntactic category. In Bangla, we do not have any large POS tagged dictionary. In this paper we develop an automated way to make a POS tagged dictionary of Noun, Verb and Adjective. Initially, a suffix (or postfix) list is created manually for Bangla language. Based on this suffix list the POS tagged dictionary is developed. The proposed algorithm is evaluated using a paragraph consisting of manually tagged 10,000 words with 11 tags. We found that POS tagging is obtained more accurately for Verb than Noun and Adjective.