ABHIDHA: an extended WordNet for Indo Aryan languages

A lexical knowledge base is an important component of any intelligent information processing system. The WordNet developed at the Cognitive Systems Laboratories at Princeton has served as a lexical reference system for natural language processing activities. The Indian language based activities at our institute mainly in text-to-speech synthesis and natural language generation from iconic inputs require the inclusion of additional features in the lexical reference system like phonology, word roots, and etymological information. Our initial efforts have been in Hindi and Bengali but commonality of Indo Aryan Languages and the importance of these extra features lead us to believe that it is a worthwhile effort to build-up a WordNet for other Indo Aryan languages containing these features. In this paper, we speak of the issues relating to the structured design and development of a generalized extended WordNet for Indo Aryan languages with special reference to Hindi and Bengali.