MAYA

Abstract: Ontologies are widely used in several areas with applications including knowledge Management, Web commerce and electronic business. An ontology provides a consensus of concept specifications for a specific domain shared by a group of people. In this paper we deal with Ontology Learning, specifically we aim to adapt the WordNet ontology, a general source of lexical knowledge, to the medical domain. We use for this task a combination of lexico-syntactic pattern, mainly conjunctions of the form “Noun_CJC_Noun,” where CJC can be {and, or, but}. Pairs of words extracted in this fashion are compared to find their similarity in the WordNet noun hierarchy, using a form of the Resnik similarity method. Large scale experiments were conducted by extracting many such pairs of nouns from the Ohsumed corpus and mapping them into WordNet. For a noun pattern like “A or B” we find the lowest common ancestor of A and B by using the hypernym and hyponym links. This enables us to keep the appropriate medical sense of the two words A and B.