A KNOWLEDGE BASED APPROACHFOR WORD SENSE DISAMBIGUATION OF TELUGU LANGUAGE

1Pasupuleti Ranjith Kumar, K Vinith Reddy, M SenthiRaja

106 Views
33 Downloads
Abstract:

Words in the Natural language often correspond to different meanings in different contexts. Such words are referred to as polysemous words i.e. words having more than one sense. A knowledge based algorithm is proposed for disambiguating Telugu polysemous words using computational linguistics tool, Word Net. The task of word sense disambiguation requires finding out the similarity between the target word and the nearby words. In this algorithm similarity is calculated either by finding out the number of common words (intersection) between the glosses (definitions/meanings) of the target and nearbywords, or by finding out the exact occurrence of the nearby word's sense in the hierarchy (hypernyms) of the target word's senses. The above two parameters are modified by computing intersection using not only the glosses but also by including the related words. Also the intersection is computed for the entire hierarchy of the target and nearby words. It also includes a third parameter 'distance' which measures the distance between target and nearby words. The proposed approach incorporates more parameters for calculating similarity, which has not been attempted by any of the previous approaches. It scores the senses based on the overall impact of three parameters i.e. intersection, hierarchy and distance and then chooses the sense with the highest score. The correct sense of Telugu polysemous word would be identified with this approach.

Keywords:

Knowledge based Approach for Word SenseDisambiguation of Telugu Language

Paper Details
Month4
Year2020
Volume24
IssueIssue 6
Pages6595-6603