Estimation of Word Net-Based Lexical Semantic Similarity Measure for Telugu Documents
Mrs. A. Kanaka Durga · IOSR Journal of Computer Engineering · 2012
The estimation of lexical semantic relatedness has numerous applications in NLP.Several measures are available for the evaluation of lexical semantic relatedness.This paper presents two approaches for measuring semantic similarity/distance between words and concepts with the help of WordNet-Telugu.The edge-based approach of the edge counting scheme and the node-based approach of the information content calculation have been explored.In the field of concepts, the measure of Wu and Palmer has the advantage of being simple to implement and have good performances compared to the other similarity measures.The obtained results show that the Wu and Palmer approach presents a better performance in terms of relevance.