Study on Techniques for Analyzing Semantic Similarity in Question Answering System
K. Shivani, M.R. Aswathy · 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI) · 2018
Semantic similarity standards are an inevitable factor in Natural Language Processing tasks. Semantic similarity uses actual meaning of words to decide similarity. Semantic similarity only contains “is a” relation. However Semantic similarity standards developed for regular use do not perform well within specific domains. Sentiment analysis, Natural language understanding, Machine translation, artificial intelligence, psychology and cognitive science are a few of the important areas where it is employed. The paper contains a study of the state of art measures containing path based measures, information based measures, feature based measures and hybrid measures. The features, performance, advantages, disadvantages and related issues of different standards are discussed. This paper gives a review of semantic similarity standards with different approaches.