Title: Recognising sentence similarity using similitude and dissimilarity features

Authors: S. Sangeetha; Michael Arock

Addresses: Department of Computer Applications, National Institute of Technology, Tiruchirapalli-620015, Tamilnadu, India. ' Department of Computer Applications, National Institute of Technology, Tiruchirapalli-620015, Tamilnadu, India

Abstract: Owing to the tremendous increase in the number and the length of the text documents, there is a need to locate the needed information in large set of text documents. Locating desired information finds its application in tasks such as information retrieval, question answering, event extraction, etc. The basic operation required to do the above is finding how similar the sentences are in a particular context. This manuscript explains a feature-based machine learning approach to find the semantic similarity between a pair of short sentences. It includes the features such as string match, part of speech, word sense, length difference, negation and modality, etc. Our approach employs dissimilarity features and similarity features to detect sentence similarity.

Keywords: sentence similarity; sentence comparison; paraphrase recognition; text documents; information retrieval; question answering; feature-based machine learning; semantic similarity; dissimilarity features; similarity features.

DOI: 10.1504/IJAIP.2012.048141

International Journal of Advanced Intelligence Paradigms, 2012 Vol.4 No.2, pp.120 - 131

Published online: 23 Aug 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article