The Use of Sentence Similarity as a Semantic Relevance Metric for Question Answering

Marco De Boni and Suresh Manandhar

An algorithm for calculating semantic similarity between sentences using a variety of linguistic information is presented and applied to the problem of Question Answering. This semantic similarity measure is used in order to determine the semantic relevance of an answer in respect to a question. The algorithm is evaluated against the TREC Question Answering test-bed and is shown to be useful in determining possible answers to a question. Not all linguistic information is shown to be useful, however, and an in-depth analysis shows that certain sentence features are more important than others in determining relevance.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.