Exploring Multiple Ontologies and WordNet Framework to Expand Query for Question Answering System

Abstract

Query expansion plays a very important role in enhancing the performance of the Question Answering Systems. There are several methods proposed for query expansion and the use of ontologies has been the latest and popular choice of the researchers because of its effectiveness in building conceptual query. However most of these query expansion methods have used either a single domain specific ontology or WordNet and none of research work has been reported the use of ontologies and WordNet together. In the context of Worldwide Web based Question Answering Systems, the use of single ontology or WordNet has not proved to be sufficient to retrieve wide variety of heterogeneous information. In this paper, we have proposed an efficient query expansion method that uses multiple ontologies retrieved from semantic web search engine such as Swoogle and combines them with WordNet to disambiguate the context. We have experimented on a set of 300 questions collected from TREC and other resources to judge the accuracy of the proposed method. We have shown results using Google as well as with respect to few existing popular web-based Question Answering Systems like START, AnswerBus, BrainBoost, and Inferret.