Query expansion using WordNet in N-layer vector space model

Abstract

Information Retrieval is concerned with the identification of documents in the collection that are relevant to users information needs. Queries formed by user are generally short and vague which makes it difficult to estimate the exact user need. Information retrieval may improve their effectiveness by using process of query expansion, which automatically adds new terms to the original query posed by the user. In this paper, a new technique is proposed based on WordNet for N-layer vector space approach. WordNet is an online lexical dictionary which describes word semantic relationships in terms of Synset. New query expansion approach is proposed to use semantic relationship while adding new terms. The concept of term association is used to mine out the word from semantic relation. The result shows that N-layer vector space model with proposed query expansion approach improves precision by approximately 5% and recall is improved by approximately 20%.