Query expansion using explicit semantic analysis

  • Authors:

  • Jing Luo;Bo Meng;Maofu Liu;Xinhui Tu;Kui Zhang

  • Affiliations:

  • Wuhan University, China and Wuhan University of Science and Technology, China;Wuhan University, China;Wuhan University of Science and Technology, China;Wuhan University of Science and Technology, China;Wuhan University of Science and Technology, China

  • Venue:
  • Proceedings of the 4th International Conference on Internet Multimedia Computing and Service
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Query expansion is a technique utilized within information retrieval to solve word mismatch between queries and document. In previous method, expansion words are usually selected by counting word co-occurrences in the documents. However, word co-occurrences are not always a good indicator for relevance, whereas some are background words of the whole collection. In order to select good expansion words, explicit semantic analysis (ESA) is adopted in our model to estimate two kinds of relevance weight. One is the relevance weight between query and its relevant word extracted from the top-ranked documents in initial retrieval results. The other is the relevance weight between each query word and its relevant words extracted from the snapshot of Google search result when that query word is used as search keyword. The estimated relevance weights are used to select good expansion words for second retrieval. The experiments on the three test collections show that our expansion words selection model is more effective than the standard Rocchio expansion.