Query Expansion with Naive Bayes for Searching Distributed Collections

The proliferation of online information resources increases the importance of effective and efficient distributed searching. However, the problem of word mismatch seriously hurts the effectiveness of distributed information retrieval. Automatic query expansion has been suggested as a technique for dealing with the fundamental issue of word mismatch. In this paper, we propose a method query expansion with Naive Bayes to address the problem, discuss its implementation in IISS system, and present experimental results demonstrating its effectiveness. Such technique not only enhances the discriminatory power of typical queries for choosing the right collections but also hence significantly improves retrieval results.