A CLASSIFICATION APPROACH TO BOOLEAN QUERY REFORMULATION

One of the difficulties in using current Boolean-based information ret rieval systems is that it is hard for a user, especially a novice, to formulate an effective Boolean query. Query reformulation can be even more difficult and complex than formulation since users often have dif ficulty incorporating the new information gained from the previous sea rch into the next query. In this article, query reformulation is viewe d as a classification problem, that is, classifying documents as eithe r relevant or nonrelevant. A new reformulation algorithm is proposed w hich builds a tree-structured classifier, called a query tree, at each reformulation from a set of feedback documents retrieved from the pre vious search. The query tree can easily be transformed into a Boolean query. The query tree is compared to two query reformulation algorithm s on benchmark test sets (CACM, CISI, and Medlars). In most experiment s, the query tree showed significant improvements in precision over th e two algorithms compared in this study, We attribute this improved pe rformance to the ability of the query tree algorithm to select good se arch terms and to represent the relationships among search terms into a tree structure.