Generation of Query-Biased Concepts Using Content and Structure for Query Reformulation

This paper proposes an approach for query reformulation based on the generation of appropriate query-biased concepts. Query-biased concepts are generated from retrieved documents using their content and structure. In this paper, we focus on three aspects of the concept generation; the selection of query-biased concepts from retrieved documents, the effect of the structure, and the number of retrieved documents used for generating the concepts.