Effective reformulation of Boolean queries with concept lattices

In this paper we describe an approach, implemented in a system named REFINER, to combining Boolean information retrieval and content-based navigation with concept lattices. When REFINER i s presented with a Boolean query, it builds and displays a portion of the concept lattice associated with the documents being searched centered around the user query. The cluster network displayed by REFINER shows the result of the query along with a set of minimal query refinements/enlargements. REFINER has two main advantages. The first i s that it can be used to improve the effectiveness of Boolean retrieval, because it allows content-driven query reformulation with controlled amount of output. The second is that it has potentials for information exploration, because the displayed network is navigatable. We compared information retrieval using REFINER with conventional Boolean retrieval. The results of an experiment conducted on a medium-sized bibliographic database showed that the performance of REFINER was better than unrefined Boolean retrieval.