FIRST: Fuzzy Information Retrieval SysTem

Abstract

This paper discusses modelling, design and imple mentation issues for a knowledge-based information retrieval system Both the domain knowledge representation and the inference mechanism are based upon a fuzzy set theoretical framework The system manages natural language queries and returns a ranked set of relevant documents, computing for each of them a degree of support depending on multiple sources of evidence. In the following, after a brief remark about the need for modelling the inherent imprecision associated with the retrieval process, a model based on fuzzy reasoning is proposed. Then the architecture is presented of FIRST, a prototype system which is intended as an experimental test-bed for the applica tion of intelligent techniques in order to improve the effective ness of information retrieval systems Finally, we discuss im plementation details with reference to the retrieval component and related strategies that have been developed to reduce the impact of using imprecise knowledge upon the computational efficiency of the system.