Intelligent Search of Full-Text Databases

This project applies expert system technology to the task of searching online collections of documents . We are developing an intelligent search intermediary to help end-users locate relevant passages in large fulltext databases. Our expert system will automatically reformulate conte.xtual Boolean queries to improve search results and will present re~rieved passages in decreasing order of relevance. It differs from other intelligent database functions in two ways: it works with semantically unprocessed tex't and the expert systems contains a knowledge base of search strategies independent of any particular content domain. The goals for our current project are to demonstrate the feasibility of the approach and to evaluate the effectiveness of the system through a controlled experiment. While the work we report here has limited objectives, the system and techniques are general a.nd can be extended ~o large, real-world databases.