Query reformulation strategies for an intelligent search intermediary

The authors describe an intelligent search intermediary to help end-users locate relevant passages in large online full-text databases. Passage retrieval has advantages in efficiency and effectiveness over traditional document retrieval yet is more computationally tractable than question-answering systems under development by researchers in artificial intelligence. However, casual users need assistance with search strategies for full-text databases. The authors provide an expert system which automatically reformulates contextual Boolean queries to improve search results and ranks the retrieved passages in decreasing order of estimated relevance. It differs from other intelligent database functions in two ways: it works with semantically and syntactically unprocessed text and the expert system contains a knowledge base of domain-independent search strategies. A simple search scenario is presented.<
>