Techniques for Information Retrieval Using an Inferential Question-Answering System with Natural-Language Input
by Coles, L. Stephen
Technical Note 74
Institution: AI Center, SRI International
Address: 333 Ravenswood Ave, Menlo Park, CA 94025
Note: SRI Project 8696. The research reported herein was sponsored by the National Science Foundation under Grant GN-895.
Most conventional computer information-retrieval systems are limited by rigid data structures, inflexible query languages, and the lack of conversational error-recovery procedures. Computer question-answering systems designed to overcome one or more of these limitations have been built, but for the most part they have been restricted to small data bases. This report describes the current state of a two-year research project aimed toward combining and extending recently developed question-answering techniques to reasonably large data files.
|Coles, L. Stephen||Alumnus|