An Experiment in Intelligent Information Systems: RESEARCHER

The development of very powerful intelligent information systems will require the use of many Artificial Intelligence techniques including some derived by studying human understanding methods. RESEARCHER is a prototype intelligent information system that reads, remembers, generalizes from and answers questions about complex technical texts, patent abstracts in particular. In this paper, we discuss three areas of current research involving RESEARCHER -- the generalization of hierarchically structured representations; the use of long-term memory in text processing, specifically in resolving ambiguity; and the tailoring of answers to questions to the level of expertise of different users. All of these areas are crucial for truly powerful information systems. We outline our methods and give examples of RESEARCHER processing various examples