Natural Language Interactions with Art if icial Experts

The aim of this paper is to justify why Natural language (NL) interaction, of a very rich functionality, is critical to the effective use of Expert Systems and to describe what is needed and what has been done to support such interaction. lnteractive functions dis-cussed here include defining terms, paraphrasing, correcting mis-conceptions, avoiding misconceptions, and modifying questions. Natural Language (NL) interfaces to database systems are already proving their worth. They allow users to get at the database facts they want, without the need to become system wizards. In this paper we are primarily concerne