Explanation in Expert Systemss: A Survey

Abstract : In order to be considered useful and acceptable, expert systems must be able to explain their knowledge of the domain and the reasoning process they employ to produce results and recommendations. Despite the fact that the need for explanation has been widely recognized, current expert systems have only limited explanatory capabilities. In this survey, we review early approaches to explanation in expert systems and discuss their limitations. We discuss improvements to the explanation capabilities based on enriched knowledge bases of expert systems. We then argue that further improvements in explanation require better generation techniques. Related work in the field of natural language generation suggests techniques that are useful to the task of explanation in expert systems; however, even those techniques will not provide all of the capabilities required for the task of carrying on a dialogue with the user. Finally, we describe our approach to explanation, which provides the facilities necessary to carry on an interactive dialogue with the user.