Using case based retrieval techniques for handling anomalous situations in advisory dialogues

Abstract

The efficacy of expert systems often depends on the accuracy and completeness of the problem specification negotiated with the user. Therefore, efficient user interfaces are needed, in order to assist the user in identifying and supplying the required data. Our approach presented in this paper is based on the utilisation of conversational interfaces, giving users the possibility of interacting with the system by means of natural language. Through the use of flexible dialogue management plans and an advanced problem solving strategy based on case based reasoning and information retrieval, efficient user guidance during the interaction with an expert system can be achieved. Thus, the user can interactively develop a comprehensive and coherent specification of his problem, based on clarifications, explanations, and context-based factual information provided by the system. As an application framework we introduce the EU-funded Project VIP-Advisor whose objective is the development of a virtual insurance and finance assistant capable of natural language interaction. © Springer-Verlag Berlin Heidelberg 2004.