Towards integration of cognitive models in dialogue management: Designing the virtual negotiation coach application

Abstract

This paper presents an approach to flexible and adaptive dialogue management driven by cog-nitive modelling of human dialogue behaviour. Artificial intelligent agents, based on the ACT-Rcognitive architecture, together with human actors are participating in a (meta)cognitive skills train-ing within a negotiation scenario. The agent employs instance-based learning to decide about itsown actions and to reflect on the behaviour of the opponent. We show that task-related actionscan be handled by a cognitive agent who is a plausible dialogue partner. Separating task-relatedand dialogue control actions enables the application of sophisticated models along with a flexiblearchitecture in which various alternative modelling methods can be combined. We evaluated theproposed approach with users assessing the relative contribution of various factors to the overallusability of a dialogue system. Subjective perception of effectiveness, efficiency and satisfactionwere correlated with various objective performance metrics, e.g. number of (in)appropriate sys-tem responses, recovery strategies, and interaction pace. It was observed that the dialogue systemusability is determined most by the quality of agreements reached in terms of estimated Paretooptimality, by the user’s negotiation strategies selected, and by the quality of system recognition,interpretation and responses. We compared human-human and human-agent performance withrespect to the number and quality of agreements reached, estimated cooperativeness level, and fre-quency of accepted negative outcomes. Evaluation experiments showed promising, consistentlypositive results throughout the range of the relevant scales.