Within the broad field of spoken dialogue systems, the application of machine-learning approaches to dialogue management strategy design is a rapidly growing research area. The main motivation is the hope of building systems that learn through trial-and-error interaction what constitutes a good dialogue strategy. Training of such systems could in theory be done using human users or using corpora of human–computer dialogue, but in practice the typically vast space of possible dialogue states and strategies cannot be explored without the use of automatic user simulation tools.

This requirement for training statistical dialogue models has created an interesting new application area for predictive statistical user modelling and a variety of different techniques for simulating user behaviour have been presented in the literature ranging from simple Markov models to Bayesian networks. The development of reliable user simulation tools is critical to further progress on automatic dialogue management design but it holds many challenges, some of which have been encountered in other areas of current research on statistical user modelling, such as the problem of ‘concept drift’, the problem of combining content-based and collaboration-based modelling techniques, and user model evaluation. The latter topic is of particular interest, because simulation-based learning is currently one of the few applications of statistical user modelling that employs both direct ‘accuracy-based’ and indirect ‘utility-based’ evaluation techniques.

In this paper, we briefly summarize the role of the dialogue manager in a spoken dialogue system, give a short introduction to reinforcement-learning of dialogue management strategies and review the literature on user modelling for simulation-based strategy learning. We further describe recent work on user model evaluation and discuss some of the current research issues in simulation-based learning from a user modelling perspective.

This work examines the interplay of inter-personal and inter-organizational trust, two distinct but related concepts, through a theoretic inter-organizational trust-based security model for a multi-agent system information-sharing community. A calculus that mathematically models trust building at the inter-organizational level is at the heart of this model. In inter-organizational or inter-firm exchange, the role of the boundary spanner, an organizational representative, is important in reducing asymmetries that may exist between the two parties. Trust is a crucial component to the dyadic interaction at the inter-personal or boundary spanner level, and the trust established at this level also affects the overall quality of the relationship at the inter-organizational level. Trust, as an aspect of social control, is thus viewed as a more effective mechanism for security in an open, distributed system, like an information-sharing community. The inter-organizational trust-based security model proposed herein represents a soft security approach. It affords several important benefits over traditional hard security mechanisms used in open systems — robustness, scalability, and adaptability. The inter-organizational trust-based model is an important contribution to the computational security community, as other open systems applications of a distributed or pervasive nature could adapt it and realize its benefits. It is also one of a few attempts to model trust building at either the inter-organizational or inter-personal level.

This article reviews formal systems that regulate persuasion dialogues. In such dialogues two or more participants aim to resolve a difference of opinion, each trying to persuade the other participants to adopt their point of view. Systems for persuasion dialogue have found application in various fields of computer science, such as non-monotonic logic, artificial intelligence and law, multi-agent systems, intelligent tutoring and computer-supported collaborative argumentation. Taking a game-theoretic view on dialogue systems, this review proposes a formal specification of the main elements of dialogue systems for persuasion and then uses it to critically review some of the main formal systems for persuasion. The focus of this review will be on regulating the interaction between agents rather than on the design and behaviour of individual agents within a dialogue.