A discourse strategy is a strategy for communicating with another agent. Designing effective dialogue systems requires designing agents that can choose among discourse strategies. We claim that the design of effective strategies must take cognitive factors into account, propose a new method for testing the hypothesized factors, and present experimental results on an effective strategy for suppo...

A discourse strategy is a strategy for communicating with another agent. Designing eeec-tive dialogue systems requires designing agents that can choose among discourse strategies. We claim that the design of eeective strategies must take cognitive factors into account, propose a new method for testing the hypothesized factors, and present experimental results on an eeective strategy for support...

This paper presents an approach to adaptive dialogue planning in the framework of an intelligent information retrieval system (MIRACLE), which provides semantic access to multimedia information via a WWW interface. The system uses abduction to infer users, interests and dialogue goals: ambiguous user queries are interpreted with respect to the semantic domain model and unexpected dialogue acts ...

In this paper, we outline a data driven approach to mixed initiative dialogue in acoustic user interfaces to databases. We present the knowledge sources that our dialogue planning algorithm needs: the dialogue model, the dialogue history, and the application description. Further, we discuss how the notions of taking, keeping, giving, and relinquishing the turn are reflected in our approach and ...

This paper presents a spoken dialogue framework that helps users in making decisions. Users often do not have a definite goal or criteria for selecting from a list of alternatives. Thus the system has to bridge this knowledge gap and also provide the users with an appropriate alternative together with the reason for this recommendation through dialogue. We present a dialogue state model for suc...

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 corpor...

This paper reports our research concerning dialogue strategies suitable for adoption by a human– computer debating system. We propose a set of strategic heuristics for a computer to adopt to enable it to function as a dialogue participant. In particular, we consider means of assessing the proposed strategy. A system involving two agents in dialogue with each other and a human– agent debate syst...

We describe an implemented spoken-language dialogue system for a travel-planning domain, which accesses a commercially available travel-information web-server and supports a exible mixed-initiative dialogue strategy. We argue, based on data from initial Wizard-of-Oz experiments , that mixed-initiative strategies are appropriate for many types of user, but require more sophisticated architecture...

This study analyzes 39 Atlantic and seven Pacific benthic δC records to characterize obliquity and precession responses in Atlantic overturning since 3 Ma. Regional benthic δC stacks are also analyzed. A major transition in orbital responses is observed at 1.5–1.6 Ma coincident with the first glacial shoaling of Northern Component Water. Since ∼1.5 Ma, the phases of Atlantic benthic δC records ...

This thesis focuses on the problem of scalable optimization of dialogue behaviour in speech-based conversational systems using reinforcement learning. Most previous investigations in dialogue strategy learning have proposed flat reinforcement learning methods, which are more suitable for small-scale spoken dialogue systems. This research formulates the problem in terms of Semi-Markov Decision P...