The learning of dialogue strategies in spoken dialogue systems using reinforcement learning is a promising approach to acquire robust dialogue strategies. However, the trade-off between available dialogue data and information in the dialogue state either forces information to be excluded from the state representations or requires large amount of training data. In this paper, we propose to use d...

We present FLoReS, a new information-state based dialogue manager, making use of forward inference, local dialogue structure, and plan operators representing sub-dialogue structure. The aim is to support both advanced, flexible, mixed initiative interaction and efficient policy creation by domain experts. The dialogue manager has been used for two characters in the SimCoach project, and is curr...

We present a proof system which implements dialogue logic as originally developed by Lorenzen. Intuitionistic and classic logic are pre-de ned. A rule language allows to easily de ne dialogue rules for other logics. DiaLog provides multi-sorted logic. The system supports fully automated and interactive proof search. A user-friendly graphical interface displays the dialogue tableau, a dialogue t...

Abstract. We implemented a generic dialogue shell that can be configured for and applied to domain-specific dialogue applications. A toolbox for ontology-based dialogue engineering provides a technical solution for the two challenges of engineering ontological domain extensions and debugging functional modules. We support a rapid implementation cycle until the dialogue systems works robustly fo...

This paper presents a first draft methodology for the development and evaluation of dialogue management for spoken dialogue systems (SLDSs). Dialogue management is arguably the core functionality of SLDSs because the dialogue manager tends to have the controlling function of the system as a whole and maintains a model of the evolving dialogue context. The paper is based on DISC Working Paper D1...

Spoken Language Understanding (SLU) is a key component of goal oriented dialogue systems that would parse user utterances into semantic frame representations. Traditionally SLU does not utilize the dialogue history beyond the previous system turn and contextual ambiguities are resolved by the downstream components. In this paper, we explore novel approaches for modeling dialogue context in a re...

Spoken dialogue systems promise eecient and natural access to a large variety of information sources and services from any phone. However, current spoken dialogue systems are deecient in their strategies for preventing, identifying and repairing problems that arise in the conversation. This paper reports results on automatically training a Problematic Dialogue Predictor to predict problematic h...

Intelligent information systems are expected to interpret the users' information needs semantically, taking the dialogue context into account. Whereas many research prototypes attempt to address the semantic interpretation of queries, only a few try to reason about other aspects of the user's individual dialogue behavior. This paper introduces an approach to context-dependent interpretation of ...

In current dialogue systems, user utterances are often verified by the system to make sure the system heard the user right. While this mechanism is useful and important in dialogue systems, it covers only a small part of the spectrum of interactive communication management (ICM) devices occuring in human-human dialogue. A view of the full range of ICM dialogue moves can be useful for suggesting...

This paper presents a novel method that controls a dialogue between a spoken dialogue system and a user efficiently so that the system responds as helpfully as possible within the limits of its knowledge. Due to speech recognition errors, a system and user must engage in a “confirmation dialogue” to clarify a user’s request. Although a confirmation dialogue is unavoidable, it should be as conci...