In the recent years, the research on the dialogue system becomes more and more important. The performance of the automatic speech recognizer of the dialogue system is unsatisfied because of bad recognizing performance for spontaneous utterance. To solve this problem, this paper proposed an automatic speech recognition strategy directed by the semantic knowledge in dialogue system. The main idea...

Although it is now possible to build real-time spoken dialogue systems for a wide variety of applications, designing the dialogue strategy of such systems involves a number of nontrivial design choices. These choices can seriously impact system performance, and include choosing appropriate strategies for initiative (whether to accept relatively open-ended versus constrained user utterances) and...

Several features of spoken dialogue systems require advanced reference resolution strategies. This paper presents a knowledge–based strategy for reference resolution implemented over an agent architecture which differentiates the Knowledge and Action Managers from the Dialogue Manager. The strategy, in conjunction with the ability of the Dialogue Manager to manipulate the dialogue history, has ...

Designing the dialogue strategy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing dialogue strategy. We first present a practical methodology that addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We then demonstrate how we have used t...

Partially observable Markov decision processes (POMDPs) have gained significant interest in research on spoken dialogue systems, due to among many benefits its ability to naturally model the dialogue strategy selection problem under the unreliability in automated speech recognition. However, the POMDP approaches are essentially model-based, and as a result, the dialogue strategy computed from P...

From a system developer’s perspective, designing a spoken dialogue system can be a time-consuming and difficult process. A developer may spend a lot of time anticipating how a potential user might interact with the system and then deciding on the most appropriate system response. These decisions are encoded in a dialogue strategy, essentially a mapping between anticipated user inputs and approp...

Formal models of dialogue systems and related notions (dialogue, dialogue strategy, evaluation function, dialogue communication, goal of dialogue) are introduced in the paper. A model of the information retrieval dialogue systems based on the dialogue strategies described by the Mealy-type automata and information systems (in the sense of Pawlak) is introduced and discussed.

In this paper we introduce a stochastic model for dialogue systems based on Markov decision process. Within this framework we show that the problem of dialogue strategy design can be stated as an optimization problem, and solved by a variety of methods, including the reinforcement learning approach. The advantages of this new paradigm include objective evaluation of dialogue systems and their a...

Adapting Spoken Dialogue Systems to the user is supposed to result in more efficient and successful dialogues. In this work, we present an evaluation of a quality-adaptive strategy with a user simulator adapting the dialogue initiative dynamically during the ongoing interaction and show that it outperforms conventional non-adaptive strategies and a random strategy. Furthermore, we indicate a co...

We propose a novel approach to developing a dialogue model that is able to take into account some aspects of the user's affective state and to act appropriately. Our dialogue model uses a Partially Observable Markov Decision Process approach with observations composed of the observed user's affective state and action. A simple example of route navigation is explained to clarify our approach. Th...