Context Representation and Reasoning for Managing Spoken Dialogue
نویسنده
چکیده
In interactive systems, the ~dialogue manager’ isa central component, whose primary task is to decide what o do next in a dialogue. This decision i volves taking a variety ofkinds of context information nto account, with different logical properties, u ed in different types of reasoning, andtherefore with different demands onrepresentation. In this paper we discuss the representation of the context information needed to support intelligent dialogue management in interactive speech systems. We argue that simple types of context information should be represented in a way that optimally supports efficient simple forms of reasoning, while other types of context information require sophisticated logics for articulate representation and full-blown reasoning. Using different types of representation for different types of context information creates a problem in situations where a type of context information, that is adequately represented in a very simple form most of the time, exceptionally requires articulate representation and sophisticated reasoning. We indicate how this problem can be resolved, and how a dialogue manager can use several forms of context representation and reasoning for generating dialogue acts, by clearly distinguishing the different ways in which dialogue acts may be constructed and the conditions under which a particular construction is to be used.
منابع مشابه
Generic Architecture for Natural Language Generation in Spoken Human-computer Dialogue
The human-computer dialogue field is nowadays a rather developed technology and research branch in its own right, but consensus hat not been reached yet with respect to several issues. Out of these, several aspects related to answer generation in spoken natural language are addressed in this paper. First, a modular architecture integrated into a distributed, agent-based dialogue framework and i...
متن کاملContextual Reasoning in Multimodal Dialogue Systems: Two Case Studies
This paper describes an approach to contextual reasoning for interpretation of spoken multimodal dialogue. The approach is based on combining recencybased search for antecedents with an object-oriented domain representation in such a way that the search is highly constrained by the type information of the antecedents. By furthermore representing candidate antecedents from the dialogue history a...
متن کاملOn-Line Learning of a Persian Spoken Dialogue System Using Real Training Data
The first spoken dialogue system developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (g) on the learning speed...
متن کاملOn-Line Learning of a Persian Spoken Dialogue System Using Real Training Data
The first spoken dialogue system developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (g) on the learning speed...
متن کاملInteroperability and Knowledge Representation in Distributed Health and Fitness Companion Dialogue System
As spoken dialogue systems move beyond task oriented dialogues and become distributed in the pervasive computing environments, their growing complexity calls for more modular structures. When different aspects of a single system can be accessed with different interfaces, knowledge representation and separation of low level interaction modeling from high level reasoning on domain level becomes i...
متن کامل