Implementing Fuzziness in Dialogue Systems
نویسنده
چکیده
A problem which must be dealt with by any reasonably general computer simulation of the cognitive processes underlying natural language dialogue behaviour is the inherent fuzziness of natural language and human thought. Artificial Intelligence (AI) research has to date achieved nothing approaching a general formal treatment covering all aspects of fuzziness. Surveys of AI approaches to the problems of vagueness can be found in WAHLSTER (1977) and PRADE (1979).
منابع مشابه
Incremental Development of Diagnostic Set-Covering Models with Therapy Effects
We will consider set–covering models for diagnostic tasks handling uncertain knowledge. Because these models have to be build manually by domain experts, we will show how this effort can be reduced by an incremental development of the set–covering models. Thus simple models can be enhanced by similarities, weights and uncertainty to increase the quality of the knowledge and the resulting system...
متن کاملModeling Lateral Communication in Holonic Multi Agent Systems
Agents, in a multi agent system, communicate with each other through the process of exchanging messages which is called dialogue. Multi agent organization is generally used to optimize agents’ communications. Holonic organization demonstrates a self-similar recursive and hierarchical structure in which each holon may include some other holons. In a holonic system, lateral communication occurs b...
متن کاملInteractive Communication Management in an Issue-based Dialogue System
We first give an overview of Interactive Communication Management (ICM), and especially feedback, in humanhuman communication. We then select a limited range of ICM behaviour useful for dialogue systems, and show how these utterances and responses to them are managed in a dialogue system implementing a theory of issue-based dialogue management.
متن کاملIdentifying Effective Moves in Tutoring: On the Refinement of Dialogue Act Annotation Schemes
The rich natural language dialogue that is exchanged between tutors and students has inspired many successful lines of research on tutorial dialogue systems. Yet, today’s tutorial dialogue systems do not regularly achieve the same level of student learning gain as has been observed with expert human tutors. Implementing models directly informed by, and even machine-learned from, human-human tut...
متن کاملAdding Dialogue to the Virtual Storyteller
The Virtual Storyteller is an interactive storytelling system in development at the University of Twente. Currently, this system does not include dialogue between agents. For creating interesting stories, dialogue is a very important aspect. This paper tries to find a way of implementing dialogue in the Virtual Storyteller by looking into other interactive storytelling systems such as FearNot! ...
متن کامل