Separating Representation, Reasoning, and Implementation for Interaction Management

Foster, M. E. and Petrick, R. P. A. (2016) Separating Representation, Reasoning, and Implementation for Interaction Management. In: International Workshop on Spoken Dialogue Systems (IWSDS2016), Saariselkä, Finland, 13-16 Jan 2016,

[img] Text
113607.pdf - Accepted Version
Restricted to Repository staff only

98kB

Publisher's URL: http://www.uni-ulm.de/in/iwsds2016/workshop/introduction.html

Abstract

Numerous toolkits are available for developing speech-based dialogue systems. Many of these toolkits include not only a method for representing states and actions, but also a mechanism for reasoning and selecting the actions, often combined with a technical framework designed to simplify the task of creating end-to-end systems. This tight coupling of representation, reasoning, and implementation makes it difficult both to compare different approaches, as well as to analyse the properties of individual techniques. We contrast this situation with the state of the art in a related research area---AI planning---where a set of common representations have been defined and are widely used to enable direct comparison of different reasoning approaches. We argue that adopting a similar separation would greatly benefit the dialogue research community.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Foster, Dr Mary Ellen
Authors: Foster, M. E., and Petrick, R. P. A.
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
College/School:College of Science and Engineering > School of Computing Science

University Staff: Request a correction | Enlighten Editors: Update this record