Wizard of Oz method for learning dialog agents

Masayuki Okamoto, Yeonsoo Yang, Toru Ishida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

This paper describes a framework to construct interface agents with example dialogs based on the tasks by the machine learning technology. The Wizard of Oz method is used to collect example dialogs, and a finite state machine-based model is used for the dialog model. We implemented a Web-based system which includes these functions, and empirically examined the system which treats with a guide task in Kyoto through the experimental use.

Original languageEnglish
Title of host publicationCooperative Information Agents V - 5th International Workshop, CIA 2001, Proceedings
EditorsFranco Zambonelli, Matthias Klusch
PublisherSpringer Verlag
Pages20-25
Number of pages6
ISBN (Electronic)3540425454, 9783540425458
Publication statusPublished - 2001 Jan 1
Externally publishedYes
Event5th International Workshop on Cooperative Information Agents, CIA 2001 - Modena, Italy
Duration: 2001 Sep 62001 Sep 8

Publication series

NameLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume2182
ISSN (Print)0302-9743

Conference

Conference5th International Workshop on Cooperative Information Agents, CIA 2001
CountryItaly
CityModena
Period01/9/601/9/8

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Wizard of Oz method for learning dialog agents'. Together they form a unique fingerprint.

  • Cite this

    Okamoto, M., Yang, Y., & Ishida, T. (2001). Wizard of Oz method for learning dialog agents. In F. Zambonelli, & M. Klusch (Eds.), Cooperative Information Agents V - 5th International Workshop, CIA 2001, Proceedings (pp. 20-25). (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 2182). Springer Verlag.