Wizard of Oz method for learning dialog agents

Masayuki Okamoto, Yeonsoo Yang, Toru Ishida

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

19 Citations (Scopus)


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
EditorsMatthias Klusch, Franco Zambonelli
PublisherSpringer Verlag
Number of pages6
ISBN (Electronic)3540425454, 9783540425458
Publication statusPublished - 2001
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)
ISSN (Print)0302-9743


Conference5th International Workshop on Cooperative Information Agents, CIA 2001

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)


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

Cite this