Wizard of Oz method for learning dialog agents

Masayuki Okamoto; Yeonsoo Yang; Toru Ishida

Wizard of Oz method for learning dialog agents

Masayuki Okamoto, Yeonsoo Yang, Toru Ishida

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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 language	English
Title of host publication	Cooperative Information Agents V - 5th International Workshop, CIA 2001, Proceedings
Editors	Franco Zambonelli, Matthias Klusch
Publisher	Springer Verlag
Pages	20-25
Number of pages	6
ISBN (Electronic)	3540425454, 9783540425458
Publication status	Published - 2001 Jan 1
Externally published	Yes
Event	5th International Workshop on Cooperative Information Agents, CIA 2001 - Modena, Italy Duration: 2001 Sep 6 → 2001 Sep 8

Publication series

Name	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume	2182
ISSN (Print)	0302-9743

Conference

Conference	5th International Workshop on Cooperative Information Agents, CIA 2001
Country	Italy
City	Modena
Period	01/9/6 → 01/9/8

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

Wizard of Oz method for learning dialog agents. / Okamoto, Masayuki; Yang, Yeonsoo; Ishida, Toru.

Cooperative Information Agents V - 5th International Workshop, CIA 2001, Proceedings. ed. / Franco Zambonelli; Matthias Klusch. Springer Verlag, 2001. p. 20-25 (Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science); Vol. 2182).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science), vol. 2182, Springer Verlag, pp. 20-25, 5th International Workshop on Cooperative Information Agents, CIA 2001, Modena, Italy, 01/9/6.

@inproceedings{ebf3073dfda942ac87982c770079201d,

title = "Wizard of Oz method for learning dialog agents",

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.",

author = "Masayuki Okamoto and Yeonsoo Yang and Toru Ishida",

year = "2001",

month = jan,

day = "1",

language = "English",

series = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

publisher = "Springer Verlag",

pages = "20--25",

editor = "Franco Zambonelli and Matthias Klusch",

booktitle = "Cooperative Information Agents V - 5th International Workshop, CIA 2001, Proceedings",

note = "5th International Workshop on Cooperative Information Agents, CIA 2001 ; Conference date: 06-09-2001 Through 08-09-2001",

}

TY - GEN

T1 - Wizard of Oz method for learning dialog agents

AU - Okamoto, Masayuki

AU - Yang, Yeonsoo

AU - Ishida, Toru

PY - 2001/1/1

Y1 - 2001/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84857778343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857778343&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84857778343

T3 - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

SP - 20

EP - 25

BT - Cooperative Information Agents V - 5th International Workshop, CIA 2001, Proceedings

A2 - Zambonelli, Franco

A2 - Klusch, Matthias

PB - Springer Verlag

T2 - 5th International Workshop on Cooperative Information Agents, CIA 2001

Y2 - 6 September 2001 through 8 September 2001

ER -

Wizard of Oz method for learning dialog agents

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Cite this