User modeling in spoken dialogue systems to generate flexible guidance

Kazunori Komatani, Shinichi Ueno, Tatsuya Kawahara, Hiroshi G. Okuno

研究成果: Article

28 引用 (Scopus)

抄録

We address the issue of appropriate user modeling to generate cooperative responses to users in spoken dialogue systems. Unlike previous studies that have focused on a user's knowledge, we propose more generalized modeling. We specifically set up three dimensions for user models: the skill level in use of the system, the knowledge level about the target domain, and the degree of urgency. Moreover, the models are automatically derived by decision tree learning using actual dialogue data collected by the system. We obtained reasonable accuracy in classification for all dimensions. Dialogue strategies based on user modeling were implemented on the Kyoto City Bus Information System that was developed at our laboratory. Experimental evaluations revealed that the cooperative responses adapted to each subject type served as good guides for novices without increasing the duration dialogue lasted for skilled users.

元の言語English
ページ(範囲)169-183
ページ数15
ジャーナルUser Modelling and User-Adapted Interaction
15
発行部数1
DOI
出版物ステータスPublished - 2005 3
外部発表Yes

Fingerprint

communication technology
Decision trees
Information systems
dialogue
information system
evaluation
knowledge
learning

ASJC Scopus subject areas

  • Human-Computer Interaction

これを引用

User modeling in spoken dialogue systems to generate flexible guidance. / Komatani, Kazunori; Ueno, Shinichi; Kawahara, Tatsuya; Okuno, Hiroshi G.

:: User Modelling and User-Adapted Interaction, 巻 15, 番号 1, 03.2005, p. 169-183.

研究成果: Article

Komatani, Kazunori ; Ueno, Shinichi ; Kawahara, Tatsuya ; Okuno, Hiroshi G. / User modeling in spoken dialogue systems to generate flexible guidance. :: User Modelling and User-Adapted Interaction. 2005 ; 巻 15, 番号 1. pp. 169-183.
@article{564c34a888594ac3a8cf299cf21df485,
title = "User modeling in spoken dialogue systems to generate flexible guidance",
abstract = "We address the issue of appropriate user modeling to generate cooperative responses to users in spoken dialogue systems. Unlike previous studies that have focused on a user's knowledge, we propose more generalized modeling. We specifically set up three dimensions for user models: the skill level in use of the system, the knowledge level about the target domain, and the degree of urgency. Moreover, the models are automatically derived by decision tree learning using actual dialogue data collected by the system. We obtained reasonable accuracy in classification for all dimensions. Dialogue strategies based on user modeling were implemented on the Kyoto City Bus Information System that was developed at our laboratory. Experimental evaluations revealed that the cooperative responses adapted to each subject type served as good guides for novices without increasing the duration dialogue lasted for skilled users.",
keywords = "Cooperative response, Decision tree learning, Dialogue strategy, Online user modeling, Spoken dialogue system",
author = "Kazunori Komatani and Shinichi Ueno and Tatsuya Kawahara and Okuno, {Hiroshi G.}",
year = "2005",
month = "3",
doi = "10.1007/s11257-004-5659-0",
language = "English",
volume = "15",
pages = "169--183",
journal = "User Modeling and User-Adapted Interaction",
issn = "0924-1868",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - User modeling in spoken dialogue systems to generate flexible guidance

AU - Komatani, Kazunori

AU - Ueno, Shinichi

AU - Kawahara, Tatsuya

AU - Okuno, Hiroshi G.

PY - 2005/3

Y1 - 2005/3

N2 - We address the issue of appropriate user modeling to generate cooperative responses to users in spoken dialogue systems. Unlike previous studies that have focused on a user's knowledge, we propose more generalized modeling. We specifically set up three dimensions for user models: the skill level in use of the system, the knowledge level about the target domain, and the degree of urgency. Moreover, the models are automatically derived by decision tree learning using actual dialogue data collected by the system. We obtained reasonable accuracy in classification for all dimensions. Dialogue strategies based on user modeling were implemented on the Kyoto City Bus Information System that was developed at our laboratory. Experimental evaluations revealed that the cooperative responses adapted to each subject type served as good guides for novices without increasing the duration dialogue lasted for skilled users.

AB - We address the issue of appropriate user modeling to generate cooperative responses to users in spoken dialogue systems. Unlike previous studies that have focused on a user's knowledge, we propose more generalized modeling. We specifically set up three dimensions for user models: the skill level in use of the system, the knowledge level about the target domain, and the degree of urgency. Moreover, the models are automatically derived by decision tree learning using actual dialogue data collected by the system. We obtained reasonable accuracy in classification for all dimensions. Dialogue strategies based on user modeling were implemented on the Kyoto City Bus Information System that was developed at our laboratory. Experimental evaluations revealed that the cooperative responses adapted to each subject type served as good guides for novices without increasing the duration dialogue lasted for skilled users.

KW - Cooperative response

KW - Decision tree learning

KW - Dialogue strategy

KW - Online user modeling

KW - Spoken dialogue system

UR - http://www.scopus.com/inward/record.url?scp=21444440253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21444440253&partnerID=8YFLogxK

U2 - 10.1007/s11257-004-5659-0

DO - 10.1007/s11257-004-5659-0

M3 - Article

AN - SCOPUS:21444440253

VL - 15

SP - 169

EP - 183

JO - User Modeling and User-Adapted Interaction

JF - User Modeling and User-Adapted Interaction

SN - 0924-1868

IS - 1

ER -