A two-stage domain selection framework for extensible multi-domain spoken dialogue systems

Mikio Nakano, Shun Sato, Kazunori Komatani, Kyoko Matsuyama, Kotaro Funakoshi, Hiroshi G. Okuno

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

22 Citations (Scopus)

Abstract

This paper describes a general and effective domain selection framework for multi-domain spoken dialogue systems that employ distributed domain experts. The framework consists of two processes: deciding if the current domain continues and estimating the probabilities for selecting other domains. If the current domain does not continue, the domain with the highest activation probability is selected. Since those processes for each domain expert can be designed independently from other experts and can use a large variety of information, the framework achieves both extensibility and robustness against speech recognition errors. The results of an experiment using a corpus of dialogues between humans and a multi-domain dialogue system demonstrate the viability of the proposed framework.

Original languageEnglish
Title of host publicationProceedings of the SIGDIAL 2011 Conference: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Pages18-29
Number of pages12
Publication statusPublished - 2011
Externally publishedYes
Event12th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2011 - Portland, OR
Duration: 2011 Jun 172011 Jun 18

Other

Other12th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2011
CityPortland, OR
Period11/6/1711/6/18

Fingerprint

Spoken Dialogue Systems
Speech recognition
Chemical activation
Continue
Experiments
Dialogue Systems
Speech Recognition
Framework
Viability
Activation
Robustness

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Modelling and Simulation

Cite this

Nakano, M., Sato, S., Komatani, K., Matsuyama, K., Funakoshi, K., & Okuno, H. G. (2011). A two-stage domain selection framework for extensible multi-domain spoken dialogue systems. In Proceedings of the SIGDIAL 2011 Conference: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue (pp. 18-29)

A two-stage domain selection framework for extensible multi-domain spoken dialogue systems. / Nakano, Mikio; Sato, Shun; Komatani, Kazunori; Matsuyama, Kyoko; Funakoshi, Kotaro; Okuno, Hiroshi G.

Proceedings of the SIGDIAL 2011 Conference: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2011. p. 18-29.

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

Nakano, M, Sato, S, Komatani, K, Matsuyama, K, Funakoshi, K & Okuno, HG 2011, A two-stage domain selection framework for extensible multi-domain spoken dialogue systems. in Proceedings of the SIGDIAL 2011 Conference: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue. pp. 18-29, 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2011, Portland, OR, 11/6/17.
Nakano M, Sato S, Komatani K, Matsuyama K, Funakoshi K, Okuno HG. A two-stage domain selection framework for extensible multi-domain spoken dialogue systems. In Proceedings of the SIGDIAL 2011 Conference: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2011. p. 18-29
Nakano, Mikio ; Sato, Shun ; Komatani, Kazunori ; Matsuyama, Kyoko ; Funakoshi, Kotaro ; Okuno, Hiroshi G. / A two-stage domain selection framework for extensible multi-domain spoken dialogue systems. Proceedings of the SIGDIAL 2011 Conference: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2011. pp. 18-29
@inproceedings{9a8d42f295b642dea70b11444e51993b,
title = "A two-stage domain selection framework for extensible multi-domain spoken dialogue systems",
abstract = "This paper describes a general and effective domain selection framework for multi-domain spoken dialogue systems that employ distributed domain experts. The framework consists of two processes: deciding if the current domain continues and estimating the probabilities for selecting other domains. If the current domain does not continue, the domain with the highest activation probability is selected. Since those processes for each domain expert can be designed independently from other experts and can use a large variety of information, the framework achieves both extensibility and robustness against speech recognition errors. The results of an experiment using a corpus of dialogues between humans and a multi-domain dialogue system demonstrate the viability of the proposed framework.",
author = "Mikio Nakano and Shun Sato and Kazunori Komatani and Kyoko Matsuyama and Kotaro Funakoshi and Okuno, {Hiroshi G.}",
year = "2011",
language = "English",
isbn = "9781937284107",
pages = "18--29",
booktitle = "Proceedings of the SIGDIAL 2011 Conference: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue",

}

TY - GEN

T1 - A two-stage domain selection framework for extensible multi-domain spoken dialogue systems

AU - Nakano, Mikio

AU - Sato, Shun

AU - Komatani, Kazunori

AU - Matsuyama, Kyoko

AU - Funakoshi, Kotaro

AU - Okuno, Hiroshi G.

PY - 2011

Y1 - 2011

N2 - This paper describes a general and effective domain selection framework for multi-domain spoken dialogue systems that employ distributed domain experts. The framework consists of two processes: deciding if the current domain continues and estimating the probabilities for selecting other domains. If the current domain does not continue, the domain with the highest activation probability is selected. Since those processes for each domain expert can be designed independently from other experts and can use a large variety of information, the framework achieves both extensibility and robustness against speech recognition errors. The results of an experiment using a corpus of dialogues between humans and a multi-domain dialogue system demonstrate the viability of the proposed framework.

AB - This paper describes a general and effective domain selection framework for multi-domain spoken dialogue systems that employ distributed domain experts. The framework consists of two processes: deciding if the current domain continues and estimating the probabilities for selecting other domains. If the current domain does not continue, the domain with the highest activation probability is selected. Since those processes for each domain expert can be designed independently from other experts and can use a large variety of information, the framework achieves both extensibility and robustness against speech recognition errors. The results of an experiment using a corpus of dialogues between humans and a multi-domain dialogue system demonstrate the viability of the proposed framework.

UR - http://www.scopus.com/inward/record.url?scp=84857746134&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857746134&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84857746134

SN - 9781937284107

SP - 18

EP - 29

BT - Proceedings of the SIGDIAL 2011 Conference: 12th Annual Meeting of the Special Interest Group on Discourse and Dialogue

ER -