Importance-Driven Turn-Bidding for spoken dialogue systems

Ethan O. Selfridge, Peter Heeman

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

24 Citations (Scopus)

Abstract

Current turn-taking approaches for spoken dialogue systems rely on the speaker releasing the turn before the other can take it. This reliance results in restricted interactions that can lead to inefficient dialogues. In this paper we present a model we refer to as Importance-Driven Turn-Bidding that treats turn-taking as a negotiative process. Each conversant bids for the turn based on the importance of the intended utterance, and Reinforcement Learning is used to indirectly learn this parameter. We find that Importance-Driven Turn-Bidding performs better than two current turntaking approaches in an artificial collaborative slot-filling domain. The negotiative nature of this model creates efficient dialogues, and supports the improvement of mixed-initiative interaction.

Original languageEnglish (US)
Title of host publicationACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Pages177-185
Number of pages9
StatePublished - 2010
Event48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Uppsala, Sweden
Duration: Jul 11 2010Jul 16 2010

Other

Other48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
CountrySweden
CityUppsala
Period7/11/107/16/10

Fingerprint

communication technology
dialogue
interaction
reinforcement
learning
Spoken Dialogue Systems
Turn-taking
Interaction
Utterance
Artificial
Reliance
Reinforcement Learning

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Selfridge, E. O., & Heeman, P. (2010). Importance-Driven Turn-Bidding for spoken dialogue systems. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 177-185)

Importance-Driven Turn-Bidding for spoken dialogue systems. / Selfridge, Ethan O.; Heeman, Peter.

ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 177-185.

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

Selfridge, EO & Heeman, P 2010, Importance-Driven Turn-Bidding for spoken dialogue systems. in ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. pp. 177-185, 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, Uppsala, Sweden, 7/11/10.
Selfridge EO, Heeman P. Importance-Driven Turn-Bidding for spoken dialogue systems. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 177-185
Selfridge, Ethan O. ; Heeman, Peter. / Importance-Driven Turn-Bidding for spoken dialogue systems. ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. pp. 177-185
@inproceedings{255c46e16a954595884e13f04194c68f,
title = "Importance-Driven Turn-Bidding for spoken dialogue systems",
abstract = "Current turn-taking approaches for spoken dialogue systems rely on the speaker releasing the turn before the other can take it. This reliance results in restricted interactions that can lead to inefficient dialogues. In this paper we present a model we refer to as Importance-Driven Turn-Bidding that treats turn-taking as a negotiative process. Each conversant bids for the turn based on the importance of the intended utterance, and Reinforcement Learning is used to indirectly learn this parameter. We find that Importance-Driven Turn-Bidding performs better than two current turntaking approaches in an artificial collaborative slot-filling domain. The negotiative nature of this model creates efficient dialogues, and supports the improvement of mixed-initiative interaction.",
author = "Selfridge, {Ethan O.} and Peter Heeman",
year = "2010",
language = "English (US)",
isbn = "9781617388088",
pages = "177--185",
booktitle = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Importance-Driven Turn-Bidding for spoken dialogue systems

AU - Selfridge, Ethan O.

AU - Heeman, Peter

PY - 2010

Y1 - 2010

N2 - Current turn-taking approaches for spoken dialogue systems rely on the speaker releasing the turn before the other can take it. This reliance results in restricted interactions that can lead to inefficient dialogues. In this paper we present a model we refer to as Importance-Driven Turn-Bidding that treats turn-taking as a negotiative process. Each conversant bids for the turn based on the importance of the intended utterance, and Reinforcement Learning is used to indirectly learn this parameter. We find that Importance-Driven Turn-Bidding performs better than two current turntaking approaches in an artificial collaborative slot-filling domain. The negotiative nature of this model creates efficient dialogues, and supports the improvement of mixed-initiative interaction.

AB - Current turn-taking approaches for spoken dialogue systems rely on the speaker releasing the turn before the other can take it. This reliance results in restricted interactions that can lead to inefficient dialogues. In this paper we present a model we refer to as Importance-Driven Turn-Bidding that treats turn-taking as a negotiative process. Each conversant bids for the turn based on the importance of the intended utterance, and Reinforcement Learning is used to indirectly learn this parameter. We find that Importance-Driven Turn-Bidding performs better than two current turntaking approaches in an artificial collaborative slot-filling domain. The negotiative nature of this model creates efficient dialogues, and supports the improvement of mixed-initiative interaction.

UR - http://www.scopus.com/inward/record.url?scp=84859977792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859977792&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84859977792

SN - 9781617388088

SP - 177

EP - 185

BT - ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

ER -