Multistream Recognition of Dialogue Acts in Meetings

Alfred Dielmann; Steve Renals

doi:10.1007/11965152_16

Multistream Recognition of Dialogue Acts in Meetings

Alfred Dielmann, Steve Renals

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

Abstract

We propose a joint segmentation and classification approach for the dialogue act recognition task on natural multi-party meetings (ICSI Meeting Corpus). Five broad DA categories are automatically recognised using a generative Dynamic Bayesian Network based infrastructure. Prosodic features and a switching graphical model are used to estimate DA boundaries, in conjunction with a factored language model which is used to relate words and DA categories. This easily generalizable and extensible system promotes a rational approach to the joint DA segmentation and recognition task, and is capable of good recognition performance.

Original language	English
Title of host publication	Machine Learning for Multimodal Interaction
Subtitle of host publication	Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers
Editors	Steve Renals, Samy Bengio, Jonathan G. Fiscus
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	178-189
Number of pages	12
ISBN (Electronic)	978-3-540-69268-3
ISBN (Print)	978-3-540-69267-6
DOIs	https://doi.org/10.1007/11965152_16
Publication status	Published - 2006
Event	Third International Workshop MLMI 2006 - Bethesda, MD, United States Duration: 1 May 2006 → 4 May 2006

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Berlin Heidelberg
Volume	4299
ISSN (Print)	0302-9743

Workshop

Workshop	Third International Workshop MLMI 2006
Country/Territory	United States
City	Bethesda, MD
Period	1/05/06 → 4/05/06

Access to Document

10.1007/11965152_16

dielmann-mlmi06Submitted manuscript, 92.3 KB

http://dx.doi.org/10.1007/11965152_16

Cite this

Dielmann, A., & Renals, S. (2006). Multistream Recognition of Dialogue Acts in Meetings. In S. Renals, S. Bengio, & J. G. Fiscus (Eds.), Machine Learning for Multimodal Interaction: Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers (pp. 178-189). (Lecture Notes in Computer Science; Vol. 4299). Springer. https://doi.org/10.1007/11965152_16

Dielmann, Alfred ; Renals, Steve. / Multistream Recognition of Dialogue Acts in Meetings. Machine Learning for Multimodal Interaction: Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers. editor / Steve Renals ; Samy Bengio ; Jonathan G. Fiscus. Berlin, Heidelberg : Springer, 2006. pp. 178-189 (Lecture Notes in Computer Science).

@inbook{afe667b1ac664cf2b22fe8495d5d6a49,

title = "Multistream Recognition of Dialogue Acts in Meetings",

abstract = "We propose a joint segmentation and classification approach for the dialogue act recognition task on natural multi-party meetings (ICSI Meeting Corpus). Five broad DA categories are automatically recognised using a generative Dynamic Bayesian Network based infrastructure. Prosodic features and a switching graphical model are used to estimate DA boundaries, in conjunction with a factored language model which is used to relate words and DA categories. This easily generalizable and extensible system promotes a rational approach to the joint DA segmentation and recognition task, and is capable of good recognition performance.",

author = "Alfred Dielmann and Steve Renals",

year = "2006",

doi = "10.1007/11965152\_16",

language = "English",

isbn = "978-3-540-69267-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "178--189",

editor = "Steve Renals and Samy Bengio and Fiscus, \{Jonathan G.\}",

booktitle = "Machine Learning for Multimodal Interaction",

address = "United Kingdom",

note = "Third International Workshop MLMI 2006 ; Conference date: 01-05-2006 Through 04-05-2006",

}

Dielmann, A & Renals, S 2006, Multistream Recognition of Dialogue Acts in Meetings. in S Renals, S Bengio & JG Fiscus (eds), Machine Learning for Multimodal Interaction: Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers. Lecture Notes in Computer Science, vol. 4299, Springer, Berlin, Heidelberg, pp. 178-189, Third International Workshop MLMI 2006, Bethesda, MD, United States, 1/05/06. https://doi.org/10.1007/11965152_16

Multistream Recognition of Dialogue Acts in Meetings. / Dielmann, Alfred; Renals, Steve.
Machine Learning for Multimodal Interaction: Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers. ed. / Steve Renals; Samy Bengio; Jonathan G. Fiscus. Berlin, Heidelberg: Springer, 2006. p. 178-189 (Lecture Notes in Computer Science; Vol. 4299).

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

TY - CHAP

T1 - Multistream Recognition of Dialogue Acts in Meetings

AU - Dielmann, Alfred

AU - Renals, Steve

PY - 2006

Y1 - 2006

N2 - We propose a joint segmentation and classification approach for the dialogue act recognition task on natural multi-party meetings (ICSI Meeting Corpus). Five broad DA categories are automatically recognised using a generative Dynamic Bayesian Network based infrastructure. Prosodic features and a switching graphical model are used to estimate DA boundaries, in conjunction with a factored language model which is used to relate words and DA categories. This easily generalizable and extensible system promotes a rational approach to the joint DA segmentation and recognition task, and is capable of good recognition performance.

AB - We propose a joint segmentation and classification approach for the dialogue act recognition task on natural multi-party meetings (ICSI Meeting Corpus). Five broad DA categories are automatically recognised using a generative Dynamic Bayesian Network based infrastructure. Prosodic features and a switching graphical model are used to estimate DA boundaries, in conjunction with a factored language model which is used to relate words and DA categories. This easily generalizable and extensible system promotes a rational approach to the joint DA segmentation and recognition task, and is capable of good recognition performance.

U2 - 10.1007/11965152_16

DO - 10.1007/11965152_16

M3 - Chapter

SN - 978-3-540-69267-6

T3 - Lecture Notes in Computer Science

SP - 178

EP - 189

BT - Machine Learning for Multimodal Interaction

A2 - Renals, Steve

A2 - Bengio, Samy

A2 - Fiscus, Jonathan G.

PB - Springer

CY - Berlin, Heidelberg

T2 - Third International Workshop MLMI 2006

Y2 - 1 May 2006 through 4 May 2006

ER -

Dielmann A, Renals S. Multistream Recognition of Dialogue Acts in Meetings. In Renals S, Bengio S, Fiscus JG, editors, Machine Learning for Multimodal Interaction: Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers. Berlin, Heidelberg: Springer. 2006. p. 178-189. (Lecture Notes in Computer Science). doi: 10.1007/11965152_16

Multistream Recognition of Dialogue Acts in Meetings

Abstract

Publication series

Workshop

Access to Document

Fingerprint

Cite this