A generative attentional neural network model for dialogue act classification

Quan Hung Tran; Ingrid Zukerman; Gholamreza Haffari

doi:10.18653/v1/P17-2083

A generative attentional neural network model for dialogue act classification

Quan Hung Tran, Ingrid Zukerman, Gholamreza Haffari

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

19 Citations (Scopus)

Abstract

We propose a novel generative neural network architecture for Dialogue Act classification. Building upon the Recurrent Neural Network framework, our model incorporates a new attentional technique and a label-to-label connection for sequence learning, akin to Hidden Markov Models. Our experiments show that both of these innovations enable our model to outperform strong baselines for dialogue-act classification on the MapTask and Switchboard corpora. In addition, we analyse empirically the effectiveness of each of these innovations.

Original language	English
Title of host publication	Annual Meeting of the Association for Computational Linguistics 2017
Subtitle of host publication	Short Papers, ACL 2017 - Proceedings
Editors	Regina Barzilay, Min-Yen Kan
Place of Publication	PA USA
Publisher	Association for Computational Linguistics (ACL)
Pages	524-529
Number of pages	6
Volume	2
ISBN (Electronic)	9781945626760
DOIs	https://doi.org/10.18653/v1/P17-2083
Publication status	Published - 2017
Event	Annual Meeting of the Association of Computational Linguistics 2017 - Vancouver, Canada Duration: 30 Jul 2017 → 4 Aug 2017 Conference number: 55th https://www.aclweb.org/anthology/events/acl-2017/ (Proceedings)

Conference

Conference	Annual Meeting of the Association of Computational Linguistics 2017
Abbreviated title	ACL 2017
Country/Territory	Canada
City	Vancouver
Period	30/07/17 → 4/08/17
Internet address	https://www.aclweb.org/anthology/events/acl-2017/ (Proceedings)

Access to Document

10.18653/v1/P17-2083

Cite this

Tran, Q. H., Zukerman, I., & Haffari, G. (2017). A generative attentional neural network model for dialogue act classification. In R. Barzilay, & M.-Y. Kan (Eds.), Annual Meeting of the Association for Computational Linguistics 2017: Short Papers, ACL 2017 - Proceedings (Vol. 2, pp. 524-529). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-2083

Tran, Quan Hung ; Zukerman, Ingrid ; Haffari, Gholamreza. / A generative attentional neural network model for dialogue act classification. Annual Meeting of the Association for Computational Linguistics 2017: Short Papers, ACL 2017 - Proceedings . editor / Regina Barzilay ; Min-Yen Kan. Vol. 2 PA USA : Association for Computational Linguistics (ACL), 2017. pp. 524-529

@inproceedings{65c8869b0bfd4560b227a26006a63e01,

title = "A generative attentional neural network model for dialogue act classification",

abstract = "We propose a novel generative neural network architecture for Dialogue Act classification. Building upon the Recurrent Neural Network framework, our model incorporates a new attentional technique and a label-to-label connection for sequence learning, akin to Hidden Markov Models. Our experiments show that both of these innovations enable our model to outperform strong baselines for dialogue-act classification on the MapTask and Switchboard corpora. In addition, we analyse empirically the effectiveness of each of these innovations.",

author = "Tran, {Quan Hung} and Ingrid Zukerman and Gholamreza Haffari",

year = "2017",

doi = "10.18653/v1/P17-2083",

language = "English",

volume = "2",

pages = "524--529",

editor = "Regina Barzilay and Min-Yen Kan",

booktitle = "Annual Meeting of the Association for Computational Linguistics 2017",

publisher = "Association for Computational Linguistics (ACL)",

note = "Annual Meeting of the Association of Computational Linguistics 2017, ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",

url = "https://www.aclweb.org/anthology/events/acl-2017/",

}

Tran, QH, Zukerman, I & Haffari, G 2017, A generative attentional neural network model for dialogue act classification. in R Barzilay & M-Y Kan (eds), Annual Meeting of the Association for Computational Linguistics 2017: Short Papers, ACL 2017 - Proceedings . vol. 2, Association for Computational Linguistics (ACL), PA USA , pp. 524-529, Annual Meeting of the Association of Computational Linguistics 2017, Vancouver, British Columbia, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-2083

A generative attentional neural network model for dialogue act classification. / Tran, Quan Hung; Zukerman, Ingrid ; Haffari, Gholamreza.
Annual Meeting of the Association for Computational Linguistics 2017: Short Papers, ACL 2017 - Proceedings . ed. / Regina Barzilay; Min-Yen Kan. Vol. 2 PA USA : Association for Computational Linguistics (ACL), 2017. p. 524-529.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - A generative attentional neural network model for dialogue act classification

AU - Tran, Quan Hung

AU - Zukerman, Ingrid

AU - Haffari, Gholamreza

N1 - Conference code: 55th

PY - 2017

Y1 - 2017

N2 - We propose a novel generative neural network architecture for Dialogue Act classification. Building upon the Recurrent Neural Network framework, our model incorporates a new attentional technique and a label-to-label connection for sequence learning, akin to Hidden Markov Models. Our experiments show that both of these innovations enable our model to outperform strong baselines for dialogue-act classification on the MapTask and Switchboard corpora. In addition, we analyse empirically the effectiveness of each of these innovations.

AB - We propose a novel generative neural network architecture for Dialogue Act classification. Building upon the Recurrent Neural Network framework, our model incorporates a new attentional technique and a label-to-label connection for sequence learning, akin to Hidden Markov Models. Our experiments show that both of these innovations enable our model to outperform strong baselines for dialogue-act classification on the MapTask and Switchboard corpora. In addition, we analyse empirically the effectiveness of each of these innovations.

UR - http://www.scopus.com/inward/record.url?scp=85040573388&partnerID=8YFLogxK

U2 - 10.18653/v1/P17-2083

DO - 10.18653/v1/P17-2083

M3 - Conference Paper

AN - SCOPUS:85040573388

VL - 2

SP - 524

EP - 529

BT - Annual Meeting of the Association for Computational Linguistics 2017

A2 - Barzilay, Regina

A2 - Kan, Min-Yen

PB - Association for Computational Linguistics (ACL)

CY - PA USA

T2 - Annual Meeting of the Association of Computational Linguistics 2017

Y2 - 30 July 2017 through 4 August 2017

ER -

A generative attentional neural network model for dialogue act classification

Abstract

Conference

Access to Document

Other files and links

Cite this