Adversarial connective-exploiting networks for implicit discourse relation classification

Lianhui Qin; Zhisong Zhang; Hai Zhao; Zhiting Hu; Eric P. Xing

doi:10.18653/v1/P17-1093

Adversarial connective-exploiting networks for implicit discourse relation classification

Lianhui Qin, Zhisong Zhang, Hai Zhao, Zhiting Hu, Eric P. Xing

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

78 Citations (Scopus)

1 Downloads (CityUHK Scholars)

Abstract

Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator. Our method effectively transfers discriminability of connectives to the implicit features, and achieves state-of-the-art performance on the PDTB benchmark. © 2017 Association for Computational Linguistics.

Original language	English
Title of host publication	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Publisher	ACL Anthology
Pages	1006-1017
Volume	1
ISBN (Print)	9781945626753
DOIs	https://doi.org/10.18653/v1/P17-1093
Publication status	Published - 2017
Externally published	Yes
Event	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada Duration: 30 Jul 2017 → 4 Aug 2017 http://acl2017.org/

Publication series

Name	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume	1

Conference

Conference	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Place	Canada
City	Vancouver
Period	30/07/17 → 4/08/17
Internet address	http://acl2017.org/

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to <a href="mailto:[email protected]">[email protected]</a>.

Funding

This paper was partially supported by Cai Yuanpei Program (CSC No. 201304490199 and No. 201304490171), National Natural Science Foundation of China (No. 61170114, No. 61672343 and No. 61272248), National Basic Research Program of China (No. 2013CB329401), Major Basic Research Program of Shanghai Science and Technology Committee (No. 15JC1400103), Art and Science Interdisciplinary Funds of Shanghai Jiao Tong University (No. 14JCRZ04), and Key Project of National Society Science Foundation of China (No. 15ZDA041).

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.18653/v1/P17-1093

316817512.pdfFinal Published version, 1.95 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Qin, L., Zhang, Z., Zhao, H., Hu, Z., & Xing, E. P. (2017). Adversarial connective-exploiting networks for implicit discourse relation classification. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 1, pp. 1006-1017). (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1). ACL Anthology. https://doi.org/10.18653/v1/P17-1093

Qin, Lianhui ; Zhang, Zhisong ; Zhao, Hai et al. / Adversarial connective-exploiting networks for implicit discourse relation classification. ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1 ACL Anthology, 2017. pp. 1006-1017 (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).

@inproceedings{1f1de6fd21c54bb0bacec0a26d281f7b,

title = "Adversarial connective-exploiting networks for implicit discourse relation classification",

abstract = "Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator. Our method effectively transfers discriminability of connectives to the implicit features, and achieves state-of-the-art performance on the PDTB benchmark. {\textcopyright} 2017 Association for Computational Linguistics.",

author = "Lianhui Qin and Zhisong Zhang and Hai Zhao and Zhiting Hu and Xing, {Eric P.}",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to <a href={"}mailto:[email protected]{"}>[email protected]</a>.; 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",

year = "2017",

doi = "10.18653/v1/P17-1093",

language = "English",

isbn = "9781945626753",

volume = "1",

series = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

publisher = "ACL Anthology",

pages = "1006--1017",

booktitle = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

address = "Australia",

url = "http://acl2017.org/",

}

Qin, L, Zhang, Z, Zhao, H, Hu, Z & Xing, EP 2017, Adversarial connective-exploiting networks for implicit discourse relation classification. in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). vol. 1, ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 1, ACL Anthology, pp. 1006-1017, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-1093

Adversarial connective-exploiting networks for implicit discourse relation classification. / Qin, Lianhui; Zhang, Zhisong; Zhao, Hai et al.
ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1 ACL Anthology, 2017. p. 1006-1017 (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Adversarial connective-exploiting networks for implicit discourse relation classification

AU - Qin, Lianhui

AU - Zhang, Zhisong

AU - Zhao, Hai

AU - Hu, Zhiting

AU - Xing, Eric P.

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to <a href="mailto:[email protected]">[email protected]</a>.

PY - 2017

Y1 - 2017

N2 - Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator. Our method effectively transfers discriminability of connectives to the implicit features, and achieves state-of-the-art performance on the PDTB benchmark. © 2017 Association for Computational Linguistics.

AB - Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract similarly salient features for accurate classification. We develop an adversarial model to enable an adaptive imitation scheme through competition between the implicit network and a rival feature discriminator. Our method effectively transfers discriminability of connectives to the implicit features, and achieves state-of-the-art performance on the PDTB benchmark. © 2017 Association for Computational Linguistics.

UR - http://www.scopus.com/inward/record.url?scp=85038378060&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85038378060&origin=recordpage

U2 - 10.18653/v1/P17-1093

DO - 10.18653/v1/P17-1093

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781945626753

VL - 1

T3 - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

SP - 1006

EP - 1017

BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

PB - ACL Anthology

T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

Y2 - 30 July 2017 through 4 August 2017

ER -

Qin L, Zhang Z, Zhao H, Hu Z, Xing EP. Adversarial connective-exploiting networks for implicit discourse relation classification. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1. ACL Anthology. 2017. p. 1006-1017. (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)). doi: 10.18653/v1/P17-1093

Adversarial connective-exploiting networks for implicit discourse relation classification

Abstract

Publication series

Conference

Bibliographical note

Funding

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this