A stacking gated neural architecture for implicit discourse relation classification

Lianhui Qin; Zhisong Zhang; Hai Zhao

doi:10.18653/v1/d16-1246

A stacking gated neural architecture for implicit discourse relation classification

Lianhui Qin, Zhisong Zhang, Hai Zhao

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

72 Citations (Scopus)

1 Downloads (CityUHK Scholars)

Abstract

Discourse parsing is considered as one of the most challenging natural language processing (NLP) tasks. Implicit discourse relation classification is the bottleneck for discourse parsing. Without the guide of explicit discourse connectives, the relation of sentence pairs are very hard to be inferred. This paper proposes a stacking neural network model to solve the classification problem in which a convolutional neural network (CNN) is utilized for sentence modeling and a collaborative gated neural network (CGNN) is proposed for feature transformation. Our evaluation and comparisons show that the proposed model outperforms previous state-of-the-art systems. © 2016 Association for Computational Linguistics

Original language	English
Title of host publication	EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings
Publisher	ACL Anthology
Pages	2263-2270
ISBN (Print)	9781945626258
DOIs	https://doi.org/10.18653/v1/d16-1246
Publication status	Published - 2016
Externally published	Yes
Event	2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016 - Austin, United States Duration: 1 Nov 2016 → 5 Nov 2016 http://dblp.uni-trier.de/db/conf/emnlp/emnlp2016.html

Publication series

Name	EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference	2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016
Place	United States
City	Austin
Period	1/11/16 → 5/11/16
Internet address	http://dblp.uni-trier.de/db/conf/emnlp/emnlp2016.html

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. 15-ZDA041).

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/d16-1246

316817540.pdfFinal Published version, 497 KBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Qin, L., Zhang, Z., & Zhao, H. (2016). A stacking gated neural architecture for implicit discourse relation classification. In EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 2263-2270). (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings). ACL Anthology. https://doi.org/10.18653/v1/d16-1246

@inproceedings{098104d789c64f39967b4faebcce328f,

title = "A stacking gated neural architecture for implicit discourse relation classification",

abstract = "Discourse parsing is considered as one of the most challenging natural language processing (NLP) tasks. Implicit discourse relation classification is the bottleneck for discourse parsing. Without the guide of explicit discourse connectives, the relation of sentence pairs are very hard to be inferred. This paper proposes a stacking neural network model to solve the classification problem in which a convolutional neural network (CNN) is utilized for sentence modeling and a collaborative gated neural network (CGNN) is proposed for feature transformation. Our evaluation and comparisons show that the proposed model outperforms previous state-of-the-art systems. {\textcopyright} 2016 Association for Computational Linguistics",

author = "Lianhui Qin and Zhisong Zhang and Hai Zhao",

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>.; 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016 ; Conference date: 01-11-2016 Through 05-11-2016",

year = "2016",

doi = "10.18653/v1/d16-1246",

language = "English",

isbn = "9781945626258",

series = "EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings",

publisher = "ACL Anthology",

pages = "2263--2270",

booktitle = "EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings",

address = "Australia",

url = "http://dblp.uni-trier.de/db/conf/emnlp/emnlp2016.html",

}

Qin, L, Zhang, Z & Zhao, H 2016, A stacking gated neural architecture for implicit discourse relation classification. in EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings. EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings, ACL Anthology, pp. 2263-2270, 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, United States, 1/11/16. https://doi.org/10.18653/v1/d16-1246

A stacking gated neural architecture for implicit discourse relation classification. / Qin, Lianhui; Zhang, Zhisong; Zhao, Hai.
EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings. ACL Anthology, 2016. p. 2263-2270 (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings).

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

TY - GEN

T1 - A stacking gated neural architecture for implicit discourse relation classification

AU - Qin, Lianhui

AU - Zhang, Zhisong

AU - Zhao, Hai

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 - 2016

Y1 - 2016

N2 - Discourse parsing is considered as one of the most challenging natural language processing (NLP) tasks. Implicit discourse relation classification is the bottleneck for discourse parsing. Without the guide of explicit discourse connectives, the relation of sentence pairs are very hard to be inferred. This paper proposes a stacking neural network model to solve the classification problem in which a convolutional neural network (CNN) is utilized for sentence modeling and a collaborative gated neural network (CGNN) is proposed for feature transformation. Our evaluation and comparisons show that the proposed model outperforms previous state-of-the-art systems. © 2016 Association for Computational Linguistics

AB - Discourse parsing is considered as one of the most challenging natural language processing (NLP) tasks. Implicit discourse relation classification is the bottleneck for discourse parsing. Without the guide of explicit discourse connectives, the relation of sentence pairs are very hard to be inferred. This paper proposes a stacking neural network model to solve the classification problem in which a convolutional neural network (CNN) is utilized for sentence modeling and a collaborative gated neural network (CGNN) is proposed for feature transformation. Our evaluation and comparisons show that the proposed model outperforms previous state-of-the-art systems. © 2016 Association for Computational Linguistics

UR - http://www.scopus.com/inward/record.url?scp=85040580351&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85040580351&origin=recordpage

U2 - 10.18653/v1/d16-1246

DO - 10.18653/v1/d16-1246

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

SN - 9781945626258

T3 - EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings

SP - 2263

EP - 2270

BT - EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings

PB - ACL Anthology

T2 - 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016

Y2 - 1 November 2016 through 5 November 2016

ER -

A stacking gated neural architecture 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