Shallow discourse parsing using convolutional neural network

Lianhui Qin; Zhisong Zhang; Hai Zhao

doi:10.18653/v1/k16-2010

Shallow discourse parsing using convolutional neural network

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

36 Citations (Scopus)

1 Downloads (CityUHK Scholars)

Abstract

This paper describes a discourse parsing system for our participation in the CoNLL 2016 Shared Task. We focus on the supplementary task: Sense Classification, especially the Non-Explicit one which is the bottleneck of discourse parsing system. To improve Non-Explicit sense classification, we propose a Convolutional Neural Network (CNN) model to determine the senses for both English and Chinese tasks. We also explore a traditional linear model with novel dependency features for Explicit sense classification. Compared with the best system in CoNLL-2015, our system achieves competitive performances. Moreover, as shown in the results, our system has higher F1 score on Non-Explicit sense classification. © 2016 Association for Computational Linguistics.

Original language	English
Title of host publication	Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016
Publisher	ACL Anthology
Pages	70-77
ISBN (Print)	1932432663, 9781932432664
DOIs	https://doi.org/10.18653/v1/k16-2010
Publication status	Published - 2016
Externally published	Yes
Event	20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016 - Berlin, Germany Duration: 7 Aug 2016 → 12 Aug 2016 http://dblp.uni-trier.de/db/conf/conll/conll2016st.html

Publication series

Name	Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016

Conference

Conference	20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016
Place	Germany
City	Berlin
Period	7/08/16 → 12/08/16
Internet address	http://dblp.uni-trier.de/db/conf/conll/conll2016st.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 sup- ported by Cai Yuanpei Program (CSC No. 201304490199 and No. 201304490171), National Natural Science Foundation of China (No. 61170114 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/k16-2010

316817385.pdfFinal Published version, 3.08 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Qin, L., Zhang, Z., & Zhao, H. (2016). Shallow discourse parsing using convolutional neural network. In Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016 (pp. 70-77). (Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016). ACL Anthology. https://doi.org/10.18653/v1/k16-2010

@inproceedings{83faa292da76488fbd2f42a3ccbe882d,

title = "Shallow discourse parsing using convolutional neural network",

abstract = "This paper describes a discourse parsing system for our participation in the CoNLL 2016 Shared Task. We focus on the supplementary task: Sense Classification, especially the Non-Explicit one which is the bottleneck of discourse parsing system. To improve Non-Explicit sense classification, we propose a Convolutional Neural Network (CNN) model to determine the senses for both English and Chinese tasks. We also explore a traditional linear model with novel dependency features for Explicit sense classification. Compared with the best system in CoNLL-2015, our system achieves competitive performances. Moreover, as shown in the results, our system has higher F1 score on Non-Explicit sense classification. {\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>.; 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016 ; Conference date: 07-08-2016 Through 12-08-2016",

year = "2016",

doi = "10.18653/v1/k16-2010",

language = "English",

isbn = "1932432663",

series = "Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016",

publisher = "ACL Anthology",

pages = "70--77",

booktitle = "Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016",

address = "Australia",

url = "http://dblp.uni-trier.de/db/conf/conll/conll2016st.html",

}

Qin, L, Zhang, Z & Zhao, H 2016, Shallow discourse parsing using convolutional neural network. in Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016. Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016, ACL Anthology, pp. 70-77, 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016, Berlin, Germany, 7/08/16. https://doi.org/10.18653/v1/k16-2010

Shallow discourse parsing using convolutional neural network. / Qin, Lianhui; Zhang, Zhisong; Zhao, Hai.
Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016. ACL Anthology, 2016. p. 70-77 (Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016).

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

TY - GEN

T1 - Shallow discourse parsing using convolutional neural network

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 - This paper describes a discourse parsing system for our participation in the CoNLL 2016 Shared Task. We focus on the supplementary task: Sense Classification, especially the Non-Explicit one which is the bottleneck of discourse parsing system. To improve Non-Explicit sense classification, we propose a Convolutional Neural Network (CNN) model to determine the senses for both English and Chinese tasks. We also explore a traditional linear model with novel dependency features for Explicit sense classification. Compared with the best system in CoNLL-2015, our system achieves competitive performances. Moreover, as shown in the results, our system has higher F1 score on Non-Explicit sense classification. © 2016 Association for Computational Linguistics.

AB - This paper describes a discourse parsing system for our participation in the CoNLL 2016 Shared Task. We focus on the supplementary task: Sense Classification, especially the Non-Explicit one which is the bottleneck of discourse parsing system. To improve Non-Explicit sense classification, we propose a Convolutional Neural Network (CNN) model to determine the senses for both English and Chinese tasks. We also explore a traditional linear model with novel dependency features for Explicit sense classification. Compared with the best system in CoNLL-2015, our system achieves competitive performances. Moreover, as shown in the results, our system has higher F1 score on Non-Explicit sense classification. © 2016 Association for Computational Linguistics.

UR - http://www.scopus.com/inward/record.url?scp=85021693727&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85021693727&origin=recordpage

U2 - 10.18653/v1/k16-2010

DO - 10.18653/v1/k16-2010

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

SN - 1932432663

SN - 9781932432664

T3 - Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016

SP - 70

EP - 77

BT - Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016

PB - ACL Anthology

T2 - 20th SIGNLL Conference on Computational Natural Language Learning: Shared Task, CoNLL 2016

Y2 - 7 August 2016 through 12 August 2016

ER -

Shallow discourse parsing using convolutional neural network

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