The DCU discourse parser for connective, argument identification and explicit sense classification

Longyue Wang; Chris Hokamp; Tsuyoshi Okita; Xiaojun Zhang; Qun Liu

The DCU discourse parser for connective, argument identification and explicit sense classification

Longyue Wang, Chris Hokamp, Tsuyoshi Okita, Xiaojun Zhang, Qun Liu

Dublin City University

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

9 Citations (Scopus)

Abstract

This paper describes our submission to the CoNLL-2015 shared task on discourse parsing. We factor the pipeline into sub-components which are then used to form the final sequential architecture. Focusing on achieving good performance when inferring explicit discourse relations, we apply maximum entropy and recurrent neural networks to different sub-tasks such as connective identification, argument extraction, and sense classification. The our final system achieves 16.51%, 12.73% and 11.15% overall F1 scores on the dev, WSJ and blind test sets, respectively.

Original language	English
Title of host publication	CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task
Publisher	Curran Associates Inc.
Pages	89-94
Number of pages	6
ISBN (Electronic)	1932432671, 9781932432671
Publication status	Published - 2014
Externally published	Yes
Event	19th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2015 - Beijing, China Duration: 30 Jul 2015 → 31 Jul 2015

Publication series

Name	CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task

Conference

Conference	19th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2015
Country/Territory	China
City	Beijing
Period	30/07/15 → 31/07/15

Cite this

Wang, L., Hokamp, C., Okita, T., Zhang, X., & Liu, Q. (2014). The DCU discourse parser for connective, argument identification and explicit sense classification. In CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task (pp. 89-94). (CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task). Curran Associates Inc..

Wang, Longyue ; Hokamp, Chris ; Okita, Tsuyoshi et al. / The DCU discourse parser for connective, argument identification and explicit sense classification. CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. Curran Associates Inc., 2014. pp. 89-94 (CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task).

@inproceedings{7c0bd427be3e4252ad71d9e43b922a6f,

title = "The DCU discourse parser for connective, argument identification and explicit sense classification",

abstract = "This paper describes our submission to the CoNLL-2015 shared task on discourse parsing. We factor the pipeline into sub-components which are then used to form the final sequential architecture. Focusing on achieving good performance when inferring explicit discourse relations, we apply maximum entropy and recurrent neural networks to different sub-tasks such as connective identification, argument extraction, and sense classification. The our final system achieves 16.51%, 12.73% and 11.15% overall F1 scores on the dev, WSJ and blind test sets, respectively.",

author = "Longyue Wang and Chris Hokamp and Tsuyoshi Okita and Xiaojun Zhang and Qun Liu",

note = "Publisher Copyright: {\textcopyright} 2014 Association for Computational Linguistics.; 19th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2015 ; Conference date: 30-07-2015 Through 31-07-2015",

year = "2014",

language = "English",

series = "CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task",

publisher = "Curran Associates Inc.",

pages = "89--94",

booktitle = "CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task",

}

Wang, L, Hokamp, C, Okita, T, Zhang, X & Liu, Q 2014, The DCU discourse parser for connective, argument identification and explicit sense classification. in CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task, Curran Associates Inc., pp. 89-94, 19th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2015, Beijing, China, 30/07/15.

The DCU discourse parser for connective, argument identification and explicit sense classification. / Wang, Longyue; Hokamp, Chris; Okita, Tsuyoshi et al.
CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. Curran Associates Inc., 2014. p. 89-94 (CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task).

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

TY - GEN

T1 - The DCU discourse parser for connective, argument identification and explicit sense classification

AU - Wang, Longyue

AU - Hokamp, Chris

AU - Okita, Tsuyoshi

AU - Zhang, Xiaojun

AU - Liu, Qun

PY - 2014

Y1 - 2014

N2 - This paper describes our submission to the CoNLL-2015 shared task on discourse parsing. We factor the pipeline into sub-components which are then used to form the final sequential architecture. Focusing on achieving good performance when inferring explicit discourse relations, we apply maximum entropy and recurrent neural networks to different sub-tasks such as connective identification, argument extraction, and sense classification. The our final system achieves 16.51%, 12.73% and 11.15% overall F1 scores on the dev, WSJ and blind test sets, respectively.

AB - This paper describes our submission to the CoNLL-2015 shared task on discourse parsing. We factor the pipeline into sub-components which are then used to form the final sequential architecture. Focusing on achieving good performance when inferring explicit discourse relations, we apply maximum entropy and recurrent neural networks to different sub-tasks such as connective identification, argument extraction, and sense classification. The our final system achieves 16.51%, 12.73% and 11.15% overall F1 scores on the dev, WSJ and blind test sets, respectively.

UR - http://www.scopus.com/inward/record.url?scp=84973379014&partnerID=8YFLogxK

M3 - Conference Proceeding

AN - SCOPUS:84973379014

T3 - CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task

SP - 89

EP - 94

BT - CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task

PB - Curran Associates Inc.

T2 - 19th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2015

Y2 - 30 July 2015 through 31 July 2015

ER -

Wang L, Hokamp C, Okita T, Zhang X, Liu Q. The DCU discourse parser for connective, argument identification and explicit sense classification. In CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. Curran Associates Inc. 2014. p. 89-94. (CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task).

The DCU discourse parser for connective, argument identification and explicit sense classification

Abstract

Publication series

Conference

Other files and links

Cite this