A refined end-to-end discourse parser

Jianxiang Wang; Man Lan

A refined end-to-end discourse parser

Jianxiang Wang
, Man Lan^*

^*Corresponding author for this work

School of Computer Science and Technology

East China Normal University

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

61 Scopus citations

Abstract

The CoNLL-2015 shared task focuses on shallow discourse parsing, which takes a piece of newswire text as input and returns the discourse relations in a PDTB style. In this paper, we describe our discourse parser that participated in the shared task. We use 9 components to construct the whole parser to identify discourse connectives, label arguments and classify the sense of Explicit or Non-Explicit relations in free texts. Compared to previous discourse parser, new components and features are added in our system, which further improves the overall performance of the discourse parser. Our parser ranks the first on two test datasets, i.e., PDTB Section 23 and a blind test dataset.

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	17-24
Number of pages	8
ISBN (Electronic)	1932432671, 9781932432671
State	Published - 2014
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

@inproceedings{3bedfe11b62d4e4082bc10a4320352e4,

title = "A refined end-to-end discourse parser",

abstract = "The CoNLL-2015 shared task focuses on shallow discourse parsing, which takes a piece of newswire text as input and returns the discourse relations in a PDTB style. In this paper, we describe our discourse parser that participated in the shared task. We use 9 components to construct the whole parser to identify discourse connectives, label arguments and classify the sense of Explicit or Non-Explicit relations in free texts. Compared to previous discourse parser, new components and features are added in our system, which further improves the overall performance of the discourse parser. Our parser ranks the first on two test datasets, i.e., PDTB Section 23 and a blind test dataset.",

author = "Jianxiang Wang and Man Lan",

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 = "英语",

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

publisher = "Curran Associates Inc.",

pages = "17--24",

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

address = "美国",

}

Wang, J & Lan, M 2014, A refined end-to-end discourse parser. 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. 17-24, 19th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2015, Beijing, China, 30/07/15.

A refined end-to-end discourse parser. / Wang, Jianxiang; Lan, Man.
CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task. Curran Associates Inc., 2014. p. 17-24 (CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings of the Shared Task).

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

TY - GEN

T1 - A refined end-to-end discourse parser

AU - Wang, Jianxiang

AU - Lan, Man

PY - 2014

Y1 - 2014

N2 - The CoNLL-2015 shared task focuses on shallow discourse parsing, which takes a piece of newswire text as input and returns the discourse relations in a PDTB style. In this paper, we describe our discourse parser that participated in the shared task. We use 9 components to construct the whole parser to identify discourse connectives, label arguments and classify the sense of Explicit or Non-Explicit relations in free texts. Compared to previous discourse parser, new components and features are added in our system, which further improves the overall performance of the discourse parser. Our parser ranks the first on two test datasets, i.e., PDTB Section 23 and a blind test dataset.

AB - The CoNLL-2015 shared task focuses on shallow discourse parsing, which takes a piece of newswire text as input and returns the discourse relations in a PDTB style. In this paper, we describe our discourse parser that participated in the shared task. We use 9 components to construct the whole parser to identify discourse connectives, label arguments and classify the sense of Explicit or Non-Explicit relations in free texts. Compared to previous discourse parser, new components and features are added in our system, which further improves the overall performance of the discourse parser. Our parser ranks the first on two test datasets, i.e., PDTB Section 23 and a blind test dataset.

UR - https://www.scopus.com/pages/publications/85011836091

M3 - 会议稿件

AN - SCOPUS:85011836091

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

SP - 17

EP - 24

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 -

A refined end-to-end discourse parser

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this