ANTNLP at Conll 2018 shared task: A Graph-based Parser for Universal Dependency Parsing

Tao Ji; Yufang Liu; Yijun Wang; Yuanbin Wu; Man Lan

doi:10.18653/v1/K18-2025

ANTNLP at Conll 2018 shared task: A Graph-based Parser for Universal Dependency Parsing

Tao Ji
, Yufang Liu
, Yijun Wang
, Yuanbin Wu
, Man Lan

School of Computer Science and Technology

East China Normal University

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

3 Scopus citations

Abstract

We describe the graph-based dependency parser in our system (AntNLP) submitted to the CoNLL 2018 UD Shared Task. We use bidirectional lstm to get the word representation, then a bi-affine pointer networks to compute scores of candidate dependency edges and the MST algorithm to get the final dependency tree. From the official testing results, our system gets 70.90 LAS F1 score (rank 9/26), 55.92 MLAS (10/26) and 60.91 BLEX (8/26).

Original language	English
Title of host publication	CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task
Subtitle of host publication	Multilingual Parsing from Raw Text to Universal Dependencies
Publisher	Association for Computational Linguistics (ACL)
Pages	248-255
Number of pages	8
ISBN (Electronic)	9781948087827
DOIs	https://doi.org/10.18653/v1/K18-2025
State	Published - 2018
Event	2018 SIGNLL Conference on Computational Natural Language Learning, CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2018 - Brussels, Belgium Duration: 31 Oct 2018 → 1 Nov 2018

Publication series

Name	CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

Conference

Conference	2018 SIGNLL Conference on Computational Natural Language Learning, CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2018
Country/Territory	Belgium
City	Brussels
Period	31/10/18 → 1/11/18

Access to Document

10.18653/v1/K18-2025

Cite this

Ji, T., Liu, Y., Wang, Y., Wu, Y., & Lan, M. (2018). ANTNLP at Conll 2018 shared task: A Graph-based Parser for Universal Dependency Parsing. In CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (pp. 248-255). (CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/K18-2025

Ji, Tao ; Liu, Yufang ; Wang, Yijun et al. / ANTNLP at Conll 2018 shared task : A Graph-based Parser for Universal Dependency Parsing. CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics (ACL), 2018. pp. 248-255 (CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies).

@inproceedings{fd118997cb2142018aaf8a75740c3346,

title = "ANTNLP at Conll 2018 shared task: A Graph-based Parser for Universal Dependency Parsing",

abstract = "We describe the graph-based dependency parser in our system (AntNLP) submitted to the CoNLL 2018 UD Shared Task. We use bidirectional lstm to get the word representation, then a bi-affine pointer networks to compute scores of candidate dependency edges and the MST algorithm to get the final dependency tree. From the official testing results, our system gets 70.90 LAS F1 score (rank 9/26), 55.92 MLAS (10/26) and 60.91 BLEX (8/26).",

author = "Tao Ji and Yufang Liu and Yijun Wang and Yuanbin Wu and Man Lan",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 2018 SIGNLL Conference on Computational Natural Language Learning, CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2018 ; Conference date: 31-10-2018 Through 01-11-2018",

year = "2018",

doi = "10.18653/v1/K18-2025",

language = "英语",

series = "CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies",

publisher = "Association for Computational Linguistics (ACL)",

pages = "248--255",

booktitle = "CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task",

address = "澳大利亚",

}

Ji, T, Liu, Y, Wang, Y, Wu, Y & Lan, M 2018, ANTNLP at Conll 2018 shared task: A Graph-based Parser for Universal Dependency Parsing. in CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Association for Computational Linguistics (ACL), pp. 248-255, 2018 SIGNLL Conference on Computational Natural Language Learning, CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2018, Brussels, Belgium, 31/10/18. https://doi.org/10.18653/v1/K18-2025

ANTNLP at Conll 2018 shared task: A Graph-based Parser for Universal Dependency Parsing. / Ji, Tao; Liu, Yufang; Wang, Yijun et al.
CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics (ACL), 2018. p. 248-255 (CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies).

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

TY - GEN

T1 - ANTNLP at Conll 2018 shared task

T2 - 2018 SIGNLL Conference on Computational Natural Language Learning, CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2018

AU - Ji, Tao

AU - Liu, Yufang

AU - Wang, Yijun

AU - Wu, Yuanbin

AU - Lan, Man

PY - 2018

Y1 - 2018

N2 - We describe the graph-based dependency parser in our system (AntNLP) submitted to the CoNLL 2018 UD Shared Task. We use bidirectional lstm to get the word representation, then a bi-affine pointer networks to compute scores of candidate dependency edges and the MST algorithm to get the final dependency tree. From the official testing results, our system gets 70.90 LAS F1 score (rank 9/26), 55.92 MLAS (10/26) and 60.91 BLEX (8/26).

AB - We describe the graph-based dependency parser in our system (AntNLP) submitted to the CoNLL 2018 UD Shared Task. We use bidirectional lstm to get the word representation, then a bi-affine pointer networks to compute scores of candidate dependency edges and the MST algorithm to get the final dependency tree. From the official testing results, our system gets 70.90 LAS F1 score (rank 9/26), 55.92 MLAS (10/26) and 60.91 BLEX (8/26).

UR - https://www.scopus.com/pages/publications/85072898965

U2 - 10.18653/v1/K18-2025

DO - 10.18653/v1/K18-2025

M3 - 会议稿件

AN - SCOPUS:85072898965

T3 - CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

SP - 248

EP - 255

BT - CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task

PB - Association for Computational Linguistics (ACL)

Y2 - 31 October 2018 through 1 November 2018

ER -

Ji T, Liu Y, Wang Y, Wu Y, Lan M. ANTNLP at Conll 2018 shared task: A Graph-based Parser for Universal Dependency Parsing. In CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics (ACL). 2018. p. 248-255. (CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies). doi: 10.18653/v1/K18-2025

ANTNLP at Conll 2018 shared task: A Graph-based Parser for Universal Dependency Parsing

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this