A fast and lightweight system for multilingual dependency parsing

Tao Ji; Yuanbin Wu; Man Lan

doi:10.18653/v1/k17-3025

A fast and lightweight system for multilingual dependency parsing

Tao Ji
, 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

1 Scopus citations

Abstract

Following Kiperwasser and Goldberg (2016), we present a multilingual dependency parser with a bidirectional-LSTM (BiLSTM) feature extractor and a multi-layer perceptron (MLP) classifier. We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks. In the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, the official results show that the macro-averaged LAS F1 score of our system Mengest is 61.33%.

Original language	English
Title of host publication	CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task
Subtitle of host publication	Multilingual Parsing from Raw Text to Universal Dependencies
Publisher	Association for Computational Linguistics (ACL)
Pages	237-242
Number of pages	6
ISBN (Electronic)	9781945626708
DOIs	https://doi.org/10.18653/v1/k17-3025
State	Published - 2017
Event	2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017 - Vancouver, Canada Duration: 3 Aug 2017 → 4 Aug 2017

Publication series

Name	CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

Conference

Conference	2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017
Country/Territory	Canada
City	Vancouver
Period	3/08/17 → 4/08/17

Access to Document

10.18653/v1/k17-3025

Cite this

Ji, T., Wu, Y., & Lan, M. (2017). A fast and lightweight system for multilingual dependency parsing. In CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (pp. 237-242). (CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/k17-3025

Ji, Tao ; Wu, Yuanbin ; Lan, Man. / A fast and lightweight system for multilingual dependency parsing. CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics (ACL), 2017. pp. 237-242 (CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies).

@inproceedings{124bbdcc60ba4cf9bc6251e19ec1c7ef,

title = "A fast and lightweight system for multilingual dependency parsing",

abstract = "Following Kiperwasser and Goldberg (2016), we present a multilingual dependency parser with a bidirectional-LSTM (BiLSTM) feature extractor and a multi-layer perceptron (MLP) classifier. We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks. In the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, the official results show that the macro-averaged LAS F1 score of our system Mengest is 61.33\%.",

author = "Tao Ji and Yuanbin Wu and Man Lan",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics.; 2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017 ; Conference date: 03-08-2017 Through 04-08-2017",

year = "2017",

doi = "10.18653/v1/k17-3025",

language = "英语",

series = "CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies",

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

pages = "237--242",

booktitle = "CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task",

address = "澳大利亚",

}

Ji, T, Wu, Y & Lan, M 2017, A fast and lightweight system for multilingual dependency parsing. in CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, Association for Computational Linguistics (ACL), pp. 237-242, 2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017, Vancouver, Canada, 3/08/17. https://doi.org/10.18653/v1/k17-3025

A fast and lightweight system for multilingual dependency parsing. / Ji, Tao; Wu, Yuanbin; Lan, Man.
CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics (ACL), 2017. p. 237-242 (CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 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 - A fast and lightweight system for multilingual dependency parsing

AU - Ji, Tao

AU - Wu, Yuanbin

AU - Lan, Man

PY - 2017

Y1 - 2017

N2 - Following Kiperwasser and Goldberg (2016), we present a multilingual dependency parser with a bidirectional-LSTM (BiLSTM) feature extractor and a multi-layer perceptron (MLP) classifier. We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks. In the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, the official results show that the macro-averaged LAS F1 score of our system Mengest is 61.33%.

AB - Following Kiperwasser and Goldberg (2016), we present a multilingual dependency parser with a bidirectional-LSTM (BiLSTM) feature extractor and a multi-layer perceptron (MLP) classifier. We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks. In the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, the official results show that the macro-averaged LAS F1 score of our system Mengest is 61.33%.

UR - https://www.scopus.com/pages/publications/85073109554

U2 - 10.18653/v1/k17-3025

DO - 10.18653/v1/k17-3025

M3 - 会议稿件

AN - SCOPUS:85073109554

T3 - CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

SP - 237

EP - 242

BT - CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task

PB - Association for Computational Linguistics (ACL)

T2 - 2017 SIGNLL Conference on Computational Natural Language Learning- CoNLL Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, CoNLL 2017

Y2 - 3 August 2017 through 4 August 2017

ER -

Ji T, Wu Y, Lan M. A fast and lightweight system for multilingual dependency parsing. In CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Association for Computational Linguistics (ACL). 2017. p. 237-242. (CoNLL 2017 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies). doi: 10.18653/v1/k17-3025

A fast and lightweight system for multilingual dependency parsing

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this