Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing

Hai Zhao; Wenliang Chen; Chunyu Kit; Guodong Zhou

Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing

Hai Zhao
, Wenliang Chen
, Chunyu Kit
, Guodong Zhou

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

26 Citations (Scopus)

51 Downloads (CityUHK Scholars)

Abstract

This paper describes our system about multilingual semantic dependency parsing (SRLonly) for our participation in the shared task of CoNLL-2009. We illustrate that semantic dependency parsing can be transformed into a word-pair classification problem and implemented as a single-stage machine learning system. For each input corpus, a large scale feature engineering is conducted to select the best fit feature template set incorporated with a proper argument pruning strategy. The system achieved the top average score in the closed challenge: 80.47% semantic labeled F1 for the average score. © 2009 Association for Computational Linguistics.

Original language	English
Title of host publication	Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009)
Subtitle of host publication	Shared Task
Editors	Jan Hajič
Publisher	Association for Computational Linguistics
Pages	55-60
Publication status	Published - Jun 2009
Event	13th Conference on Computational Natural Language Learning, CoNLL 2009 - Boulder, CO, United States Duration: 4 Jun 2009 → 4 Jun 2009 https://aclanthology.org/W09-12

Publication series

Name	CoNLL- Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task

Conference

Conference	13th Conference on Computational Natural Language Learning, CoNLL 2009
Place	United States
City	Boulder, CO
Period	4/06/09 → 4/06/09
Internet address	https://aclanthology.org/W09-12

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-SA 3.0. https://creativecommons.org/licenses/by-nc-sa/3.0/

Access Output

5954335.pdfFinal Published version, 485 KBLicence: CC BY-NC-SA

https://aclanthology.org/W09-1208

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zhao, H., Chen, W., Kit, C., & Zhou, G. (2009). Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing. In J. Hajič (Ed.), Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task (pp. 55-60). (CoNLL- Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task). Association for Computational Linguistics. https://aclanthology.org/W09-1208

Zhao, Hai ; Chen, Wenliang ; Kit, Chunyu et al. / Multilingual dependency learning : A huge feature engineering method to semantic dependency parsing. Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task. editor / Jan Hajič . Association for Computational Linguistics, 2009. pp. 55-60 (CoNLL- Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task).

@inproceedings{5d3c2251080b49968192919a169cf8a9,

title = "Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing",

abstract = "This paper describes our system about multilingual semantic dependency parsing (SRLonly) for our participation in the shared task of CoNLL-2009. We illustrate that semantic dependency parsing can be transformed into a word-pair classification problem and implemented as a single-stage machine learning system. For each input corpus, a large scale feature engineering is conducted to select the best fit feature template set incorporated with a proper argument pruning strategy. The system achieved the top average score in the closed challenge: 80.47\% semantic labeled F1 for the average score. {\textcopyright} 2009 Association for Computational Linguistics.",

author = "Hai Zhao and Wenliang Chen and Chunyu Kit and Guodong Zhou",

year = "2009",

month = jun,

language = "English",

series = "CoNLL- Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task",

publisher = "Association for Computational Linguistics",

pages = "55--60",

editor = "\{Haji{\v c} \}, Jan",

booktitle = "Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009)",

address = "United States",

note = "13th Conference on Computational Natural Language Learning, CoNLL 2009 ; Conference date: 04-06-2009 Through 04-06-2009",

url = "https://aclanthology.org/W09-12",

}

Zhao, H, Chen, W, Kit, C & Zhou, G 2009, Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing. in J Hajič (ed.), Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task. CoNLL- Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task, Association for Computational Linguistics, pp. 55-60, 13th Conference on Computational Natural Language Learning, CoNLL 2009, Boulder, CO, United States, 4/06/09. <https://aclanthology.org/W09-1208>

Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing. / Zhao, Hai; Chen, Wenliang; Kit, Chunyu et al.
Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task. ed. / Jan Hajič . Association for Computational Linguistics, 2009. p. 55-60 (CoNLL- Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task).

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

TY - GEN

T1 - Multilingual dependency learning

T2 - 13th Conference on Computational Natural Language Learning, CoNLL 2009

AU - Zhao, Hai

AU - Chen, Wenliang

AU - Kit, Chunyu

AU - Zhou, Guodong

PY - 2009/6

Y1 - 2009/6

N2 - This paper describes our system about multilingual semantic dependency parsing (SRLonly) for our participation in the shared task of CoNLL-2009. We illustrate that semantic dependency parsing can be transformed into a word-pair classification problem and implemented as a single-stage machine learning system. For each input corpus, a large scale feature engineering is conducted to select the best fit feature template set incorporated with a proper argument pruning strategy. The system achieved the top average score in the closed challenge: 80.47% semantic labeled F1 for the average score. © 2009 Association for Computational Linguistics.

AB - This paper describes our system about multilingual semantic dependency parsing (SRLonly) for our participation in the shared task of CoNLL-2009. We illustrate that semantic dependency parsing can be transformed into a word-pair classification problem and implemented as a single-stage machine learning system. For each input corpus, a large scale feature engineering is conducted to select the best fit feature template set incorporated with a proper argument pruning strategy. The system achieved the top average score in the closed challenge: 80.47% semantic labeled F1 for the average score. © 2009 Association for Computational Linguistics.

UR - https://www.scopus.com/pages/publications/84859984064#tab=impact

UR - https://www.scopus.com/pages/publications/84859984064

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

T3 - CoNLL- Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task

SP - 55

EP - 60

BT - Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009)

A2 - Hajič , Jan

PB - Association for Computational Linguistics

Y2 - 4 June 2009 through 4 June 2009

ER -

Zhao H, Chen W, Kit C, Zhou G. Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing. In Hajič J, editor, Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task. Association for Computational Linguistics. 2009. p. 55-60. (CoNLL- Shared Task - Proceedings of the Thirteenth Conference on Computational Natural Language Learning, CoNLL: Shared Task).

Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing

Abstract

Publication series

Conference

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this