How to best use syntax in semantic role labelling

Yufei Wang; Mark Johnson; Stephen Wan; Yifang Sun; Wei Wang

How to best use syntax in semantic role labelling

Yufei Wang, Mark Johnson, Stephen Wan, Yifang Sun, Wei Wang

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

Abstract

There are many different ways in which external information might be used in an NLP task. This paper investigates how external syntactic information can be used most effectively in the Semantic Role Labeling (SRL) task. We evaluate three different ways of encoding syntactic parses and three different ways of injecting them into a state-of-the-art neural ELMo-based SRL sequence labelling model. We show that using a constituency representation as input features improves performance the most, achieving a new state-of-the-art for non-ensemble SRL models on the in-domain CoNLL'05 and CoNLL'12 benchmarks.¹.

Original language	English
Title of host publication	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	5338-5343
Number of pages	6
ISBN (Electronic)	9781950737482
Publication status	Published - 2020
Externally published	Yes
Event	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, Italy Duration: 28 Jul 2019 → 2 Aug 2019

Publication series

Name	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Country/Territory	Italy
City	Florence
Period	28/07/19 → 2/08/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics

Cite this

Wang, Y., Johnson, M., Wan, S., Sun, Y., & Wang, W. (2020). How to best use syntax in semantic role labelling. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 5338-5343). (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Wang, Yufei ; Johnson, Mark ; Wan, Stephen et al. / How to best use syntax in semantic role labelling. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. pp. 5338-5343 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{6493a98e6bbc4f05a93dc9b1cf098993,

title = "How to best use syntax in semantic role labelling",

abstract = "There are many different ways in which external information might be used in an NLP task. This paper investigates how external syntactic information can be used most effectively in the Semantic Role Labeling (SRL) task. We evaluate three different ways of encoding syntactic parses and three different ways of injecting them into a state-of-the-art neural ELMo-based SRL sequence labelling model. We show that using a constituency representation as input features improves performance the most, achieving a new state-of-the-art for non-ensemble SRL models on the in-domain CoNLL'05 and CoNLL'12 benchmarks.1.",

author = "Yufei Wang and Mark Johnson and Stephen Wan and Yifang Sun and Wei Wang",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2020",

language = "English",

series = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

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

pages = "5338--5343",

booktitle = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

}

Wang, Y, Johnson, M, Wan, S, Sun, Y & Wang, W 2020, How to best use syntax in semantic role labelling. in ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 5338-5343, 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, Florence, Italy, 28/07/19.

How to best use syntax in semantic role labelling. / Wang, Yufei; Johnson, Mark; Wan, Stephen et al.
ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. p. 5338-5343 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - How to best use syntax in semantic role labelling

AU - Wang, Yufei

AU - Johnson, Mark

AU - Wan, Stephen

AU - Sun, Yifang

AU - Wang, Wei

PY - 2020

Y1 - 2020

N2 - There are many different ways in which external information might be used in an NLP task. This paper investigates how external syntactic information can be used most effectively in the Semantic Role Labeling (SRL) task. We evaluate three different ways of encoding syntactic parses and three different ways of injecting them into a state-of-the-art neural ELMo-based SRL sequence labelling model. We show that using a constituency representation as input features improves performance the most, achieving a new state-of-the-art for non-ensemble SRL models on the in-domain CoNLL'05 and CoNLL'12 benchmarks.1.

AB - There are many different ways in which external information might be used in an NLP task. This paper investigates how external syntactic information can be used most effectively in the Semantic Role Labeling (SRL) task. We evaluate three different ways of encoding syntactic parses and three different ways of injecting them into a state-of-the-art neural ELMo-based SRL sequence labelling model. We show that using a constituency representation as input features improves performance the most, achieving a new state-of-the-art for non-ensemble SRL models on the in-domain CoNLL'05 and CoNLL'12 benchmarks.1.

UR - http://www.scopus.com/inward/record.url?scp=85084094070&partnerID=8YFLogxK

M3 - Conference Paper published in a book

AN - SCOPUS:85084094070

T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

SP - 5338

EP - 5343

BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Wang Y, Johnson M, Wan S, Sun Y, Wang W. How to best use syntax in semantic role labelling. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 5338-5343. (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

How to best use syntax in semantic role labelling

Abstract

Publication series

Conference

Bibliographical note

Other files and links

Fingerprint

Cite this