Improving a strong neural parser with conjunction-specific features

Jessica Ficler; Yoav Goldberg

doi:10.18653/v1/e17-2055

Improving a strong neural parser with conjunction-specific features

Jessica Ficler, Yoav Goldberg

Department of Computer Science

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

5 Scopus citations

Abstract

While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others. In particular, dependency parsers perform poorly in coordination construction (i.e., correctly attaching the conj relation). We extend a state-of-the-art dependency parser with conjunction-specific features, focusing on the similarity between the conjuncts head words. Training the extended parser yields an improvement in conj attachment as well as in overall dependency parsing accuracy on the Stanford dependency conversion of the Penn TreeBank.

Original language	English
Title of host publication	Short Papers
Publisher	Association for Computational Linguistics (ACL)
Pages	343-348
Number of pages	6
ISBN (Electronic)	9781510838604
DOIs	https://doi.org/10.18653/v1/e17-2055
State	Published - 2017
Event	15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017

Publication series

Name	15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference
Volume	2

Conference

Conference	15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
Country/Territory	Spain
City	Valencia
Period	3/04/17 → 7/04/17

Bibliographical note

Publisher Copyright:
© 2017 Association for Computational Linguistics.

Access to Document

10.18653/v1/e17-2055

Cite this

@inproceedings{f3bbd2a819514e659fff2c2d267dc4bc,

title = "Improving a strong neural parser with conjunction-specific features",

abstract = "While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others. In particular, dependency parsers perform poorly in coordination construction (i.e., correctly attaching the conj relation). We extend a state-of-the-art dependency parser with conjunction-specific features, focusing on the similarity between the conjuncts head words. Training the extended parser yields an improvement in conj attachment as well as in overall dependency parsing accuracy on the Stanford dependency conversion of the Penn TreeBank.",

author = "Jessica Ficler and Yoav Goldberg",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics.; 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 ; Conference date: 03-04-2017 Through 07-04-2017",

year = "2017",

doi = "10.18653/v1/e17-2055",

language = "אנגלית",

series = "15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference",

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

pages = "343--348",

booktitle = "Short Papers",

address = "ארצות הברית",

}

Ficler, J & Goldberg, Y 2017, Improving a strong neural parser with conjunction-specific features. in Short Papers. 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference, vol. 2, Association for Computational Linguistics (ACL), pp. 343-348, 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, Valencia, Spain, 3/04/17. https://doi.org/10.18653/v1/e17-2055

Improving a strong neural parser with conjunction-specific features. / Ficler, Jessica; Goldberg, Yoav.
Short Papers. Association for Computational Linguistics (ACL), 2017. p. 343-348 (15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference; Vol. 2).

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

TY - GEN

T1 - Improving a strong neural parser with conjunction-specific features

AU - Ficler, Jessica

AU - Goldberg, Yoav

PY - 2017

Y1 - 2017

N2 - While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others. In particular, dependency parsers perform poorly in coordination construction (i.e., correctly attaching the conj relation). We extend a state-of-the-art dependency parser with conjunction-specific features, focusing on the similarity between the conjuncts head words. Training the extended parser yields an improvement in conj attachment as well as in overall dependency parsing accuracy on the Stanford dependency conversion of the Penn TreeBank.

AB - While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others. In particular, dependency parsers perform poorly in coordination construction (i.e., correctly attaching the conj relation). We extend a state-of-the-art dependency parser with conjunction-specific features, focusing on the similarity between the conjuncts head words. Training the extended parser yields an improvement in conj attachment as well as in overall dependency parsing accuracy on the Stanford dependency conversion of the Penn TreeBank.

UR - http://www.scopus.com/inward/record.url?scp=85021635908&partnerID=8YFLogxK

U2 - 10.18653/v1/e17-2055

DO - 10.18653/v1/e17-2055

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85021635908

T3 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference

SP - 343

EP - 348

BT - Short Papers

PB - Association for Computational Linguistics (ACL)

T2 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017

Y2 - 3 April 2017 through 7 April 2017

ER -

Improving a strong neural parser with conjunction-specific features

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this