Template kernels for dependency parsing

Hillel Taub-Tabib; Yoav Goldberg; Amir Globerson

doi:10.3115/v1/n15-1163

Template kernels for dependency parsing

Hillel Taub-Tabib, Yoav Goldberg, Amir Globerson

CS@BIU

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

2 Scopus citations

Abstract

A common approach to dependency parsing is scoring a parse via a linear function of a set of indicator features. These features are typically manually constructed from templates that are applied to parts of the parse tree. The templates define which properties of a part should combine to create features. Existing approaches consider only a small subset of the possible combinations, due to statistical and computational efficiency considerations. In this work we present a novel kernel which facilitates efficient parsing with feature representations corresponding to a much larger set of combinations. We integrate the kernel into a parse reranking system and demonstrate its effectiveness on four languages from the CoNLL-X shared task.¹

Original language	English
Title of host publication	NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	1422-1427
Number of pages	6
ISBN (Electronic)	9781941643495
DOIs	https://doi.org/10.3115/v1/n15-1163
State	Published - 2015
Event	Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 - Denver, United States Duration: 31 May 2015 → 5 Jun 2015

Publication series

Name	NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Conference

Conference	Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015
Country/Territory	United States
City	Denver
Period	31/05/15 → 5/06/15

Bibliographical note

Publisher Copyright:
© 2015 Association for Computational Linguistics.

Access to Document

10.3115/v1/n15-1163

Cite this

Taub-Tabib, H., Goldberg, Y., & Globerson, A. (2015). Template kernels for dependency parsing. In NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 1422-1427). (NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/n15-1163

Taub-Tabib, Hillel ; Goldberg, Yoav ; Globerson, Amir. / Template kernels for dependency parsing. NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. pp. 1422-1427 (NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

@inproceedings{1fd687821258425f82a368988f57adc4,

title = "Template kernels for dependency parsing",

abstract = "A common approach to dependency parsing is scoring a parse via a linear function of a set of indicator features. These features are typically manually constructed from templates that are applied to parts of the parse tree. The templates define which properties of a part should combine to create features. Existing approaches consider only a small subset of the possible combinations, due to statistical and computational efficiency considerations. In this work we present a novel kernel which facilitates efficient parsing with feature representations corresponding to a much larger set of combinations. We integrate the kernel into a parse reranking system and demonstrate its effectiveness on four languages from the CoNLL-X shared task.1",

author = "Hillel Taub-Tabib and Yoav Goldberg and Amir Globerson",

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics.; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 ; Conference date: 31-05-2015 Through 05-06-2015",

year = "2015",

doi = "10.3115/v1/n15-1163",

language = "אנגלית",

series = "NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",

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

pages = "1422--1427",

booktitle = "NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics",

address = "ארצות הברית",

}

Taub-Tabib, H, Goldberg, Y & Globerson, A 2015, Template kernels for dependency parsing. in NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 1422-1427, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015, Denver, United States, 31/05/15. https://doi.org/10.3115/v1/n15-1163

Template kernels for dependency parsing. / Taub-Tabib, Hillel; Goldberg, Yoav; Globerson, Amir.
NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2015. p. 1422-1427 (NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference).

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

TY - GEN

T1 - Template kernels for dependency parsing

AU - Taub-Tabib, Hillel

AU - Goldberg, Yoav

AU - Globerson, Amir

PY - 2015

Y1 - 2015

N2 - A common approach to dependency parsing is scoring a parse via a linear function of a set of indicator features. These features are typically manually constructed from templates that are applied to parts of the parse tree. The templates define which properties of a part should combine to create features. Existing approaches consider only a small subset of the possible combinations, due to statistical and computational efficiency considerations. In this work we present a novel kernel which facilitates efficient parsing with feature representations corresponding to a much larger set of combinations. We integrate the kernel into a parse reranking system and demonstrate its effectiveness on four languages from the CoNLL-X shared task.1

AB - A common approach to dependency parsing is scoring a parse via a linear function of a set of indicator features. These features are typically manually constructed from templates that are applied to parts of the parse tree. The templates define which properties of a part should combine to create features. Existing approaches consider only a small subset of the possible combinations, due to statistical and computational efficiency considerations. In this work we present a novel kernel which facilitates efficient parsing with feature representations corresponding to a much larger set of combinations. We integrate the kernel into a parse reranking system and demonstrate its effectiveness on four languages from the CoNLL-X shared task.1

UR - http://www.scopus.com/inward/record.url?scp=84960158031&partnerID=8YFLogxK

U2 - 10.3115/v1/n15-1163

DO - 10.3115/v1/n15-1163

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

AN - SCOPUS:84960158031

T3 - NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

SP - 1422

EP - 1427

BT - NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

T2 - Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015

Y2 - 31 May 2015 through 5 June 2015

ER -

Taub-Tabib H, Goldberg Y, Globerson A. Template kernels for dependency parsing. In NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2015. p. 1422-1427. (NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference). doi: 10.3115/v1/n15-1163

Template kernels for dependency parsing

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this