Transition-based dependency parsing as latent-variable constituent parsing

Mark Jan Nederhof

Transition-based dependency parsing as latent-variable constituent parsing

School of Computer Science

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

Abstract

We provide a theoretical argument that a common form of projective transition-based dependency parsing is less powerful than constituent parsing using latent variables. The argument is a proof that, under reasonable assumptions, a transition-based dependency parser can be converted to a latent-variable context-free grammar producing equivalent structures.

Original language	English
Title of host publication	Proceedings of the SIGFSM Workshop on Statistical NLP and Weighted Automata
Place of Publication	Berlin
Publisher	Association for Computational Linguistics
Pages	21-31
Number of pages	11
ISBN (Electronic)	9781945626135
Publication status	Published - 12 Aug 2016
Event	54th Annual meeting of the Association for Computational Linguistics - Berlin, Germany Duration: 7 Aug 2016 → 12 Aug 2016 http://www.acl2016.org/

Conference

Conference	54th Annual meeting of the Association for Computational Linguistics
Country/Territory	Germany
City	Berlin
Period	7/08/16 → 12/08/16
Internet address	http://www.acl2016.org/

Keywords

Automata theory
Parsing algorithms

Access to Document

10_Paper (1)
© 2016, Association for Computational Linguistics. This work is made available online in accordance with the publisher’s policies. This is the author created, accepted version manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at http://www.aclweb.org/anthology/W16-2403
Accepted author manuscript, 243 KB

Cite this

@inproceedings{ac34e2d7eac64ecab42a2a680c54f30f,

title = "Transition-based dependency parsing as latent-variable constituent parsing",

abstract = "We provide a theoretical argument that a common form of projective transition-based dependency parsing is less powerful than constituent parsing using latent variables. The argument is a proof that, under reasonable assumptions, a transition-based dependency parser can be converted to a latent-variable context-free grammar producing equivalent structures.",

keywords = "Automata theory, Parsing algorithms",

author = "Nederhof, \{Mark Jan\}",

year = "2016",

month = aug,

day = "12",

language = "English",

pages = "21--31",

booktitle = "Proceedings of the SIGFSM Workshop on Statistical NLP and Weighted Automata",

publisher = "Association for Computational Linguistics",

note = "54th Annual meeting of the Association for Computational Linguistics ; Conference date: 07-08-2016 Through 12-08-2016",

url = "http://www.acl2016.org/",

}

TY - GEN

T1 - Transition-based dependency parsing as latent-variable constituent parsing

AU - Nederhof, Mark Jan

PY - 2016/8/12

Y1 - 2016/8/12

N2 - We provide a theoretical argument that a common form of projective transition-based dependency parsing is less powerful than constituent parsing using latent variables. The argument is a proof that, under reasonable assumptions, a transition-based dependency parser can be converted to a latent-variable context-free grammar producing equivalent structures.

AB - We provide a theoretical argument that a common form of projective transition-based dependency parsing is less powerful than constituent parsing using latent variables. The argument is a proof that, under reasonable assumptions, a transition-based dependency parser can be converted to a latent-variable context-free grammar producing equivalent structures.

KW - Automata theory

KW - Parsing algorithms

M3 - Conference contribution

SP - 21

EP - 31

BT - Proceedings of the SIGFSM Workshop on Statistical NLP and Weighted Automata

PB - Association for Computational Linguistics

CY - Berlin

T2 - 54th Annual meeting of the Association for Computational Linguistics

Y2 - 7 August 2016 through 12 August 2016

ER -

Transition-based dependency parsing as latent-variable constituent parsing

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this