Automatic Feature Selection for Agenda-Based Dependency Parsing

Miguel  Ballesteros; Bernd Bohnet

Automatic Feature Selection for Agenda-Based Dependency Parsing

Miguel Ballesteros, Bernd Bohnet

Computer Science

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

11 Citations (Scopus)

Abstract

In this paper we present an in-depth study on automatic feature selection for beam-search dependency parsers. The search strategy is inherited from the one implemented in MaltOptimizer, but searches in a much larger set of feature templates that could lead to a higher number of combinations. Our models provide results that are on par with models trained with a larger set of feature templates, and this implies that our models provide faster training and parsing times. Moreover, the results establish the state of the art for some of the languages.

Original language	English
Title of host publication	Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics:
Subtitle of host publication	Technical Papers
Editors	Junichi Tsujii, Jan Hajic
Publisher	Association for Computational Linguistics, ACL
Pages	794-805
ISBN (Print)	9781941643266
Publication status	Published - 19 Aug 2014
Event	COLING 2014, the 25th International Conference on Computational Linguistics - Dublin, Ireland Duration: 23 Aug 2014 → 29 Aug 2014

Conference

Conference	COLING 2014, the 25th International Conference on Computational Linguistics
Country/Territory	Ireland
City	Dublin
Period	23/08/14 → 29/08/14

Access to Document

https://www.aclweb.org/anthology/C14-1Licence: Creative Commons: Attribution (CC BY)

Cite this

@inproceedings{3ba8f8b0cca949c9883dfdc428032676,

title = "Automatic Feature Selection for Agenda-Based Dependency Parsing",

abstract = "In this paper we present an in-depth study on automatic feature selection for beam-search dependency parsers. The search strategy is inherited from the one implemented in MaltOptimizer, but searches in a much larger set of feature templates that could lead to a higher number of combinations. Our models provide results that are on par with models trained with a larger set of feature templates, and this implies that our models provide faster training and parsing times. Moreover, the results establish the state of the art for some of the languages.",

author = "Miguel Ballesteros and Bernd Bohnet",

year = "2014",

month = aug,

day = "19",

language = "English",

isbn = "9781941643266",

pages = "794--805",

editor = "Tsujii, {Junichi } and Jan Hajic",

booktitle = "Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics:",

publisher = "Association for Computational Linguistics, ACL",

note = "COLING 2014, the 25th International Conference on Computational Linguistics ; Conference date: 23-08-2014 Through 29-08-2014",

}

Ballesteros, M & Bohnet, B 2014, Automatic Feature Selection for Agenda-Based Dependency Parsing. in J Tsujii & J Hajic (eds), Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. Association for Computational Linguistics, ACL, pp. 794-805, COLING 2014, the 25th International Conference on Computational Linguistics, Dublin, Ireland, 23/08/14. <https://www.aclweb.org/anthology/C14-1>

Automatic Feature Selection for Agenda-Based Dependency Parsing. / Ballesteros, Miguel ; Bohnet, Bernd.

Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. ed. / Junichi Tsujii; Jan Hajic. Association for Computational Linguistics, ACL, 2014. p. 794-805.

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

TY - GEN

T1 - Automatic Feature Selection for Agenda-Based Dependency Parsing

AU - Ballesteros, Miguel

AU - Bohnet, Bernd

PY - 2014/8/19

Y1 - 2014/8/19

N2 - In this paper we present an in-depth study on automatic feature selection for beam-search dependency parsers. The search strategy is inherited from the one implemented in MaltOptimizer, but searches in a much larger set of feature templates that could lead to a higher number of combinations. Our models provide results that are on par with models trained with a larger set of feature templates, and this implies that our models provide faster training and parsing times. Moreover, the results establish the state of the art for some of the languages.

AB - In this paper we present an in-depth study on automatic feature selection for beam-search dependency parsers. The search strategy is inherited from the one implemented in MaltOptimizer, but searches in a much larger set of feature templates that could lead to a higher number of combinations. Our models provide results that are on par with models trained with a larger set of feature templates, and this implies that our models provide faster training and parsing times. Moreover, the results establish the state of the art for some of the languages.

M3 - Conference contribution

SN - 9781941643266

SP - 794

EP - 805

BT - Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics:

A2 - Tsujii, Junichi

A2 - Hajic, Jan

PB - Association for Computational Linguistics, ACL

T2 - COLING 2014, the 25th International Conference on Computational Linguistics

Y2 - 23 August 2014 through 29 August 2014

ER -

Automatic Feature Selection for Agenda-Based Dependency Parsing

Abstract

Conference

Access to Document

Fingerprint

Cite this