Labeled pseudo-projective dependency parsing with support vector machines

Joakim Nivre; Johan Hall; Jens Nilsson; Gülşen Eryiǧit; Svetoslav Marinov

Labeled pseudo-projective dependency parsing with support vector machines

Joakim Nivre, Johan Hall, Jens Nilsson, Gülşen Eryiǧit, Svetoslav Marinov

Department of Artificial Intelligence and Data Engineering

Research output: Contribution to conference › Paper › peer-review

6 Citations (Scopus)

Abstract

We use SVM classifiers to predict the next action of a deterministic parser that builds labeled projective dependency graphs in an incremental fashion. Non-projective dependencies are captured indirectly by projectivizing the training data for the classifiers and applying an inverse transformation to the output of the parser. We present evaluation results and an error analysis focusing on Swedish and Turkish.

Original language	English
Pages	221-225
Number of pages	5
Publication status	Published - 2006
Event	10th Conference on Computational Natural Language Learning, CoNLL 2006 - New York City, United States Duration: 8 Jun 2006 → 9 Jun 2006

Conference

Conference	10th Conference on Computational Natural Language Learning, CoNLL 2006
Country/Territory	United States
City	New York City
Period	8/06/06 → 9/06/06

Bibliographical note

Publisher Copyright:
© 2006 Association for Computational Linguistics

Funding

We are grateful for the support from TÜB˙TAK (The Scientific and Technical Research Council of Turkey) and the Swedish Research Council. We also want to thank Atanas Chanev for assistance with Slovene, the organizers of the shared task for all their hard work, and the creators of the treebanks for making the data available.

Funders	Funder number
Vetenskapsrådet
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Cite this

@conference{8adc4d24eaab491285c65d48bab04bc4,

title = "Labeled pseudo-projective dependency parsing with support vector machines",

abstract = "We use SVM classifiers to predict the next action of a deterministic parser that builds labeled projective dependency graphs in an incremental fashion. Non-projective dependencies are captured indirectly by projectivizing the training data for the classifiers and applying an inverse transformation to the output of the parser. We present evaluation results and an error analysis focusing on Swedish and Turkish.",

author = "Joakim Nivre and Johan Hall and Jens Nilsson and G{\"u}l{\c s}en Eryiǧit and Svetoslav Marinov",

note = "Publisher Copyright: {\textcopyright} 2006 Association for Computational Linguistics; 10th Conference on Computational Natural Language Learning, CoNLL 2006 ; Conference date: 08-06-2006 Through 09-06-2006",

year = "2006",

language = "English",

pages = "221--225",

}

TY - CONF

T1 - Labeled pseudo-projective dependency parsing with support vector machines

AU - Nivre, Joakim

AU - Hall, Johan

AU - Nilsson, Jens

AU - Eryiǧit, Gülşen

AU - Marinov, Svetoslav

PY - 2006

Y1 - 2006

N2 - We use SVM classifiers to predict the next action of a deterministic parser that builds labeled projective dependency graphs in an incremental fashion. Non-projective dependencies are captured indirectly by projectivizing the training data for the classifiers and applying an inverse transformation to the output of the parser. We present evaluation results and an error analysis focusing on Swedish and Turkish.

AB - We use SVM classifiers to predict the next action of a deterministic parser that builds labeled projective dependency graphs in an incremental fashion. Non-projective dependencies are captured indirectly by projectivizing the training data for the classifiers and applying an inverse transformation to the output of the parser. We present evaluation results and an error analysis focusing on Swedish and Turkish.

UR - http://www.scopus.com/inward/record.url?scp=85008243496&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85008243496

SP - 221

EP - 225

T2 - 10th Conference on Computational Natural Language Learning, CoNLL 2006

Y2 - 8 June 2006 through 9 June 2006

ER -

Labeled pseudo-projective dependency parsing with support vector machines

Abstract

Conference

Bibliographical note

Funding

Other files and links

Fingerprint

Cite this