Multilingual syntactic-semantic dependency parsing with three-stage approximate max-margin linear models

Yotaro Watanabe; Masayuki Asahara; Yuji Matsumoto

doi:10.3115/1596409.1596429

Multilingual syntactic-semantic dependency parsing with three-stage approximate max-margin linear models

Yotaro Watanabe, Masayuki Asahara, Yuji Matsumoto

INF - System Information Sciences

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

1 Citation (Scopus)

Abstract

This paper describes a system for syntacticsemantic dependency parsing for multiple languages. The system consists of three parts: a state-of-the-art higher-order projective dependency parser for syntactic dependency parsing, a predicate classifier, and an argument classifier for semantic dependency parsing. For semantic dependency parsing, we explore use of global features. All components are trained with an approximate max-margin learning algorithm. In the closed challenge of the CoNLL-2009 Shared Task (Hajič et al., 2009), our system achieved the 3rd best performances for English and Czech, and the 4th best performance for Japanese.

Original language	English
Pages	114-119
Number of pages	6
DOIs	https://doi.org/10.3115/1596409.1596429
Publication status	Published - 2009
Event	13th Conference on Computational Natural Language Learning, CoNLL 2009 - Boulder, CO, United States Duration: 2009 Jun 4 → 2009 Jun 4

Other

Other	13th Conference on Computational Natural Language Learning, CoNLL 2009
Country	United States
City	Boulder, CO
Period	09/6/4 → 09/6/4

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction
Linguistics and Language

Access to Document

10.3115/1596409.1596429

Fingerprint Dive into the research topics of 'Multilingual syntactic-semantic dependency parsing with three-stage approximate max-margin linear models'. Together they form a unique fingerprint.

Cite this

@conference{f6d869348c8b465c9252fc973ea19452,

title = "Multilingual syntactic-semantic dependency parsing with three-stage approximate max-margin linear models",

abstract = "This paper describes a system for syntacticsemantic dependency parsing for multiple languages. The system consists of three parts: a state-of-the-art higher-order projective dependency parser for syntactic dependency parsing, a predicate classifier, and an argument classifier for semantic dependency parsing. For semantic dependency parsing, we explore use of global features. All components are trained with an approximate max-margin learning algorithm. In the closed challenge of the CoNLL-2009 Shared Task (Haji{\v c} et al., 2009), our system achieved the 3rd best performances for English and Czech, and the 4th best performance for Japanese.",

author = "Yotaro Watanabe and Masayuki Asahara and Yuji Matsumoto",

year = "2009",

doi = "10.3115/1596409.1596429",

language = "English",

pages = "114--119",

note = "13th Conference on Computational Natural Language Learning, CoNLL 2009 ; Conference date: 04-06-2009 Through 04-06-2009",

}

TY - CONF

T1 - Multilingual syntactic-semantic dependency parsing with three-stage approximate max-margin linear models

AU - Watanabe, Yotaro

AU - Asahara, Masayuki

AU - Matsumoto, Yuji

PY - 2009

Y1 - 2009

N2 - This paper describes a system for syntacticsemantic dependency parsing for multiple languages. The system consists of three parts: a state-of-the-art higher-order projective dependency parser for syntactic dependency parsing, a predicate classifier, and an argument classifier for semantic dependency parsing. For semantic dependency parsing, we explore use of global features. All components are trained with an approximate max-margin learning algorithm. In the closed challenge of the CoNLL-2009 Shared Task (Hajič et al., 2009), our system achieved the 3rd best performances for English and Czech, and the 4th best performance for Japanese.

AB - This paper describes a system for syntacticsemantic dependency parsing for multiple languages. The system consists of three parts: a state-of-the-art higher-order projective dependency parser for syntactic dependency parsing, a predicate classifier, and an argument classifier for semantic dependency parsing. For semantic dependency parsing, we explore use of global features. All components are trained with an approximate max-margin learning algorithm. In the closed challenge of the CoNLL-2009 Shared Task (Hajič et al., 2009), our system achieved the 3rd best performances for English and Czech, and the 4th best performance for Japanese.

UR - http://www.scopus.com/inward/record.url?scp=84863870416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863870416&partnerID=8YFLogxK

U2 - 10.3115/1596409.1596429

DO - 10.3115/1596409.1596429

M3 - Paper

AN - SCOPUS:84863870416

SP - 114

EP - 119

T2 - 13th Conference on Computational Natural Language Learning, CoNLL 2009

Y2 - 4 June 2009 through 4 June 2009

ER -

Multilingual syntactic-semantic dependency parsing with three-stage approximate max-margin linear models

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this