A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis

Daisuke Kawahara; Sadao Kurohashi

doi:10.3115/1220835.1220858

A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis

Daisuke Kawahara^*, Sadao Kurohashi

^*Corresponding author for this work

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

115 Citations (Scopus)

Abstract

We present an integrated probabilistic model for Japanese syntactic and case structure analysis. Syntactic and case structure are simultaneously analyzed based on wide-coverage case frames that are constructed from a huge raw corpus in an unsupervised manner. This model selects the syntactic and case structure that has the highest generative probability. We evaluate both syntactic structure and case structure. In particular, the experimental results for syntactic analysis on web sentences show that the proposed model significantly outperforms known syntactic analyzers.

Original language	English
Pages	176-183
Number of pages	8
DOIs	https://doi.org/10.3115/1220835.1220858
Publication status	Published - 2006
Externally published	Yes
Event	2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006 - New York, NY, United States Duration: 2006 Jun 4 → 2006 Jun 9

Conference

Conference	2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006
Country/Territory	United States
City	New York, NY
Period	06/6/4 → 06/6/9

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Access to Document

10.3115/1220835.1220858

Cite this

Kawahara, D., & Kurohashi, S. (2006). A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis. 176-183. Paper presented at 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006, New York, NY, United States. https://doi.org/10.3115/1220835.1220858

A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis. / Kawahara, Daisuke; Kurohashi, Sadao.
2006. 176-183 Paper presented at 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006, New York, NY, United States.

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

Kawahara, D & Kurohashi, S 2006, 'A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis', Paper presented at 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006, New York, NY, United States, 06/6/4 - 06/6/9 pp. 176-183. https://doi.org/10.3115/1220835.1220858

@conference{6c4478ccf79147a3b58ca7034e78f967,

title = "A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis",

abstract = "We present an integrated probabilistic model for Japanese syntactic and case structure analysis. Syntactic and case structure are simultaneously analyzed based on wide-coverage case frames that are constructed from a huge raw corpus in an unsupervised manner. This model selects the syntactic and case structure that has the highest generative probability. We evaluate both syntactic structure and case structure. In particular, the experimental results for syntactic analysis on web sentences show that the proposed model significantly outperforms known syntactic analyzers.",

author = "Daisuke Kawahara and Sadao Kurohashi",

year = "2006",

doi = "10.3115/1220835.1220858",

language = "English",

pages = "176--183",

note = "2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006 ; Conference date: 04-06-2006 Through 09-06-2006",

}

TY - CONF

T1 - A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis

AU - Kawahara, Daisuke

AU - Kurohashi, Sadao

PY - 2006

Y1 - 2006

N2 - We present an integrated probabilistic model for Japanese syntactic and case structure analysis. Syntactic and case structure are simultaneously analyzed based on wide-coverage case frames that are constructed from a huge raw corpus in an unsupervised manner. This model selects the syntactic and case structure that has the highest generative probability. We evaluate both syntactic structure and case structure. In particular, the experimental results for syntactic analysis on web sentences show that the proposed model significantly outperforms known syntactic analyzers.

AB - We present an integrated probabilistic model for Japanese syntactic and case structure analysis. Syntactic and case structure are simultaneously analyzed based on wide-coverage case frames that are constructed from a huge raw corpus in an unsupervised manner. This model selects the syntactic and case structure that has the highest generative probability. We evaluate both syntactic structure and case structure. In particular, the experimental results for syntactic analysis on web sentences show that the proposed model significantly outperforms known syntactic analyzers.

UR - http://www.scopus.com/inward/record.url?scp=84858385981&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858385981&partnerID=8YFLogxK

U2 - 10.3115/1220835.1220858

DO - 10.3115/1220835.1220858

M3 - Paper

AN - SCOPUS:84858385981

SP - 176

EP - 183

T2 - 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006

Y2 - 4 June 2006 through 9 June 2006

ER -

A fully-lexicalized probabilistic model for Japanese syntactic and case structure analysis

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this