A probabilistic feature-based parsing model for head-final languages

So Young Park, Yong Jae Kwak, Joon Ho Lim, Hae-Chang Rim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose a probabilistic feature-based parsing model for head-final languages, which can lead to an improvement of syntactic disambiguation while reducing the parsing cost related to lexical information. For effective syntactic disambiguation, the proposed parsing model utilizes several useful features such as a syntactic label feature, a content feature, a functional feature, and a size feature. Moreover, it is designed to be suitable for representing word order variation of nonhead words in head-final languages. Experimental results show that the proposed parsing model performs better than previous lexicalized parsing models, although it has much less dependence on lexical information.

Original languageEnglish
Pages (from-to)2893-2897
Number of pages5
JournalIEICE Transactions on Information and Systems
VolumeE87-D
Issue number12
Publication statusPublished - 2004 Dec 1

Fingerprint

Syntactics
Labels
Costs

Keywords

  • Natural language processing
  • Probabilistic parsing models
  • Syntactic disambiguation

ASJC Scopus subject areas

  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

A probabilistic feature-based parsing model for head-final languages. / Park, So Young; Kwak, Yong Jae; Lim, Joon Ho; Rim, Hae-Chang.

In: IEICE Transactions on Information and Systems, Vol. E87-D, No. 12, 01.12.2004, p. 2893-2897.

Research output: Contribution to journalArticle

Park, So Young ; Kwak, Yong Jae ; Lim, Joon Ho ; Rim, Hae-Chang. / A probabilistic feature-based parsing model for head-final languages. In: IEICE Transactions on Information and Systems. 2004 ; Vol. E87-D, No. 12. pp. 2893-2897.
@article{c7d08c2d5da84513a2e40f1687adc7ce,
title = "A probabilistic feature-based parsing model for head-final languages",
abstract = "In this paper, we propose a probabilistic feature-based parsing model for head-final languages, which can lead to an improvement of syntactic disambiguation while reducing the parsing cost related to lexical information. For effective syntactic disambiguation, the proposed parsing model utilizes several useful features such as a syntactic label feature, a content feature, a functional feature, and a size feature. Moreover, it is designed to be suitable for representing word order variation of nonhead words in head-final languages. Experimental results show that the proposed parsing model performs better than previous lexicalized parsing models, although it has much less dependence on lexical information.",
keywords = "Natural language processing, Probabilistic parsing models, Syntactic disambiguation",
author = "Park, {So Young} and Kwak, {Yong Jae} and Lim, {Joon Ho} and Hae-Chang Rim",
year = "2004",
month = "12",
day = "1",
language = "English",
volume = "E87-D",
pages = "2893--2897",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "12",

}

TY - JOUR

T1 - A probabilistic feature-based parsing model for head-final languages

AU - Park, So Young

AU - Kwak, Yong Jae

AU - Lim, Joon Ho

AU - Rim, Hae-Chang

PY - 2004/12/1

Y1 - 2004/12/1

N2 - In this paper, we propose a probabilistic feature-based parsing model for head-final languages, which can lead to an improvement of syntactic disambiguation while reducing the parsing cost related to lexical information. For effective syntactic disambiguation, the proposed parsing model utilizes several useful features such as a syntactic label feature, a content feature, a functional feature, and a size feature. Moreover, it is designed to be suitable for representing word order variation of nonhead words in head-final languages. Experimental results show that the proposed parsing model performs better than previous lexicalized parsing models, although it has much less dependence on lexical information.

AB - In this paper, we propose a probabilistic feature-based parsing model for head-final languages, which can lead to an improvement of syntactic disambiguation while reducing the parsing cost related to lexical information. For effective syntactic disambiguation, the proposed parsing model utilizes several useful features such as a syntactic label feature, a content feature, a functional feature, and a size feature. Moreover, it is designed to be suitable for representing word order variation of nonhead words in head-final languages. Experimental results show that the proposed parsing model performs better than previous lexicalized parsing models, although it has much less dependence on lexical information.

KW - Natural language processing

KW - Probabilistic parsing models

KW - Syntactic disambiguation

UR - http://www.scopus.com/inward/record.url?scp=11144290684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11144290684&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:11144290684

VL - E87-D

SP - 2893

EP - 2897

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 12

ER -