Naïve probabilistic shift-reduce parsing model using functional word based context for agglutinative languages

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

Research output: Contribution to journalArticle

Abstract

In this paper, we propose a naïve probabilistic shift-reduce parsing model which can use contextual information more flexibly than the previous probabilistic GLR parsing models, and utilize the characteristics of agglutinative language in which the functional words are highly developed. Experimental results on Korean have shown that our model using the proposed contextual information improves the parsing accuracy more effectively than the previous models. Moreover, it is compact in model size, and is robust with a small training set.

Original languageEnglish
Pages (from-to)2286-2289
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE87-D
Issue number9
Publication statusPublished - 2004 Sep 1

Fingerprint

Information use

Keywords

  • Probabilistic parsing
  • Shift-reduce parsing

ASJC Scopus subject areas

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

Cite this

Naïve probabilistic shift-reduce parsing model using functional word based context for agglutinative languages. / Kwak, Yong Jae; Park, So Young; Lim, Joon Ho; Rim, Hae-Chang.

In: IEICE Transactions on Information and Systems, Vol. E87-D, No. 9, 01.09.2004, p. 2286-2289.

Research output: Contribution to journalArticle

@article{1857bfc334d94786ad5deb021447cb49,
title = "Na{\"i}ve probabilistic shift-reduce parsing model using functional word based context for agglutinative languages",
abstract = "In this paper, we propose a na{\"i}ve probabilistic shift-reduce parsing model which can use contextual information more flexibly than the previous probabilistic GLR parsing models, and utilize the characteristics of agglutinative language in which the functional words are highly developed. Experimental results on Korean have shown that our model using the proposed contextual information improves the parsing accuracy more effectively than the previous models. Moreover, it is compact in model size, and is robust with a small training set.",
keywords = "Probabilistic parsing, Shift-reduce parsing",
author = "Kwak, {Yong Jae} and Park, {So Young} and Lim, {Joon Ho} and Hae-Chang Rim",
year = "2004",
month = "9",
day = "1",
language = "English",
volume = "E87-D",
pages = "2286--2289",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "9",

}

TY - JOUR

T1 - Naïve probabilistic shift-reduce parsing model using functional word based context for agglutinative languages

AU - Kwak, Yong Jae

AU - Park, So Young

AU - Lim, Joon Ho

AU - Rim, Hae-Chang

PY - 2004/9/1

Y1 - 2004/9/1

N2 - In this paper, we propose a naïve probabilistic shift-reduce parsing model which can use contextual information more flexibly than the previous probabilistic GLR parsing models, and utilize the characteristics of agglutinative language in which the functional words are highly developed. Experimental results on Korean have shown that our model using the proposed contextual information improves the parsing accuracy more effectively than the previous models. Moreover, it is compact in model size, and is robust with a small training set.

AB - In this paper, we propose a naïve probabilistic shift-reduce parsing model which can use contextual information more flexibly than the previous probabilistic GLR parsing models, and utilize the characteristics of agglutinative language in which the functional words are highly developed. Experimental results on Korean have shown that our model using the proposed contextual information improves the parsing accuracy more effectively than the previous models. Moreover, it is compact in model size, and is robust with a small training set.

KW - Probabilistic parsing

KW - Shift-reduce parsing

UR - http://www.scopus.com/inward/record.url?scp=5444273116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=5444273116&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:5444273116

VL - E87-D

SP - 2286

EP - 2289

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 9

ER -