Feature-based Korean grammar utilizing learned constraint rules

S. O Young Park, Yong Jae Kwak, Hae-Chang Rim, Heui Seok Lim

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose a feature-based Korean grammar utilizing the learned constraint rules in order to improve parsing efficiency. The proposed grammar consists of feature structures, feature operations, and constraint rules; and it has the following characteristics. First, a feature structure includes several features to express useful linguistic information for Korean parsing. Second, a feature operation generating a new feature structure is restricted to the binary-branching form which can deal with Korean properties such as variable word order and constituent ellipsis. Third, constraint rules improve efficiency by preventing feature operations from generating spurious feature structures. Moreover, these rules are learned from a Korean treebank by a decision tree learning algorithm. The experimental results show that the feature-based Korean grammar can reduce the number of candidates by a third of candidates at most and it runs 1.5 ∼ 2 times faster than a CFG on a statistical parser.

Original languageEnglish
Pages (from-to)69-89
Number of pages21
JournalComputational Intelligence
Volume21
Issue number1
Publication statusPublished - 2005 Feb 1

Fingerprint

Grammar
Parsing
Decision trees
Linguistics
Learning algorithms
Ellipsis
Tree Algorithms
Decision tree
Branching
Learning Algorithm
Express
Binary
Experimental Results

Keywords

  • Constraint rules
  • Korean grammar
  • Natural language processing
  • Parsing algorithm

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence
  • Safety, Risk, Reliability and Quality
  • Computational Mathematics

Cite this

Feature-based Korean grammar utilizing learned constraint rules. / Park, S. O Young; Kwak, Yong Jae; Rim, Hae-Chang; Lim, Heui Seok.

In: Computational Intelligence, Vol. 21, No. 1, 01.02.2005, p. 69-89.

Research output: Contribution to journalArticle

@article{a434f98620ad46dc8cac17c9c1339d3f,
title = "Feature-based Korean grammar utilizing learned constraint rules",
abstract = "In this paper, we propose a feature-based Korean grammar utilizing the learned constraint rules in order to improve parsing efficiency. The proposed grammar consists of feature structures, feature operations, and constraint rules; and it has the following characteristics. First, a feature structure includes several features to express useful linguistic information for Korean parsing. Second, a feature operation generating a new feature structure is restricted to the binary-branching form which can deal with Korean properties such as variable word order and constituent ellipsis. Third, constraint rules improve efficiency by preventing feature operations from generating spurious feature structures. Moreover, these rules are learned from a Korean treebank by a decision tree learning algorithm. The experimental results show that the feature-based Korean grammar can reduce the number of candidates by a third of candidates at most and it runs 1.5 ∼ 2 times faster than a CFG on a statistical parser.",
keywords = "Constraint rules, Korean grammar, Natural language processing, Parsing algorithm",
author = "Park, {S. O Young} and Kwak, {Yong Jae} and Hae-Chang Rim and Lim, {Heui Seok}",
year = "2005",
month = "2",
day = "1",
language = "English",
volume = "21",
pages = "69--89",
journal = "Computational Intelligence",
issn = "0824-7935",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Feature-based Korean grammar utilizing learned constraint rules

AU - Park, S. O Young

AU - Kwak, Yong Jae

AU - Rim, Hae-Chang

AU - Lim, Heui Seok

PY - 2005/2/1

Y1 - 2005/2/1

N2 - In this paper, we propose a feature-based Korean grammar utilizing the learned constraint rules in order to improve parsing efficiency. The proposed grammar consists of feature structures, feature operations, and constraint rules; and it has the following characteristics. First, a feature structure includes several features to express useful linguistic information for Korean parsing. Second, a feature operation generating a new feature structure is restricted to the binary-branching form which can deal with Korean properties such as variable word order and constituent ellipsis. Third, constraint rules improve efficiency by preventing feature operations from generating spurious feature structures. Moreover, these rules are learned from a Korean treebank by a decision tree learning algorithm. The experimental results show that the feature-based Korean grammar can reduce the number of candidates by a third of candidates at most and it runs 1.5 ∼ 2 times faster than a CFG on a statistical parser.

AB - In this paper, we propose a feature-based Korean grammar utilizing the learned constraint rules in order to improve parsing efficiency. The proposed grammar consists of feature structures, feature operations, and constraint rules; and it has the following characteristics. First, a feature structure includes several features to express useful linguistic information for Korean parsing. Second, a feature operation generating a new feature structure is restricted to the binary-branching form which can deal with Korean properties such as variable word order and constituent ellipsis. Third, constraint rules improve efficiency by preventing feature operations from generating spurious feature structures. Moreover, these rules are learned from a Korean treebank by a decision tree learning algorithm. The experimental results show that the feature-based Korean grammar can reduce the number of candidates by a third of candidates at most and it runs 1.5 ∼ 2 times faster than a CFG on a statistical parser.

KW - Constraint rules

KW - Korean grammar

KW - Natural language processing

KW - Parsing algorithm

UR - http://www.scopus.com/inward/record.url?scp=14844349279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=14844349279&partnerID=8YFLogxK

M3 - Article

VL - 21

SP - 69

EP - 89

JO - Computational Intelligence

JF - Computational Intelligence

SN - 0824-7935

IS - 1

ER -