A Probabilistic Feature-Based Parsing Model for Head-Final Languages

So-Young PARK; Yong-Jae KWAK; Joon-Ho LIM; Hae-Chang RIM

A Probabilistic Feature-Based Parsing Model for Head-Final Languages

So-Young PARK, Yong-Jae KWAK, Joon-Ho LIM, Hae-Chang RIM

Full Text Views

0

Share
Cite this

Summary :

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 non-head 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.

Publication: IEICE TRANSACTIONS on Information Vol.E87-D No.12 pp.2893-2897

Publication Date: 2004/12/01

Publicized

Online ISSN

DOI

Type of Manuscript: LETTER

Category: Natural Language Processing

Cite this

Copy

So-Young PARK, Yong-Jae KWAK, Joon-Ho LIM, Hae-Chang RIM, "A Probabilistic Feature-Based Parsing Model for Head-Final Languages" in IEICE TRANSACTIONS on Information, vol. E87-D, no. 12, pp. 2893-2897, December 2004, doi: .
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 non-head 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.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e87-d_12_2893/_p

Copy

@ARTICLE{e87-d_12_2893,
author={So-Young PARK, Yong-Jae KWAK, Joon-Ho LIM, Hae-Chang RIM, },
journal={IEICE TRANSACTIONS on Information},
title={A Probabilistic Feature-Based Parsing Model for Head-Final Languages},
year={2004},
volume={E87-D},
number={12},
pages={2893-2897},
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 non-head 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={},
doi={},
ISSN={},
month={December},}

Copy

TY - JOUR
TI - A Probabilistic Feature-Based Parsing Model for Head-Final Languages
T2 - IEICE TRANSACTIONS on Information
SP - 2893
EP - 2897
AU - So-Young PARK
AU - Yong-Jae KWAK
AU - Joon-Ho LIM
AU - Hae-Chang RIM
PY - 2004
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E87-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2004
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 non-head 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.
ER -