Naïve Probabilistic Shift-Reduce Parsing Model Using Functional Word Based Context for Agglutinative Languages
Summary :
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.
- Publication
- IEICE TRANSACTIONS on Information Vol.E87-D No.9 pp.2286-2289
- Publication Date
- 2004/09/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- LETTER
- Category
- Natural Language Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yong-Jae KWAK, So-Young PARK, Joon-Ho LIM, Hae-Chang RIM, "Naïve Probabilistic Shift-Reduce Parsing Model Using Functional Word Based Context for Agglutinative Languages" in IEICE TRANSACTIONS on Information,
vol. E87-D, no. 9, pp. 2286-2289, September 2004, doi: .
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.
URL: https://global.ieice.org/en_transactions/information/10.1587/e87-d_9_2286/_p
Copy
@ARTICLE{e87-d_9_2286,
author={Yong-Jae KWAK, So-Young PARK, Joon-Ho LIM, Hae-Chang RIM, },
journal={IEICE TRANSACTIONS on Information},
title={Naïve Probabilistic Shift-Reduce Parsing Model Using Functional Word Based Context for Agglutinative Languages},
year={2004},
volume={E87-D},
number={9},
pages={2286-2289},
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.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - Naïve Probabilistic Shift-Reduce Parsing Model Using Functional Word Based Context for Agglutinative Languages
T2 - IEICE TRANSACTIONS on Information
SP - 2286
EP - 2289
AU - Yong-Jae KWAK
AU - So-Young PARK
AU - Joon-Ho LIM
AU - Hae-Chang RIM
PY - 2004
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E87-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2004
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.
ER -
English
