In this paper, we propose a new model of automatically constructing an acronym dictionary. The proposed model generates possible acronym candidates from a definition, and then verifies each acronym-definition pair with a Naive Bayes classifier based on web documents. In order to achieve high dictionary quality, the proposed model utilizes the characteristics of acronym generation types: a syllable-based generation type, a word-based generation type, and a mixed generation type. Compared with a previous model recognizing an acronym-definition pair in a document, the proposed model verifying a pair in web documents improves approximately 50% recall on obtaining acronym-definition pairs from 314 Korean definitions. Also, the proposed model improves 7.25% F-measure on verifying acronym-definition candidate pairs by utilizing specialized classifiers with the characteristics of acronym generation types.
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.
Copy
Yeo-Chan YOON, So-Young PARK, Young-In SONG, Hae-Chang RIM, Dae-Woong RHEE, "Automatic Acronym Dictionary Construction Based on Acronym Generation Types" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 5, pp. 1584-1587, May 2008, doi: 10.1093/ietisy/e91-d.5.1584.
Abstract: In this paper, we propose a new model of automatically constructing an acronym dictionary. The proposed model generates possible acronym candidates from a definition, and then verifies each acronym-definition pair with a Naive Bayes classifier based on web documents. In order to achieve high dictionary quality, the proposed model utilizes the characteristics of acronym generation types: a syllable-based generation type, a word-based generation type, and a mixed generation type. Compared with a previous model recognizing an acronym-definition pair in a document, the proposed model verifying a pair in web documents improves approximately 50% recall on obtaining acronym-definition pairs from 314 Korean definitions. Also, the proposed model improves 7.25% F-measure on verifying acronym-definition candidate pairs by utilizing specialized classifiers with the characteristics of acronym generation types.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.5.1584/_p
Copy
@ARTICLE{e91-d_5_1584,
author={Yeo-Chan YOON, So-Young PARK, Young-In SONG, Hae-Chang RIM, Dae-Woong RHEE, },
journal={IEICE TRANSACTIONS on Information},
title={Automatic Acronym Dictionary Construction Based on Acronym Generation Types},
year={2008},
volume={E91-D},
number={5},
pages={1584-1587},
abstract={In this paper, we propose a new model of automatically constructing an acronym dictionary. The proposed model generates possible acronym candidates from a definition, and then verifies each acronym-definition pair with a Naive Bayes classifier based on web documents. In order to achieve high dictionary quality, the proposed model utilizes the characteristics of acronym generation types: a syllable-based generation type, a word-based generation type, and a mixed generation type. Compared with a previous model recognizing an acronym-definition pair in a document, the proposed model verifying a pair in web documents improves approximately 50% recall on obtaining acronym-definition pairs from 314 Korean definitions. Also, the proposed model improves 7.25% F-measure on verifying acronym-definition candidate pairs by utilizing specialized classifiers with the characteristics of acronym generation types.},
keywords={},
doi={10.1093/ietisy/e91-d.5.1584},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Automatic Acronym Dictionary Construction Based on Acronym Generation Types
T2 - IEICE TRANSACTIONS on Information
SP - 1584
EP - 1587
AU - Yeo-Chan YOON
AU - So-Young PARK
AU - Young-In SONG
AU - Hae-Chang RIM
AU - Dae-Woong RHEE
PY - 2008
DO - 10.1093/ietisy/e91-d.5.1584
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2008
AB - In this paper, we propose a new model of automatically constructing an acronym dictionary. The proposed model generates possible acronym candidates from a definition, and then verifies each acronym-definition pair with a Naive Bayes classifier based on web documents. In order to achieve high dictionary quality, the proposed model utilizes the characteristics of acronym generation types: a syllable-based generation type, a word-based generation type, and a mixed generation type. Compared with a previous model recognizing an acronym-definition pair in a document, the proposed model verifying a pair in web documents improves approximately 50% recall on obtaining acronym-definition pairs from 314 Korean definitions. Also, the proposed model improves 7.25% F-measure on verifying acronym-definition candidate pairs by utilizing specialized classifiers with the characteristics of acronym generation types.
ER -