Automatic acronym dictionary construction based on acronym generation types

Yeo Chan Yoon, So Young Park, Young I. Song, Hae-Chang Rim, Dae Woong Rhee

Research output: Contribution to journalArticle

3 Citations (Scopus)

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 acronymdefinition 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.

Original languageEnglish
Pages (from-to)1584-1587
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE91-D
Issue number5
DOIs
Publication statusPublished - 2008 May 1

Fingerprint

Glossaries
Classifiers

Keywords

  • Acronym
  • Automatic dictionary construction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Software
  • Electrical and Electronic Engineering

Cite this

Automatic acronym dictionary construction based on acronym generation types. / Yoon, Yeo Chan; Park, So Young; Song, Young I.; Rim, Hae-Chang; Rhee, Dae Woong.

In: IEICE Transactions on Information and Systems, Vol. E91-D, No. 5, 01.05.2008, p. 1584-1587.

Research output: Contribution to journalArticle

Yoon, Yeo Chan ; Park, So Young ; Song, Young I. ; Rim, Hae-Chang ; Rhee, Dae Woong. / Automatic acronym dictionary construction based on acronym generation types. In: IEICE Transactions on Information and Systems. 2008 ; Vol. E91-D, No. 5. pp. 1584-1587.
@article{a07d29acfb384dd593b276827352d8d9,
title = "Automatic acronym dictionary construction based on acronym generation types",
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 acronymdefinition 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 = "Acronym, Automatic dictionary construction",
author = "Yoon, {Yeo Chan} and Park, {So Young} and Song, {Young I.} and Hae-Chang Rim and Rhee, {Dae Woong}",
year = "2008",
month = "5",
day = "1",
doi = "10.1093/ietisy/e91-d.5.1584",
language = "English",
volume = "E91-D",
pages = "1584--1587",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "5",

}

TY - JOUR

T1 - Automatic acronym dictionary construction based on acronym generation types

AU - Yoon, Yeo Chan

AU - Park, So Young

AU - Song, Young I.

AU - Rim, Hae-Chang

AU - Rhee, Dae Woong

PY - 2008/5/1

Y1 - 2008/5/1

N2 - 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 acronymdefinition 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.

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 acronymdefinition 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.

KW - Acronym

KW - Automatic dictionary construction

UR - http://www.scopus.com/inward/record.url?scp=68149101395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68149101395&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e91-d.5.1584

DO - 10.1093/ietisy/e91-d.5.1584

M3 - Article

VL - E91-D

SP - 1584

EP - 1587

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 5

ER -