상세정보
학술지
Automatic Acronym Dictionary Construction Based on Acronym Generation Types
- 저자
- 윤여찬, 박소영, 송영인, 임해창, 리대웅
- 발행일
- 200805
- 출처
- IEICE Transactions on Information and Systems, v.E91-D no.5, pp.1584-1587
- ISSN
- 0916-8532
- 출판사
- 일본, 전자정보통신학회 (IEICE)
- 협약과제
- 08MS3700, 웹 QA 기술개발, 장명길
- 초록
- 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. Copyright © 2008 The Institute of Electronics, Information and Communication Engineers.
- KSP 제안 키워드
- Dictionary construction, F-measure, Information and communication, New model, Proposed model, Web Documents, Word-based, naive Bayes classifier