ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Classification-Based Approach for Hybridizing Statistical and Rule-Based Machine Translation
Cited 2 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
저자
박은진, 권오욱, 김강일, 김영길
발행일
201506
출처
ETRI Journal, v.37 no.3, pp.541-550
ISSN
1225-6463
출판사
한국전자통신연구원 (ETRI)
DOI
https://dx.doi.org/10.4218/etrij.15.0114.1017
협약과제
14MS5500, 지식학습 기반의 다국어 확장이 용이한 관광/국제행사 통역률 90%급 자동 통번역 소프트웨어 원천 기술 개발, 김영길
초록
In this paper, we propose a classification-based approach for hybridizing statistical machine translation and rule-based machine translation. Both the training dataset used in the learning of our proposed classifier and our feature extraction method affect the hybridization quality. To create one such training dataset, a previous approach used auto-evaluation metrics to determine from a set of component machine translation (MT) systems which gave the more accurate translation (by a comparative method). Once this had been determined, the most accurate translation was then labelled in such a way so as to indicate the MT system from which it came. In this previous approach, when the metric evaluation scores were low, there existed a high level of uncertainty as to which of the component MT systems was actually producing the better translation. To relax such uncertainty or error in classification, we propose an alternative approach to such labeling; that is, a cut-off method. In our experiments, using the aforementioned cut-off method in our proposed classifier, we managed to achieve a translation accuracy of 81.5% - a 5.0% improvement over existing methods.
키워드
Automatic labeling, Hybrid machine translation, Machine translation, Rule-based machine translation, Statistical machine translation.
KSP 제안 키워드
Automatic Labeling, Based Approach, Comparative method, Cut-off, Hybrid machine translation, MT system, Machine Translation(MT), Metric evaluation, Rule-based, Statistical Machine Translation, Translation Accuracy