특허 기계번역 결과물의 평가 - KIPRIS의 무료 한영 기계번역을 중심으로
A Study on the evaluation of Korean-English patent machine translation–Focusing on KIPRIS K2E-PAT translation.
0
조회
0
다운로드
52
인용
0
참고문헌
키워드
초록
This study aims at assessing the quality of patent translations by K2E-PAT, a Korean-English machine translation system run by Korean Intellectual Property Office, based on the analysis of machine translations of 38 semiconductor-related patent abstracts. In the study, we’ve conducted both automated evaluation widely used in the machine translation evaluation and human evaluation which can complement the shortcomings of automated evaluation. For the automated evaluation, case insensitive BLEU was adopted as an automated score, as it is the most widespread in the intellectual property field. For human evaluation, two examiners examined the quality of machine translation in terms of fidelity and readability. Both automated and human evaluations revealed the machine translations are mostly not satisfactory according to the criteria. Human evaluation indicates that the patent abstract translations contain numerous semantic and syntactic errors as well as terminological ones, severely hampering fidelity and readability. The findings highlight the need to improve the quality standards of K2E-PAT machine translation by fostering collaboration between translation experts and computational linguists.
Abstract
This study aims at assessing the quality of patent translations by K2E-PAT, a Korean-English machine translation system run by Korean Intellectual Property Office, based on the analysis of machine translations of 38 semiconductor-related patent abstracts. In the study, we’ve conducted both automated evaluation widely used in the machine translation evaluation and human evaluation which can complement the shortcomings of automated evaluation. For the automated evaluation, case insensitive BLEU was adopted as an automated score, as it is the most widespread in the intellectual property field. For human evaluation, two examiners examined the quality of machine translation in terms of fidelity and readability. Both automated and human evaluations revealed the machine translations are mostly not satisfactory according to the criteria. Human evaluation indicates that the patent abstract translations contain numerous semantic and syntactic errors as well as terminological ones, severely hampering fidelity and readability. The findings highlight the need to improve the quality standards of K2E-PAT machine translation by fostering collaboration between translation experts and computational linguists.
참고문헌 (43)
- 류상민, "연봉 1억 영문 특허 번역 가이드북", 넥서스, ~ (2015)
- 전종섭, "웹기반 영한 번역을 위한 중간 언어의 효율성 연구", 통번역학연구, 17(3), pp.201~229 (2013), 통번역연구소
- 이상빈, "트랜스크리에이션, 기계번역, 번역교육의 미래", 통역과 번역, 18(2), pp.129~152 (2016), 한국통역번역학회
- 임순정, "구글 번역의 사례연구: 번역품질과 번역단위와의 관계를 중심으로", 번역학연구, 15(1), pp.177~209 (2014), 한국번역학회
- 최승권, "영어 특허문서 자동번역을 위한 특허번역패턴 연구", 번역학연구, 8(1), pp.301~322 (2007), 한국번역학회
- 최승권, "도메인 특화 방법에 의한 영한 특허 자동 번역 시스템의 구축", 정보과학회논문지 : 소프트웨어 및 응용, 34(2), pp.95~103 (2007), 한국정보과학회
- 최승권, "패턴기반 영한 자동번역 시스템의 상용화를 위한 도메인 특화 방법", 정보과학회논문지 : 소프트웨어 및 응용, 39(4), pp.253~260 (2012), 한국정보과학회
- Bani, S., "Current status of MT application in JPO", Paper presented at the Third Workshop on Patent Translation (2009)
- Barnhart, Z., "A Comparative Analysis of Web-based Machine Translation Quality: English to French and French to English", master, pp.2012
- Bazrafshan, M., "Semantic Features for Statistical Machine Translation", doctor, pp.2014
- Choi, Y. C., "Korean to English Patent Automatic Translation(K2E-PAT)and cross lingual retrieval on KIPRIS", World Patent Information, 31, pp.135~136 (2009)
- Coughlin, D., "Correlating automated and human assessments of machine translation quality", Paper presented at MT Summit Ⅸ (2003)
- Daems, J., "The impact of machine translation error types on post-editing effort indicators", Paper presented at MT Summit XV: The Fourth Workshop on Post-Editing Technology and Practice (2015)
- Dorr, B., "Handbook of Natural Language Processing and Machine Translation", pp.745~843 (2011), Springer
- Fiederer, R., "Quality and machine translation: A realistic objective?", The Journal of Specialised Translation, 11, pp.52~72 (2009)
- Hutchins, J., "Survey of the State of the Art in Human Language Technology", pp.418~419 (1997), Giardini
- Kato, K., "Initiatives of the Japan Patent Office", Paper presented at MT Summit XV: The Sixth Workshop on Patent and Scientific Literature Translation (PSLT6) (2015)
- Koponen, M., "Assessing machine translation quality with error analysis", Paper presented at the KäTu Symposium on Translation and Interpreting Studies (2010)
- Le Chapelain, B., "Machine translation project and activities in EPO: ‘The patent case’", Paper presented at MT Summit XⅢ: The Fourth Workshop on Patent Translation (2011)
- Li, H., "A hybrid system for Chinese-English patent machine translation", Paper presented at MT Summit XV: The Sixth Workshop on Patent and Scientific Literature Translation (PSLT6) (2015)
- Melby, A. K., "Quality evaluation of four translations of a kidney document: Focus on reliability", Paper presented at MT Summit XV : The Sixth Workshop on Patent and Scientific Literature Translation(PSLT6), Miami and Florida (2015)
- Olohan, M., "Scientific and Technical Translation" (2015), Routledge
- Papineni, K., "BLEU: A method for automatic evaluation of machine translation", Paper presented at the 40th annual meeting of the Association for Computational Linguistics (ACL) (2002)
- Poliquen, B., "Full-text patent translation at WIPO: Scalability, quality and usability", Paper presented at MT Summit XV: The Sixth Workshop on Patent and Scientific Literature Translation (PSLT6) (2015)
- Pym, A., "Translation skill-sets in a machine-translation age", Meta, 58(3), pp.487~503 (2013)
- Raido, V. E., "Translators as adaptive experts in a flat world: From globalization 1.0 to globalization 4.0?", International Journal of Communication, 10, pp.970~988 (2016)
- Reeder, F., "April). An introduction to MT evaluation", Paper presented at the Workshop on MT Evaluation (2001)
- Rossi, L., "Applicability and application of machine translation quality metrics in the patent field", World Patent Information, 35, pp.115~125 (2013)
- Rychtyckyj, N., "Applying automated language translation at a global enterprise level", AI Magazine, 34(1), pp.43~54 (2013)
- Siriussoft., "Current machine translation status for patent domain users in Korea", Paper presented at the First Symposium on Patent Information Processing (2010)
- "인공지능 번역 ‘고도화’...英語 업계 “나 떨고 있니?" (2017)[URL]
- "한국특허 얼굴 ‘특허영문초록’ 오류 투성이" (2012)[URL]
- "구글번역 10주년...‘인공지능’ 적용 서비스 선보여" (2016)[URL]
- "특허청, 키프리스 한영 기계번역서비스 무료 제공" (2013)[URL]
- "진화하는 번역기... 사라지는 번역가?" (2017)[URL]
- "지식재산정보! 언어장벽 없이 이용하세요" (2013)[URL]
- "MT evaluation: Human measures and assessment methods" (2013)[URL]
- "TAPTA: Translation Assistant for Patent Titles and Abstracts" (2014)[URL]
- "지식재산권 통계" (2017)[URL]
- "키프리스 소개" (2017)[URL]
- "EPO PatentTranslate FAQ" (2017)[URL]
- "Google Neural Machine Translation" (2017)[URL]
- "Moses Introduction" (2017)[URL]