풀 포스트에디팅에 대한 고찰—풀 포스트에디팅 생산성에 영향을 주는 요소를 중심으로
An Investigation into English to Korean Full Post-editing: Factors Affecting Productivity of Full Post-editing
1
조회
0
다운로드
9
인용
0
참고문헌
키워드
초록
This research investigates the nature of English to Korean full post-editing and what factors can affect the productivity of full post-editing. The first goal is to examine if machine translation post-editing is faster than human translation and if the adequacy and fluency are not inferior to human translation. The data collected from 14 students showed that full post-editing is 69.66% faster than human translation. A sampling evaluation found that post-editing quality is not inferior to human translation. Furthermore, a statistical analysis found that editing volume does not correlate closely with productivity. This analysis implies that editing volume is one of the core factors that can explain productivity, but there can be other factors. In addition, a text analysis found that the frequency and severity of errors in raw machine translation are directly related to productivity losses. This paper discusses the reasons behind these findings and suggests how the industry and academia should use these findings.
Abstract
This research investigates the nature of English to Korean full post-editing and what factors can affect the productivity of full post-editing. The first goal is to examine if machine translation post-editing is faster than human translation and if the adequacy and fluency are not inferior to human translation. The data collected from 14 students showed that full post-editing is 69.66% faster than human translation. A sampling evaluation found that post-editing quality is not inferior to human translation. Furthermore, a statistical analysis found that editing volume does not correlate closely with productivity. This analysis implies that editing volume is one of the core factors that can explain productivity, but there can be other factors. In addition, a text analysis found that the frequency and severity of errors in raw machine translation are directly related to productivity losses. This paper discusses the reasons behind these findings and suggests how the industry and academia should use these findings.
참고문헌 (16)
- 김순미, "번역학계와 언어서비스업체(LSP)간 산학협력연구: ‘포스트에디팅 생산성’과 ‘기계번역 엔진 성능 비교’", 번역학연구, 20(1), pp.41~76 (2019), 한국번역학회[DOI]
- 김자경, "한영 포스트에디팅 과정에서의 노력 탐색 - 시간, 기술적 노력, 검색을 중심으로", 통번역학연구, 26(2), pp.1~24 (2022), 통번역연구소[DOI]
- 박혜경, "석사 과정의 기계번역 수업에 대한 소고: 한일번역 전공생의 포스트에디팅 사례를 통하여", 번역학연구, 19(3), pp.163~193 (2018), 한국번역학회[DOI]
- 신지선, "기계번역 포스트에디팅에 관한 해외 연구 동향", 번역학연구, 21(4), pp.87~114 (2020), 한국번역학회[DOI]
- 이준호, "영한 포스트에디팅 생산성에 대한 고찰- 시간적 노력을 중심으로", 통번역학연구, 25(2), pp.55~83 (2021), 통번역연구소[DOI]
- 이준호, "한영 포스트에디팅 노력 예비연구: 트랜스로그 II를 활용한 한영 인간번역과 포스트에디팅의 차이 분석", 번역학연구, 22(5), pp.271~298 (2021), 한국번역학회[DOI]
- 최문선, "국내 번역학 기계번역 연구 동향:내용 분석과 키워드 분석을 중심으로", 언어학연구, 24(1), pp.275~297 (2019), 한국언어연구학회[DOI]
- Akoglu, Haldun, "User’s Guide to Correlation Coefficients", Turkish Journal of Emergency Medicine, 18(3), pp.91~93 (2018)
- Aranberri, Nora, "Comparison of Post-editing Productivity between Professional Translators and Lay Users", Proceedings of the 11th Conference of the Association for Machine Translation in the Americas, pp.20~33 (2014)
- Daems, Joke, "Interactive Adaptive SMT versus Interactive Adaptive NMT: A User Experience Evaluation", Machine Translation, 33(1), pp.117~134 (2019)
- Daems, Joke, "Translation Methods and Experience: A Comparative Analysis of Human Translation and Post-editing with Students and Professional Translators", Meta: Translators’ Journal, 62(2), pp.245~270 (2017)
- Gaspari, Federico, "Perception vs. Reality: Measuring Machine Translation Post-editing Productivity", Proceedings of the 11th Conference of the Association for Machine Translation in the Americas, pp.60~72 (2014)
- Koehn, Philipp, "Statistical Machine Translation" (2009), Cambridge UP
- O’Brien, Shanon, "Towards Predicting Post-editing Productivity", Machine Translation, 25(3), pp.197~215 (2011)
- Plitt, Mirko, "A Productivity Test of Statistical Machine Translation Post-editing in a Typical Localisation Context", The Prague Bulletin of Mathematical Linguistics, 93 (2010)
- Snover, Matthew, "A Study of Translation Edit Rate with Targeted Human Annotation", Proceedings of the 7th Conference of the Association for Machine Translation in the Americas, pp.223~231 (2006)