한영 포스트에디팅에서 정확성 오류의 수정 양상 고찰
An Investigation into Correction of Accuracy Errors in Post-editing
0
조회
0
다운로드
10
인용
0
참고문헌
키워드
초록
The purpose of this study is to investigate which accuracy errors are more likely to be left uncorrected in post-edited output. To this end, this study analyzed post-edited results produced by 13 student translators with no formal post-editing education. The participants were asked to conduct full post-editing of Korean-to-English machine-translated texts with 23 accuracy errors without time constraints. The results showed that omissions were almost completely corrected, indicating that omission is less likely to remain unedited when enough time is allowed for the post-editing task. In lexical errors, terminology errors were most notably found uncorrected, compared with mistranslated polysemous words and other lexical errors. In syntax errors, errors that require subject knowledge for their identification were most frequently uncorrected, regardless of whether the errors were caused by modifiers or subjects. Such findings shed light on the importance of the education of terminology translation and subject knowledge in post-editing training. This study draws attention to the type of errors as a significant predictor of post-editing quality, pointing to the need for further investigation into the impact of error types on post-editing process and results.
Abstract
The purpose of this study is to investigate which accuracy errors are more likely to be left uncorrected in post-edited output. To this end, this study analyzed post-edited results produced by 13 student translators with no formal post-editing education. The participants were asked to conduct full post-editing of Korean-to-English machine-translated texts with 23 accuracy errors without time constraints. The results showed that omissions were almost completely corrected, indicating that omission is less likely to remain unedited when enough time is allowed for the post-editing task. In lexical errors, terminology errors were most notably found uncorrected, compared with mistranslated polysemous words and other lexical errors. In syntax errors, errors that require subject knowledge for their identification were most frequently uncorrected, regardless of whether the errors were caused by modifiers or subjects. Such findings shed light on the importance of the education of terminology translation and subject knowledge in post-editing training. This study draws attention to the type of errors as a significant predictor of post-editing quality, pointing to the need for further investigation into the impact of error types on post-editing process and results.
참고문헌 (21)
- 김자경, "포스트에디팅 결과물에 나타난 오류 고찰 - AI 학습용 한영 번역 말뭉치를 대상으로", 통번역학연구, 24(4), pp.35~62 (2020), 통번역연구소[DOI]
- 김자경, "포스트에디팅 결과물의 정확성 오류 고찰 —AI 학습용 금융", 증시 분야 한-영 번역 말뭉치를 대상으로—, 2021, pp.23(3), 29~57[DOI]
- 변길자, "기계번역을 활용한 한영번역에서의 번역품질 비교연구", 영어영문학, 26(3), pp.233~259 (2021), 미래영어영문학회[DOI]
- 서보현, "번역사의 번역교육 경험이 포스트에디팅 결과물의 품질에 미치는 영향에 관한 사례연구", 번역학연구, 21(3), pp.63~91 (2020), 한국번역학회[DOI]
- 이상빈, "학부번역전공자의 기계번역 포스트에디팅, 무엇이 문제이고, 무엇을 가르쳐야 하는가?", 통역과 번역, 19(3), pp.37~64 (2017), 한국통역번역학회[DOI]
- 이선우, "학부번역전공자의 인간번역과 기계번역 포스트에디팅 품질 비교", T&I REVIEW, 11(2), pp.101~124 (2021), 통역번역연구소[DOI]
- 이준호, "한영 포스트에디팅, 누구나 수행할 수 있는가?: 포스트에디팅 수업 설계를 위한 예비 연구", 번역학연구, 22(1), pp.171~198 (2021), 한국번역학회[DOI]
- 한승희, "기계번역과 인간번역, 기계번역 사후편집본과 인간번역 감수본의 품질평가 비교 연구 - 한-노 번역 사례를 중심으로", 통번역학연구, 26(1), pp.195~219 (2022), 통번역연구소[DOI]
- Daems, Joke, "On the Origin of Errors: A Fine-grained Analysis of MT and PE Errors and Their Relationship", Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pp.62~66 (2014)
- Daems, Joke, "The Impact of Machine Translation Error Types on Post-editing Effort Indicators", Proceedings of the 4th Workshop on Post-Editing Technology and Practice, pp.31~45 (2015)
- Escartín, Carla Parra, "Translation Revison and Post-editing: Industry Practices and Cognitive Processes", pp.89~106 (2021), Routledge
- Hu, Kevin Ke, "How MT Errors Correlate with Post-editing Effort: A New Ranking of Error Types", Asia Pacific Translation and Intercultural Studies, 7(3), pp.299~309 (2020)
- Koponen, Maarit, "Post-editing Time as a Measure of Cognitive Effort", Proceedings of the AMTA 2012 Workshop on Post-editing Technology and Practice, pp.11~20 (2012)
- Lacruz, Isabel, "Post-editing of Machine Translation Processes and Applications", pp.246~272 (2014), Cambridge Scholars Publishing
- Mitchell, Linda, "The Potential and Limits of Lay Post-editing in an Online Community", Proceedings of the 18th Annual Conference of the European Associations for Machine Translation, pp.67~74 (2015)
- O’Brien, Sharon, "Teaching Post-editing: A Proposal for Course Content", Proceedings of the 6th EAMT Workshop: Teaching Machine Translation, pp.99~106 (2002)
- Popović, Maja, "Relations between Different Types of Post-editing Operations, Cognitive Effort and Temporal Effort", Proceedings of the Seventeenth Annual Conference of the European Association for Machine Translation (EAMT14), pp.191~198 (2014)
- Sánchez-Gijón, Pilar, "MT Post-editing into the Mother Tongue or into a Foreign Language? Spanish-to-English MT Translation Output Post-edited by Translation Trainees", Third Workshop on Post-Editing Technology and Practice (AMTA), pp.5~19 (2014)
- Temnikova, Irina, "Cognitive Evaluation Approach for a Controlled Language Post-editing Experiment", Proceedings of the 7th International Conference on Language Resources and Evaluation. European Language Resources (ELRA), pp.3485~3490 (2010)
- Vardaro, Jennifer, "Translation Quality and Error Recognition in Professional Neural Machine Translation Post-editing", Informatics, 6(3), pp.1~29 (2019)
- Zaretskaya, Anna, "Comparing Post-editing Difficulty of Different Machine Translation Errors in Spanish and German Translations from English", International Journal of Language and Linguistics, 3(3), pp.91~100 (2016)