기계번역의 오류 양상과 사후수정(post-editing)이L2 쓰기 적절성에 미치는 영향
Machine translation errors and the effect of post-editing on the appropriateness of revised L2 texts
1
조회
0
다운로드
10
인용
0
참고문헌
키워드
초록
Although machine translation (MT) such as Google Translate (GT) may be used by second language (L2) learners to solve lexical and syntactic problems for L2 writing, the use of MT requires L2 learners to notice errors in MT output and post-edit MT errors. The purposes of the study were to 1) analyze the types of MT errors; 2) examine how post-editing of MT errors would have an effect on sentence adequacy scores of post-edited texts; and 3) examine any differences between the MT output and post-edited texts on measures of lexical and syntactic complexity. To this end, 57 L2 university learners were asked to compose a text in L1, translate it with GT, and post-edit the text for any mistranslations, ungrammatical sentences, or incomplete expressions. The MT output produced a total of 931 sentences of which 600 sentences (64.5%) were without any errors. Three hundred and thirty-one sentences had errors in the areas of mistranslation (65.56%), ungrammaticality (16.11%), missing word (16.94%), and extra words (1.39%). When the effectiveness of post-editing was examined, the total mean of sentence adequacy scores was found to have improved significantly in comparison to those of the machine translator. Examination of lexical and syntactic complexity measures indicated an increased number of sentences but a drop in the number of coordinate phrases in the post-edited texts. The results are discussed as to how MT can be used to help learners improve their L2 writing skills.
Abstract
Although machine translation (MT) such as Google Translate (GT) may be used by second language (L2) learners to solve lexical and syntactic problems for L2 writing, the use of MT requires L2 learners to notice errors in MT output and post-edit MT errors. The purposes of the study were to 1) analyze the types of MT errors; 2) examine how post-editing of MT errors would have an effect on sentence adequacy scores of post-edited texts; and 3) examine any differences between the MT output and post-edited texts on measures of lexical and syntactic complexity. To this end, 57 L2 university learners were asked to compose a text in L1, translate it with GT, and post-edit the text for any mistranslations, ungrammatical sentences, or incomplete expressions. The MT output produced a total of 931 sentences of which 600 sentences (64.5%) were without any errors. Three hundred and thirty-one sentences had errors in the areas of mistranslation (65.56%), ungrammaticality (16.11%), missing word (16.94%), and extra words (1.39%). When the effectiveness of post-editing was examined, the total mean of sentence adequacy scores was found to have improved significantly in comparison to those of the machine translator. Examination of lexical and syntactic complexity measures indicated an increased number of sentences but a drop in the number of coordinate phrases in the post-edited texts. The results are discussed as to how MT can be used to help learners improve their L2 writing skills.
참고문헌 (36)
- 국가영어능력평가시험 대비 영어 말하기․쓰기 평가매뉴얼: 고등학교용, "신동광", 한국교육과정평가원, ~, pp.연구자료 ORM 2012-67 (2012)
- 윤채원, "기계 번역의 오류 유형 분석과 학습자들의 오류 수정 전략", 석사, pp.2021
- 이윤재, "영어자동번역기 활용이 고등학생 영어 글쓰기에 미치는 영향", 영어교과교육, 19(2), pp.159~180 (2020), 한국영어교과교육학회[DOI]
- 이준호, "포스트에디팅 교육을 위한 포스트에디팅과 인간번역의 차이 연구", 통역과 번역, 20(1), pp.73~96 (2018), 한국통역번역학회[DOI]
- 임희주, "교양영어 수업에서 영어자동번역기 사용에 대한 대학생의 인식 및 태도연구 ― 영작문 수업을 중심으로", 교양교육연구, 11(6), pp.727~751 (2017), 한국교양교육학회
- 안수진, "Students’ Perceptions of the Use of Online Machine Translation in L2 Writing", 멀티미디어 언어교육, 23(2), pp.10~35 (2020), 한국멀티미디어언어교육학회[DOI]
- Alhaisoni, E., "students’ attitudes towards the use of Google", International Journal of English Language Education, 5(1), pp.72~82 (2017)[DOI]
- Bowker, L, "Machine translation and global research: Towards improved machine translation literacy in the scholarly community" (2019), Emerald Publishing
- Brown, T. B., "Language models are few-shot learners", ArXiv. https:, arxiv.org, pp.pdf, 2005.14165v4[DOI]
- 전유아, "Direct Writing, Translated Writing, and Machine-Translated Writing: A Text Level Analysis with Coh-Metrix", 영어교육, 75(1), pp.25~48 (2020), 한국영어교육학회
- 정은선, "The Effect of L2 Proficiency on Post-editing Machine Translated Texts", Journal of Asia TEFL, 17(1), pp.182~193 (2020), 아시아테플
- Daems, J., "The impact of machine translation error types on post-editing effort indicators", 4th Workshop on Post-Editing Technology and Practice, pp.31~45 (2015), Association for Machine Translation in the Americas
- Daniels, P., "Grammar software ready for EFL writers?", OnCUE Journal, 9(4), pp.391~401 (2013)[DOI]
- Ferris, D., "Treatment of error in second language student writing" (2011), University of Michigan Press
- Gaskell, D., "Can learners use concordance feedback for writing errors?", System, 32(3), pp.301~319 (2004)[DOI]
- Grant, L., "Using computer-tagged linguistic features to describe L2 writing differences", Journal of Second Language Writing, 9(2), pp.123~145 (2000)[DOI]
- Groves, M., "Friend or foe? Google Translate in language for academic purposes", English for Specific Purposes, 37, pp.112~121 (2015)[DOI]
- Grammatical structures written at three grade levels, "Hunt, K.", NCTE, ~, pp.NCTE Research Rep. No. 3 (1965)
- Hwang, G-J., "Vision, challenges, roles and research issues of Artificial Intelligence in Education", Computers & Education : Artificial Intelligence, 1, pp.100001~ (2020)[DOI]
- Jia, Y., "How does the post-editing of neural machine translation compare with from-scratch translation? : A product and process study", The Journal of Specialised Translation, 31, pp.60~86 (2019)[DOI]
- 정연주, "Predicting Second Language Writing Proficiency in Learner Texts Using Computational Tools", Journal of Asia TEFL, 16(1), pp.37~52 (2019), 아시아테플
- 김나영, "Effects of the Use of Bilingual Dictionary and Machine Translation on EFL Students' English Proficiency", 영어교과교육, 17(1), pp.21~42 (2018), 한국영어교과교육학회[DOI]
- 김성우, "Playing with Machine Translation in Language Classroom: Affordances and Constraints", 멀티미디어 언어교육, 22(2), pp.9~28 (2019), 한국멀티미디어언어교육학회[DOI]
- Kol, S., "Google Translate in academic writing courses?", The EuroCALL Review, 26(2), pp.50~57 (2018)[DOI]
- Lee, S. M., "The impact of using machine translation on EFL students’ writing", Computer Assisted Language Learning, 33(3), pp.157~175 (2020)[DOI]
- Lee, S. M., "Effects of using machine translation to mediate the revision process of Korean university students’ academic writing", ReCALL, 33(1), pp.18~33 (2021)[DOI]
- Lu, X., "Automatic analysis of syntactic complexity in second language writing", International Journal of Corpus Linguistics, 15(4), pp.474~496 (2010)[DOI]
- Lu, X., "The relationship of lexical richness to the quality of ESL learners' oral narratives", The Modern Language Journal, 96(2), pp.190~208 (2012)[DOI]
- "GPT-3: An AI breakthrough, but not coming for your job" (2020)[URL]
- O'Sullivan, I., "Learners’ writing skills in French : Corpus consultation and learner evaluation", Journal of Second Language Writing, 15, pp.46~68 (2006)[DOI]
- PACTE Group, "Investigating translation competence. Conceptual and methodological issues", Meta : Translators' Journal, 50(2), pp.609~619 (2005)[DOI]
- Pokrivcakov, S., "Preparing teachers for the application of AI-powered technologies in foreign language education", Journal of Language and Cultural Education, 7(3), pp.136~153 (2019)[DOI]
- Shin, D., "The effect of using online language-support resources on L2 writing performance", Language Testing in Asia, 11(4) (2021)[DOI]
- Tian, L., "Learner engagement with automated feedback, peer feedback and teacher feedback in an online EFL writing context", System, 91, pp.102247~ (2020)[DOI]
- Tsai, S. -C., "Using Google Translate in EFL drafts: A preliminary investigation", Computer Assisted Language Learning, 32(5-6), pp.510~526 (2019)[DOI]
- Vilar, D., "Error analysis of statistical machine translation output", Proceedings of the 5th International Conference on Language Resources and Evaluation, pp.697~702 (2006), European Language Resources Association (ELRA)