Sentence Length and Translation: A Comparative Review of Human, NMT, and LLM Translations
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
This paper aims to investigate the handling of long sentences in Korean-to-English translation by human translators, large language models (LLMs), and neural machine translation (NMT). Using reliable human translations in the business reports genre as a reference, the article analyzes human, NMT, and LLM translations through three analytic phases: a quantitative comparison, a qualitative analysis, and retranslation after pre-editing. The analysis found that the sentence length in the original source texts negatively correlates with translation quality in MT outputs, and that NMT's tendency to preserve the original sentence boundary often led to omissions and incomplete translations. However, retranslation after pre-editing effectively fixed both issues. The findings in this article contribute to broadening the literature on machine translation by highlighting the need to focus on the linguistic characteristics of MT, exploring different translation tendencies of the LLM and NMT models, and enhancing the representativeness of test corpora.
Abstract
This paper aims to investigate the handling of long sentences in Korean-to-English translation by human translators, large language models (LLMs), and neural machine translation (NMT). Using reliable human translations in the business reports genre as a reference, the article analyzes human, NMT, and LLM translations through three analytic phases: a quantitative comparison, a qualitative analysis, and retranslation after pre-editing. The analysis found that the sentence length in the original source texts negatively correlates with translation quality in MT outputs, and that NMT's tendency to preserve the original sentence boundary often led to omissions and incomplete translations. However, retranslation after pre-editing effectively fixed both issues. The findings in this article contribute to broadening the literature on machine translation by highlighting the need to focus on the linguistic characteristics of MT, exploring different translation tendencies of the LLM and NMT models, and enhancing the representativeness of test corpora.
참고문헌 (46)
- Baker, M., "Terminology, LSP and translation", pp.175~186 (1996), John Benjamins
- Bisiada, M, "From Hypotaxis to Parataxis: An Investigation of English-German Syntactic Convergence in Translation", PhD, pp.2013
- Bizzoni, Y., "How human is machine translationese? comparing human and machine translations of text and speech", Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp.280~290 (2020)
- Blum-Kulka, S., "Strategies in Interlanguage Communication", pp.119~139 (1983), Longman
- Castilho, S., "Is neural machine translation the new state of the art?", The Prague Bulletin of Mathematical Linguistics, 108, pp.109~120 (2017)
- Chang, M., "Research on Text Difficulty Evaluation for Teaching Reading in Korean", PhD, pp.2012
- Choi, H. E, "A Study on the evaluation of Korean-English patent machine translation-focusing on KIPRIS K2E-PAT translation", Interpretation and Translation, 19(1), pp.139~178 (2017)
- Choi, M, "Assessing Source Text Difficulty for Interpreter Education: With a Focus on Textual Factors of English Source Texts in English-Korean Consecutive Interpreting", PhD, pp.2013
- Dale, E., "A formula for predicting readability : instructions", Educational Research Bulletin, 27(2), pp.37~54 (1948)
- Flesch, R., "A new readability yardstick", Journal of Applied Psychology, 32(3), pp.221~233 (1948)
- Goh, G. Y., "A corpus-based study of translation universals in English translations of Korean newspaper texts", Cross-Cultural Studies, 45, pp.109~143 (2016)
- Graesser, A. C., "Coh-Metrix : analysis of text on cohesion and language", Behavior Research Methods, Instruments, & Computers, 36(2), pp.193~202 (2004)
- Kim, K., "The influence of case markers on the machine-translation of Korean proverbs into English", The Linguistic Association of Korea Journal, 26(3), pp.139~157 (2018)
- Derivation of New Readability Formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy Enlisted Personnel (RESEARCH BRANCH REPORT 8-75;Naval Technical Training), "Kincaid, J. P.", Defense Technical Information Center, ~ (1975)
- Koo, M. J., "A Study of text difficulty analysis on the Korean reading materials", Journal of Korean Language Education, 22(2), pp.27~48 (2011)
- Koo, "A Study on Measuring Text Difficulty for Korean Reading Education", PhD, pp.2013
- "KRX Series: KTOP30"[URL]
- Lee, C. S., "A study of lexical usage differences between human and machine translation in English translations of Korean newspaper editorials", Interpretation and Translation, 22(1), pp.245~262 (2020)
- Lee, C. S., "Machine learning classification of literary translation samples by human and machine translators", The Journal of Translation Studies, 22(1), pp.199~217 (2021)
- Lee, C. S., "A follow-up study of stylistic differences between human and machine translation with ChatGPT added in the mix", The Journal of Translation Studies, 24(3), pp.539~561 (2023)
- Lee, J., "A Study on performance evaluation of an specialized machine translation engine in the legal domain : focusing on the Korean-to-English translation of legal contracts", T&I Review, 12(1), pp.169~192 (2022)
- Lee, J. H., "Human interpretation and machine translations based upon interviews with Director Joon-ho Bong", Korean Journal of English Language and Linguistics, 23, pp.204~219 (2023)
- Lee. J., "A case study of Korean-English machine translation of dual subject sentences : a comparison of statutory translations by Google Translate and Naver Papago", T&I Review, 12(1), pp.211~241 (2022)
- Lee, J., "A case study on the evaluation of Korean-English legal translations by generic and custom neural machine translation engines", Interpretation and Translation, 25(1), pp.75~98 (2023)
- Lee, J., "A case study on the quality of machine translation and the source text difficulty : a case of a Korean-English statutory translation by Google Translate", Journal of Linguistic Studies, 28(1), pp.77~101 (2023)
- Lee, J. H., "An analysis of Korean-English translation errors in Google Translate", The Journal of Linguistics Science, 89, pp.221~257 (2019)
- Lee, J. H., "A study of error types in Korean-English translation from Korean spoken language to Papago", Modern English Education, 23(1), pp.56~65 (2022)
- Lee, S. B., "Review of literature on machine translation : based on arts and humanities journals covered in KCI Journal Database(from 2011 to early 2020)", Interpretation and Translation, 22(2), pp.75~104 (2020)
- Lee, S., "The development of a web-based automatic text complexity measurement program", Journal of Korean Language Education, 30(2), pp.163~180 (2019)
- Lee, S. H., "A study on the difficulty distribution of texts for Korean education using the text difficulty measurement program", The Studies of Korean Language and Literature, 68, pp.425~450 (2020)
- Lee, Y. C., "Spotting non-nativeness in L2 texts : a statistical approach to translationese", Studies in English Language & Literature, 45(1), pp.367~388 (2019)
- Lommel, A., "Translation Quality Assessment", pp.109~127 (2018), pringer Cham
- Luo, J., "Universals in machine translation?", International Journal of Corpus Linguistics, 27(1), pp.31~58 (2022)
- Lyu, Q., "Translating radiology reports into plain language using ChatGPT and GPT-4 with prompt learning: results, limitations, and potential", Visual Computing for Industry, Biomedicine, and Art, 6(1) (2023)
- Papineni, K., "BLEU: a method for automatic evaluation of machine translation", Proceedings of ACL-2002: 40th Annual meeting of the Association for Computational Linguistics, pp.311~318 (2002)
- Park, O., "Error analysis according to the typological characteristics of source text in Korean-English machine translation", The Journal of Society for Humanities Studies in East Asia, 41, pp.155~183 (2017)
- Park, O., "Error analysis and criterion for correcting error of machine translation in terms of source language : based on the syntactic characteristics of non-literary texts", Dongainmunhak, 44, pp.151~171 (2018)
- Ragni, V., "What has changed with neural machine translation? a critical review of human factors", Perspectives : Studies in Translation Theory and Practice, 30(1), pp.137~158 (2022)
- The Lexile scale in theory and practice:final report for NIH grant ID-19448, "Smith, D. R.", International Reading Association, ~ (1989)
- ".Retrievedfrom" (2023)[URL]
- Yim, J., "Translation universals in translated CEO letters in sustainability reports", The Journal of Translation Studies, 20(5), pp.131~162 (2019)
- Yim, J., "NMT vs. LLM - focused on long-sentence translation", 2023 Fall Proceedings of the Korea Association of Translation Studies, pp.92~104 (2023)
- Zhang, M., "The effect of translationese in machine translation test sets", WMT 2019 - 4th Conference on Machine Translation, Proceedings of the Conference, 1, pp.73~81 (2019)