챗GPT 출현 이후 기계 번역과 인간 번역 간의 번역 문체 차이 변화 연구
A Follow-up Study of Stylistic Differences between Human and Machine Translation with ChatGPT Added in the Mix
0
조회
0
다운로드
14
인용
0
참고문헌
키워드
초록
The present study explores whether new shifts have developed in the stylistic landscape of human vs. machine translation in the wake of ChatGPT’s arrival. For this purpose, it conducts a series of principal component analyses (PCAs) on a normalized frequency dataset comprising 67 morphological and syntactic linguistic features borrowed from Biber’s (1988) research on register variation. The dataset is derived from a corpus of Korean editorials from three Korean newspapers, their human English translations, and English translations generated by four machine translation systems (Papago, Google, DeepL, ChatGPT), including ChatGPT’s self-proofread versions. The analyses indicate that human and machine translation remain distinctly differentiated in terms of style, as demonstrated in previous studies. However, among the machine translation systems, ChatGPT, both in its translations and self-proofread versions, deviates significantly from the others. A closer examination of the linguistic features strongly associated with ChatGPT reveals that this difference can be attributed to the model’s intrinsic preference for a formal, written style. Notably, there are no substantial stylistic divergences between ChatGPT’s translations and its self-proofread versions.
Abstract
The present study explores whether new shifts have developed in the stylistic landscape of human vs. machine translation in the wake of ChatGPT’s arrival. For this purpose, it conducts a series of principal component analyses (PCAs) on a normalized frequency dataset comprising 67 morphological and syntactic linguistic features borrowed from Biber’s (1988) research on register variation. The dataset is derived from a corpus of Korean editorials from three Korean newspapers, their human English translations, and English translations generated by four machine translation systems (Papago, Google, DeepL, ChatGPT), including ChatGPT’s self-proofread versions. The analyses indicate that human and machine translation remain distinctly differentiated in terms of style, as demonstrated in previous studies. However, among the machine translation systems, ChatGPT, both in its translations and self-proofread versions, deviates significantly from the others. A closer examination of the linguistic features strongly associated with ChatGPT reveals that this difference can be attributed to the model’s intrinsic preference for a formal, written style. Notably, there are no substantial stylistic divergences between ChatGPT’s translations and its self-proofread versions.
참고문헌 (28)
- 이창수, "기계학습 알고리즘을 활용한 문학번역에서의 기계 번역과 인간 번역 결과물 분류 연구", 번역학연구, 22(1), pp.199~217 (2021), 한국번역학회[DOI]
- 이현주, "문학작품의 중-한 기계번역 결과의 결속구조 분석 - 인간번역과의 비교를 중심으로", 중어중문학, (87), pp.259~282 (2022), 한국중어중문학회[DOI]
- 전혜진, "AI 시대, 문학번역에서 기계번역과 인간번역 비교분석 연구 - 똘스또이의 『유년시절』번역 분석을 중심으로", 노어노문학, 31(1), pp.111~154 (2019), 한국노어노문학회
- 한승희, "인간번역, 기계번역, 컴퓨터보조번역 간 문체 비교 연구: SFL 이론을 중심으로", 박사, pp.2020
- Biber, Douglas, "Variation across Speech and Writing" (1988), Cambridge UP
- BIber, Douglas, "Dimensions of Register Variation: A Cross-linguistic Comparison" (1995), Cambridge UP
- Burrows, John, "The Englishing of Juvenal : Computational Stylistics and Translated Texts", Style, 36(4), pp.677~699 (2002)
- Hu, Xianyao, "How Do English Translations Differ from Non-Translated English Writings? A Multi-Feature Statistical Model for Linguistic Variation Analysis", Corpus Linguistics and Linguistic Theory, 15(2), pp.347~382 (2019)
- Kocoń, Jan, "ChatGPT: Jack of All Trades, Master of None", Information Fusion, 99, pp.1~37 (2023)
- Kunilovskaya, Maria, "Translationese Features as Indicators of Quality in English-Russian Human Translation", Proceedings of the Human-Informed Translation and Interpreting Technology Workshop (HiT-IT 2019), pp.47~56 (2019)
- Lars, Ahrenberg, "Comparing Machine Translation and Human Translation: A Case Study", RANLP 2017 The First Workshop on Human-Informed Translation and Interpreting Technology (HiT-IT) Proceedings of the Workshop, pp.21~28 (2017), Association for Computational Linguistics
- Lee, Changsoo, "Do Language Combinations Affect Translators’ Stylistic Visibility in Translated Texts?", Digital Scholarship in the Humanities, 33(3), pp.592~603 (2018)
- Nini, Andrea, "Multi-Dimensional Analysis: Research Methods and Current Issues", pp.67~94 (2019), Bloomsbury Academic
- Oakes, Michael, "Computational Stylometry of Wittgensteins Diktat fȕr Schlick", Bergen Language and Linguistics Studies (BcLLs), 3(1), pp.221~240 (2013)
- Rothwell, Andrew, "Translation Tools and Technologies" (2023), Routledge
- Rybicki, Jan, "Burrowing into Translation : Character Idiolects in Henryk Sienkiewicz’s Trilogy and Its Two English Translations", Literary and Linguistic Computing, 21(1), pp.91~103 (2008)
- Rybicki, Jan, "Quantitative Methods in Corpus-Based Translation Studies", pp.231~248 (2012), John Benjamins
- Stamatatos, Efstathios, "Automatic Text Categorization in Terms of Genre and Author", Computational Linguistics, 26(4), pp.471~495 (2000)
- Rebecca Webster, "Gutenberg Goes Neural: Comparing Features of Dutch Human Translations with Raw Neural Machine Translation Outputs in a Corpus of English Literary Classics", Informatics, 7(3), pp.32~ (2020), MDPI AG[DOI]
- Westin, Ingrid, "Language Change in English Newspaper Editorials" (2002), Rodopi