Comparative analysis of human and machine translation: Focusing on George Orwell's Animal Farm
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper introduces a computational method for distinguishing machine-generated text from human-written text, employing both qualitative and quantitative analyses. To differentiate human and machine translation, the degree of similarity between chapters was examined. This involved unsupervised clustering and supervised SVM, focusing on George Orwell's well-known literary masterpiece, Animal Farm. Text cohesion within the structural framework distinguished the original English text from its English-to-Korean translations. Furthermore, contrasting Korean translated texts revealed that human translation captures the intended meaning more effectively. Conversely, when back-translated into English, machine translation's semantic connections closely mirrored those of the original text. These findings contribute to the ongoing discussion of translation quality and the challenges of achieving semantic fidelity in various translation contexts.
Abstract
This paper introduces a computational method for distinguishing machine-generated text from human-written text, employing both qualitative and quantitative analyses. To differentiate human and machine translation, the degree of similarity between chapters was examined. This involved unsupervised clustering and supervised SVM, focusing on George Orwell's well-known literary masterpiece, Animal Farm. Text cohesion within the structural framework distinguished the original English text from its English-to-Korean translations. Furthermore, contrasting Korean translated texts revealed that human translation captures the intended meaning more effectively. Conversely, when back-translated into English, machine translation's semantic connections closely mirrored those of the original text. These findings contribute to the ongoing discussion of translation quality and the challenges of achieving semantic fidelity in various translation contexts.
참고문헌 (18)
- Ahrenberg, L., "Comparing machine translation and human translation: A case study", Papers at the Workshop Human-Informed Translation and Interpreting Technology, pp.21~28 (2017), Association for Computational Linguistics
- Baker, M., "Corpora in translation studies : An overview and some suggestions for future research", Target, 7(2), pp.223~243 (1995)
- Bhardwaj, S., "Human or neural translation?", Papers at the 28th International Conference on Computational Linguistics, pp.6553~6564 (2020), International Committee on Computational Linguistics
- Bizzoni, Y., "How human is machine translationese? Comparing human and machine translations of text and speech", Papers at the 17th International Conference on Spoken Language Translation (IWSLT), pp.280~290 (2020), Association for Computational Linguistics
- Chichirau, M., "Automatic discrimination of human and neural machine translation in multilingual scenarios", Papers at the 24th Annual Conference of the European Association for Machine Translation, pp.217~226 (2023), European Association for Machine Translation
- Halliday, M. A. K., "Cohesion in English" (1976), Longman Publishing
- Hansen-Schirra, S., "Cross-linguistic corpora for the study of translations. Insights from the language pair English-German" (2012), Mouton de Gruyter
- Lapshinova-Koltunski, E., "New perspectives on cohesion and coherence", pp.95~118 (2017), Language Science Press
- Muftah, M., "Machine vs human translation: a new reality or a threat to professional Arabic-English translators", PSU Research Review (2022)
- Orwell, G., "Animal farm" (1945), Secker and Warburg
- Orwell, G., (1998), 민음사
- Teich, E., "Cross-linguistic variation in system and text. A methodology for the investigation of translations and comparable texts" (2003), Mouton de Gruyter
- Toral, A., "Post-editese: an exacerbated translationese", Papers at Machine Translation Summit XVII: Research Track, pp.273~281 (2019), European Association for Machine Translation
- van der Werff, T., "Automatic discrimination of human and neural machine translation: A study with multiple pre-trained models and longer context", Papers at the 23rd Annual Conference of the European Association for Machine Translation, pp.161~170 (2022), European Association for Machine Translation
- Vanmassenhove, E., "Lost in translation: Loss and decay of linguistic richness in machine translation", Papers at Machine Translation Summit XVII: Research Track, pp.222~232 (2019), European Association for Machine Translation