ChatGPT翻译的译前编辑策略探究——以《英译中国现代散文选》为例
Study on Pre-Editing Strategies of ChatGPT Translation—Taking “Selected Modern Chinese Essays” as an Example
DOI: 10.12677/ml.2024.1210898, PDF,   
作者: 何长睿：曲阜师范大学外国语学院，山东 曲阜
关键词: 译前编辑；ChatGPT；汉译英；Pre-Editing； ChatGPT； Chinese-English Translation
摘要: 本研究从准确性、可读性、创造性、风格和文化适应度5个维度对ChatGPT的译文进行人工评测，通过观察有无译前编辑的两组译文在5个维度的表现来评估编辑的有效性、探索编辑方法。研究发现：1) 译前编辑主要侧重于语义和文化方面，编辑后的译文在准确性、可读性方面具有显著提升。2) 译前编辑体现了人类的创意和主体性，使机器能捕捉到原文的意蕴及情感，减少了译后编辑的不确定性和所需时间。3) 由于机翻错误的不可预知性，译前编辑并不能解决译文存在的所有问题。若想获得高质量的译文，译前编辑和译后编辑在人机协作中都不可或缺。
Abstract: Through human evaluation of ChatGPT translation texts from five aspects: accuracy, readability, creativity, style and cultural adaptation, this study aims to explore the effectiveness and strategies of the pre-editing. The study yields the following findings: 1) Pre-editing strategies are mainly based on semantic and cultural levels, letting the translation texts have a significant improvement in accuracy and readability. 2) Pre-editing reflects the creativity and subjectivity of human, enabling the machine to capture the connotations and emotions of the original texts, and reducing the uncertainty and time required for post-editing. 3) Due to the unpredictability of machine errors, pre-editing cannot resolve all problems of translation texts. Both post-editing and pre-editing are indispensable during the human-machine cooperation process.
文章引用：何长睿. ChatGPT翻译的译前编辑策略探究——以《英译中国现代散文选》为例[J]. 现代语言学, 2024, 12(10): 334-345. https://doi.org/10.12677/ml.2024.1210898

参考文献

[1] Zamfiroiu, A., Vasile, D. and Savu, D. (2023) ChatGPT—A Systematic Review of Published Research Papers. Informatica Economica, 27, 5-16. [Google Scholar] [CrossRef] 
[2] Nugroho, A., Putro, N.H.P.S. and Syamsi, K. (2023) The Potentials of ChatGPT for Language Learning: Unpacking Its Benefits and Limitations. Register Journal, 16, 224-247. [Google Scholar] [CrossRef] 
[3] 王华树, 谢亚. ChatGPT时代翻译技术发展及其启示[J]. 外国语言与文化, 2023, 7(4): 80-89.
[4] Cotton, D.R.E., Cotton, P.A. and Shipway, J.R. (2023) Chatting and Cheating: Ensuring Academic Integrity in the Era of ChatGPT. Innovations in Education and Teaching International, 61, 228-239. [Google Scholar] [CrossRef] 
[5] Mijwil, M., Hiran, K.K., Doshi, R., Dadhich, M., Al-Mistarehi, A. and Bala, I. (2023) ChatGPT and the Future of Academic Integrity in the Artificial Intelligence Era: A New Frontier. Al-Salam Journal for Engineering and Technology, 2, 116-127. [Google Scholar] [CrossRef] 
[6] 徐华东, 姚振军. 后现代语境中机译伦理问题研究[J]. 上海翻译, 2023(5): 12-17.
[7] 叶子南. 在ChatGPT时代, 人译独领风骚[J]. 中国翻译, 2023, 44(3): 173-178.
[8] 蔡力坚. 算法与翻译[J]. 中国翻译, 2023, 44(4): 179-187.
[9] 王克非. 智能时代翻译之可为可不为[J]. 外国语(上海外国语大学学报), 2024, 47(1): 5-9, 13.
[10] 李长栓. 利用ChatGPT做好中译外[J]. 民族翻译, 2023(4): 74-85.
[11] 耿芳, 胡健. 人工智能辅助译后编辑新方向——基于ChatGPT的翻译实例研究[J]. 中国外语, 2023, 20(3): 41-47.
[12] 张文煜, 赵璧. 生成式人工智能开创机器翻译的新纪元了吗?——一项质量对比研究及对翻译教育的思考[J]. 北京第二外国语学院学报, 2024, 46(1): 83-98.
[13] 王和私, 马柯昕. 人工智能翻译应用的对比研究——以生物医学文本为例[J]. 中国科技翻译, 2023, 36(3): 23-26.
[14] 文旭, 田亚灵. ChatGPT应用于中国特色话语翻译的有效性研究[J]. 上海翻译, 2024(2): 27-34, 94-95.
[15] 赵雪, 赵志枭, 孙凤兰, 等. 面向语言文学领域的大语言模型性能评测研究[J]. 外语电化教学, 2023(6): 57-65+114.
[16] 冯全功, 李嘉伟. 新闻翻译的译后编辑模式研究[J]. 外语电化教学, 2016(6): 74-79.
[17] 夏玲, 李宜蔓, 李弘武. 人工智能背景下科技论文摘要的机器翻译与译后编辑[J]. 编辑学报, 2022, 34(4): 396-401, 406.
[18] 冯全功, 高琳. 基于受控语言的译前编辑对机器翻译的影响[J]. 当代外语研究, 2017(2): 63-68, 87, 110.
[19] Wang, J. (2023) A ChatGPT-Driven Study of Translating and Post-Editing Chinese Enterprise Publicity Materials. Modern Languages, Literatures, and Linguistics, 2, 7-17.
[20] 王俊超. 人工智能语言服务视域下中国语言景观翻译编辑模式新论[J]. 语言服务研究, 2024, 4(1): 3-22.
[21] 黄越悦. 浅谈机器翻译中译前编辑的应用[J]. 湖北函授大学学报, 2017, 30(3): 175-176, 179.
[22] 仇全菊. 人工智能背景下汉译英译前编辑策略探究[J]. 青岛职业技术学院学报, 2023, 36(2): 23-26.
[23] 仲文明, 徐佳敏, 李芸昕. 机译中汉语科技文本的模糊特质与译前编辑[J]. 中国科技翻译, 2021, 34(4): 36-39, 42.
[24] 李国兵, 张敬. 译前编辑对译后编辑、译文质量和翻译效率的影响[J]. 当代外语教育, 2023(1): 146-158.
[25] Babych, B., Hartley, A. and Sharoff, S. (2009) Evaluation-Guided Pre-Editing of Source Text: Improving MT-Tractability of Light Verb Constructions. Proceedings of the 13th Annual conference of the European Association for Machine Translation, European Association for Machine Translation, Barcelona, 14-15 May 2009, 36-43.
[26] Hiraoka, Y. and Yamada, M. (2019) Pre-Editing Plus Neural Machine Translation for Subtitling: Effective Pre-Editing Rules for Subtitling of TED Talks. Proceedings of Machine Translation Summit XVII: Translator, Project and User Tracks, Dublin, August 2019, 64-72.
[27] Lommel, A., Uszkoreit, H. and Burchardt, A. (2014) Multidimensional Quality Metrics (MQM): A Framework for Declaring and Describing Translation Quality Metrics. Tradumàtica tecnologies de la traducció, No. 12, 455-463. [Google Scholar] [CrossRef] 
[28] 秦洪武, 周霞. 大语言模型与语言对比研究[J]. 外语教学与研究, 2024, 56(2): 163-176, 318.
[29] Alawida, M., Mejri, S., Mehmood, A., Chikhaoui, B. and Isaac Abiodun, O. (2023) A Comprehensive Study of ChatGPT: Advancements, Limitations, and Ethical Considerations in Natural Language Processing and Cybersecurity. Information, 14, 462-485. [Google Scholar] [CrossRef] 
[30] 冯志伟, 张灯柯. 人工智能中的大语言模型[J]. 外国语文, 2024, 40(3): 1-29.
[31] 王贇, 张政. ChatGPT人工智能翻译的隐忧与纾解[J]. 中国翻译, 2024, 45(2): 95-102.
[32] 冯志伟, 张灯柯. GPT与语言研究[J]. 外语电化教学, 2023(2): 3-11, 105.
[33] 秦洪武, 王雪敏. 译即“阐” “释”: 许国璋先生翻译思想探微[J]. 北京第二外国语学院学报, 2017, 39(1): 85-93, 134.
[34] 连淑能. 英汉对比研究[M]. 北京: 高等教育出版社, 1993.
[35] 黄伯荣, 廖旭东. 现代汉语[M]. 北京: 高等教育出版社, 2011.
[36] 王满良. 英汉主语比较[J]. 外语教学, 1999(1): 88-91, 96.
[37] Li, C.N. and Thompson, N. (1976) Subject and Topic: A New Typology of Language. Academic Press, 456-488.
[38] 翁义明, 王金平. 文学语篇机器翻译的特征与局限——汉语流水句人机英译对比研究[J]. 当代外语研究, 2020(6): 128-137.
[39] Jesperson, O. (1949) A Modern English Grammar on Historical Principles. Routledge.
[40] 杜安. ChatGPT时代人工翻译的价值空间与翻译教育转型[J]. 外国语言与文化, 2023, 7(4): 90-103.
[41] 梁君英, 刘益光. 人类智能的翻译能力优势——基于语料库的人机翻译对比研究[J]. 外语与外语教学, 2023(3): 74-84, 147-148.
[42] Nida, E.A. and Taber, C.R. (1974) The Theory and Practice of Translation. E.J. Brill.
[43] Bang, Y.S., Cahyawijaya, S., Lee, N., et al. (2023) Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity.
https://arxiv.org/pdf/2302.04023
[44] 王东风. 文化缺省与翻译中的连贯重构[J]. 外国语(上海外国语大学学报), 1997(6): 56-61.
[45] Nida, E.A. (2002) Language and Culture: Contexts in Translating. Foreign Language Education Press.
[46] Baker, K.L., Franz, A.M., Jordan, P.W., Mitamura, T. and Nyberg, E.H. (1994) Coping with Ambiguity in a Large-Scale Machine Translation System. Proceedings of the 15th conference on Computational linguistics, Kyoto, 5-9 August 1994, 90-94. [Google Scholar] [CrossRef] 
[47] Mitamura, T. and Nyberg, E. (1995) Controlled English for Knowledge-Based MT: Experience with the KANT System. Proceedings of the 6th International Conference on Theoretical and Methodological Issues in Machine Translation, Leuven, 5-7 July 1995, 94-99.
[48] 胡清平. 机器翻译中的受控语言[J]. 中国科技翻译, 2005, 18(3): 24-27.
[49] 胡开宝, 李翼. 机器翻译特征及其与人工翻译关系的研究[J]. 中国翻译, 2016, 37(5): 10-14.
[50] 李洋, 孙宁, 梁玉静. 基于机器翻译的人机交互译前编辑模式研究[J]. 语言教育, 2021, 9(2): 55-62.