GenAI时代机器翻译译后编辑的发展与趋势
Keywords:
生成式人工智能；机器翻译；译后编辑；大语言模型；人机协作Abstract
机器翻译译后编辑是兼顾翻译质量、效率与成本的重要生产方式。早期译后编辑主要指译者对机器翻译输出进行检查和修正，其工作重点是纠正词汇、句法、术语及格式错误。神经机器翻译提高了译文流畅度，也使部分语义错误更难被发现。生成式人工智能及大语言模型的兴起进一步改变了译后编辑的对象、流程和人员角色。译后编辑逐渐从句段层面的错误修正，扩展为包含提示词设计、上下文管理、事实核查、风格控制和风险审查的全过程质量管理。本文梳理机器翻译译后编辑从传统机器翻译、神经机器翻译到生成式人工智能辅助翻译的发展，分析GenAI给译后编辑带来的效率收益及质量风险，并讨论未来工作流程、质量评价、职业分工和人才培养的发展方向。研究认为，GenAI不会消除译后编辑，而会促使其从语言修订活动转向以人类监督为核心的翻译质量治理。
References
[1]崔启亮. (2014). 论机器翻译的译后编辑. 中国翻译, (6), 68–73.
[2]Karpinska, M., & Iyyer, M. (2023). Large language models effectively leverage document-level context for literary translation, but critical errors persist. In Proceedings of the Eighth Conference on Machine Translation (pp. 419–451). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.wmt-1.41
[3]Koponen, M. (2016). Is machine translation post-editing worth the effort? A survey of research into post-editing and effort. The Journal of Specialised Translation, 25, 131–148. https://doi.org/10.26034/cm.jostrans.2016.303
[4]Sarti, G., Bisazza, A., Guerberof-Arenas, A., & Toral, A. (2022). DivEMT: Neural machine translation post-editing effort across typologically diverse languages. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (pp. 7795–7816). Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.emnlp-main.532
[5]Wang, L., Lyu, C., Ji, T., Zhang, Z., Yu, D., Shi, S., & Tu, Z. (2023). Document-level machine translation with large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 16646–16661). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.emnlp-main.1036
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 郑书政, 王佩琳霖, Wonggy Mia
This work is licensed under a Creative Commons Attribution 4.0 International License.
