多模态机器翻译发展现状研究
Research on Current Development Status of Multimodal Machine Translation
摘要: 随着科学技术的高速发展，多模态机器翻译(Multimodal Machine Translation, MMT)作为新兴的计算机辅助翻译技术，日益受到关注。本文聚焦于多模态机器翻译的发展现状，深入剖析其定义、技术路径、应用领域以及面临的挑战，并探讨其对翻译变革的影响。通过对相关文献的梳理和技术方法的分析，全面呈现多模态机器翻译的研究进展和实际应用场景，同时针对其面临的挑战提出相应的解决策略，旨在为该领域的进一步研究提供坚实的理论基础和有益的参考，推动多模态机器翻译技术的持续发展和在翻译实践中的更广泛应用。
Abstract: The rapid advancement of science and technology has propelled Multimodal Machine Translation (MMT) into the spotlight as a cutting-edge computer-aided translation technology. This paper centers on the current development status of MMT, delving into its definition, technical pathways, application domains, challenges, and implications for translation transformation. By meticulously examining relevant literature and technical approaches, it offers a comprehensive overview of MMT’s research progress and real-world applications. Moreover, it offers targeted solutions to the encountered challenges and contemplates the impact of MMT on the translation landscape, thereby laying a robust theoretical groundwork for further exploration and propelling the ongoing evolution and practical deployment of MMT technology within the translation realm.
文章引用：沈思娴. 多模态机器翻译发展现状研究[J]. 现代语言学, 2025, 13(5): 604-609. https://doi.org/10.12677/ml.2025.135514

参考文献

[1] 许钧. 翻译概论(修订版) [M]. 北京: 外语教学与研究出版社, 2020.
[2] Catford, J. (1965) A Linguistics Theory of Translation. Oxford University Press.
[3] Li, L. (2014) Evolving Academic Libraries in the Future. In: Li, L., Ed., Scholarly Information Discovery in the Networked Academic Learning Environment, Elsevier, 279-309. [Google Scholar] [CrossRef] 
[4] 李小华, 唐青叶. 国内多模态翻译研究的可视化分析: 现状、问题及建议[J]. 北京科技大学学报(社会科学版), 2021, 37(5): 534-542.
[5] 吴赟. 媒介转向下的多模态翻译研究[J]. 外国语(上海外国语大学学报), 2021, 44(1): 115-123.
[6] Díaz-Cintas, J. and Muñoz-Sánchez, P. (2006) Fansubs: Audiovisual Translation in an Amateur Environment. Journal of Specialised Translation, No. 6, 37-52.
[7] Elliott, D., Frank, S. and Hasler, E. (2016) Multilingual Image Description with Neural Sequence Models. Proceedings of the International Conference on Learning Representations, 1, 1-16.
[8] Calixto, I., Elliott, D. and Frank, S. (2016) DCU-UvA Multimodal MT System Report. Proceedings of the First Conference on Machine Translation, 2, 634-638. [Google Scholar] [CrossRef] 
[9] Caglayan, O., Kuyu, M., Amac, M.S., Madhyastha, P., Erdem, E., Erdem, A., et al. (2021) Cross-Lingual Visual Pre-Training for Multimodal Machine Translation. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, 19-23 April 2021, 1317-1324. [Google Scholar] [CrossRef] 
[10] Baltrusaitis, T., Ahuja, C. and Morency, L. (2019) Multimodal Machine Learning: A Survey and Taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 423-443. [Google Scholar] [CrossRef] [PubMed]
[11] 胡富茂, 宋江文, 王文静. 多模态旅游翻译语料库建设与应用研究[J]. 上海翻译, 2022(5): 26-31.
[12] Calixto, I., Liu, Q. and Campbell, N. (2017) Doubly-Attentive Decoder for Multi-Modal Neural Machine Translation. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vancouver, 30 July-4 August 2017, 1913-1924. [Google Scholar] [CrossRef] 
[13] Caglayan, O., et al. (2020) What Do You Mean? Visually-Grounded Meaning Representations for Multimodal Machine Translation. arXiv:2001.08999.
[14] Specia, L., et al. (2020) A Survey of Multimodal Translation. arXiv:2005.12139.
[15] Specia, L., et al. (2020) Findings of the WMT 2020 Shared Task on Multimodal Machine Translation. arXiv:2010.07652.
[16] 黄鑫, 张家俊, 宗成庆. 基于跨模态实体信息融合的神经机器翻译方法[J]. 自动化学报, 2023, 49(1): 1-11.