To Vu Thanh * and Tran Duc Thang

* Corresponding author: (tovuthanh.sfl@tnu.edu.vn)

Abstract

The advancement of Neural Machine Translation (NMT) and Large Language Models (LLMs) is placing fundamental reform demands on Vietnamese–Chinese translation training at the university level. This paper addresses the question of how Vietnamese–Chinese translation pedagogy must change in the AI era and which integration model best suits the specificities of this language pair. The study employs document analysis and synthesis, theoretical systematization, and pedagogical reasoning grounded in constructivist theory, the TPACK and SAMR frameworks, and hybrid translator competence theory. The findings identify six components of hybrid translator competence and propose the VCT-AI model (Vietnamese–Chinese Translation – AI Integration Model), structured around four pillars: consolidating manual translation foundations; developing domain-specific prompt engineering skills; practicing pedagogically guided post-editing; and assessing ethical conduct alongside hybrid translator competence. The model is operationalized through a five-step instructional process and a four-dimensional assessment rubric with weighted criteria. This study contributes a specialized pedagogical framework for the Vietnamese–Chinese language pair in the AI era, offering practical implications for translation course design at the undergraduate level and laying the groundwork for future classroom experiments.
Keywords: Translation pedagogy, Vietnamese–Chinese translation, Artificial intelligence, Post-editing, Hybrid translator competence

Tóm tắt

Sự phát triển của dịch máy nơ-ron (NMT) và các mô hình ngôn ngữ lớn (LLMs) đang đặt ra yêu cầu đổi mới căn bản đối với dạy học dịch thuật Việt–Trung ở bậc đại học. Bài báo đặt câu hỏi: dạy học dịch thuật Việt–Trung cần thay đổi như thế nào để đáp ứng bối cảnh AI, và mô hình tích hợp nào phù hợp với đặc thù cặp ngôn ngữ này? Nghiên cứu sử dụng phương pháp phân tích–tổng hợp tài liệu, hệ thống hóa lý thuyết và suy luận dạy học dựa trên các khung lý thuyết kiến tạo, TPACK, SAMR và lý thuyết năng lực dịch thuật lai. Kết quả nghiên cứu xác định sáu thành tố của năng lực dịch thuật lai và đề xuất mô hình VCT-AI (Vietnamese–Chinese Translation – AI Integration Model) gồm bốn trụ cột: củng cố nền tảng dịch thuật thủ công; phát triển kỹ năng prompt engineering chuyên ngành Việt–Trung; thực hành hậu biên tập có hướng dẫn; và đánh giá đạo đức cùng năng lực dịch thuật lai. Mô hình được cụ thể hóa qua quy trình dạy học năm bước và hệ tiêu chí đánh giá bốn chiều có phân bổ trọng số. Nghiên cứu đóng góp một khung dạy học dịch thuật chuyên biệt cho cặp Việt–Trung trong kỷ nguyên AI, có ý nghĩa ứng dụng thiết thực cho thiết kế học phần dịch ở bậc đại học, đồng thời đặt nền móng cho các thực nghiệm lớp học tiếp theo.
Từ khóa: Dạy học dịch thuật, Dịch thuật Việt–Trung, Trí tuệ nhân tạo, Hậu biên tập, Năng lực dịch thuật lai

Article Details

References

Anthropic. (2023). Claude 2 model card. https://www.anthropic.com/claude-2-model-card

Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. In Proceedings of the International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1409.0473

Bowker, L. (2020). Machine translation literacy instruction for international business students and business English instructors. Journal of Business & Finance Librarianship, 25(1–2), 25–43. https://doi.org/10.1080/08963568.2020.1794739

Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., ... Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.

Do, T. P. (2018). A survey on errors made by students of School of Foreign Languages, Thai Nguyen University when translating Sino-Vietnamese words directly into Chinese and solutions. Journal of Inquiry into Languages and Cultures, 2(1). https://vjol.info.vn/index.php/nnvh/article/view/49682

Doherty, S., & Kenny, D. (2014). The design and evaluation of a statistical machine translation syllabus for translation students. The Interpreter and Translator Trainer, 8(2), 295–315. https://doi.org/10.1080/1750399X.2014.937571

González Davies, M. (2004). Multiple voices in the translation classroom: Activities, tasks and projects. John Benjamins.

Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., & Liu, T. (2025). A survey on hallucination in large language models. ACM Computing Surveys. https://doi.org/10.1145/3703155

International Organization for Standardization. (2017). ISO 18587:2017 Translation services—Post-editing of machine translation output—Requirements. https://www.iso.org/standard/62970.html

Kiraly, D. (2000). A social constructivist approach to translator education: Empowerment from theory to practice. St. Jerome Publishing.

Lommel, A. R., Burchardt, A., & Uszkoreit, H. (2013). Multidimensional quality metrics: A flexible system for assessing translation quality. In Proceedings of Translating and the Computer 35. https://aclanthology.org/2013.tc-1.6/

Mishra, P., & Koehler, M. J. (2006). Technological pedagogical content knowledge: A framework for teacher knowledge. Teachers College Record, 108(6), 1017–1054. https://doi.org/10.1111/j.1467-9620.2006.00684.x

Moorkens, J. (2018). What to expect from neural machine translation: A practical in-class translation evaluation exercise. The Interpreter and Translator Trainer, 12(4), 375–387. https://doi.org/10.1080/1750399X.2018.1501639

Nguyen, T. M., & Nguyen, T. H. N. (2016). Translating Chinese–Vietnamese political texts: Some issues to note. VNU Journal of Foreign Studies, 32(1), 66–68. https://js.vnu.edu.vn/FS/article/view/289/275

Nguyen, T. N. C., & Nguyen, P. T. (2021). A comparative analysis of pragmatic functions of personal pronouns in Vietnamese and Chinese. Journal of Science and Technology – Duy Tan University, 5(48), 144–154.

O'Brien, S. (2011). Towards predicting post-editing productivity. Machine Translation, 25(3), 197–215. https://doi.org/10.1007/s10590-011-9096-7

PACTE Group. (2003). Building a translation competence model. In F. Alves (Ed.), Triangulating translation: Perspectives in process-oriented research (pp. 43–66). John Benjamins.

Puentedura, R. R. (2006). Transformation, technology, and education. Hippasus. https://hippasus.com/resources/tte/

Pym, A. (2013). Translation skill-sets in a machine-translation age. Meta, 58(3), 487–503. https://doi.org/10.7202/1025047ar

Pym, A. (2014). Exploring translation theories (2nd ed.). Routledge.

Tran, B. L. (2015). A study of Chinese–Vietnamese translation: Based on Chinese–Vietnamese business text translations (Doctoral dissertation, Vietnam National University, Hanoi).

Tran, Q. H. (2024). Semantic shifts of Sino-Vietnamese words and errors in Vietnamese–Chinese and Chinese–Vietnamese translation. Journal of Science and Technology – The University of Danang, 22(8), 65–68. https://jst-ud.vn/jst-ud/article/view/9282

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008.

Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes (M. Cole, V. John-Steiner, S. Scribner, & E. Souberman, Eds.). Harvard University Press.

Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., Klingner, J., Shah, A., Johnson, M., Liu, X., Kaiser, Ł., Gouws, S., Kato, Y., Kudo, T., Kazawa, H., ... Dean, J. (2016). Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv. https://arxiv.org/abs/1609.08144