A Study on the Cross-linguistic Reconstruction of Imagery in Chinese Classical Poetry by Artificial Intelligence: A Case Study of the "Pine" Imagery
Abstract
In recent years, the rapid development of generative artificial intelligence (Generative AI) has brought new momentum to literary creation and cross-cultural communication. However, its widespread use in language generation and text reconstruction has revealed limitations in conveying Chinese traditional culture across languages—such as misinterpreting cultural context, lacking aesthetic depth, and oversimplifying poetic imagery. Understanding how AI can accurately reconstruct classical Chinese poetic imagery across languages is therefore of both theoretical significance and practical value. This paper examines the "pine" imagery in classical Chinese poetry to assess Generative AI’s ability in linguistic transformation and cultural representation in translation. Through case analysis and by drawing on literary translation theory, this study evaluates AI-generated translations in detail. Findings show that AI excels in semantic accuracy, fluency, and translation efficiency, but falls short in capturing cultural nuance, poetic rhythm, and contextual appropriateness. The study concludes that AI is best used as a supportive tool rather than a replacement for human translators in deep interpretation and creative expression. Future research could analyze more types of imagery, develop a broader framework for cross-linguistic reconstruction, and explore human-AI collaboration models to better integrate technology and culture.
References
- Guzman, A. L., & Lewis, S. C. (2024). What generative AI means for the media industries, and why it matters to study the collective consequences for advertising, journalism, and public relations. Emerging Media, 2(3), 347–355.
- Ooi, K. B., Tan, G. W. H., Al-Emran, M., et al. (2025). The potential of generative artificial intelligence across disciplines: Perspectives and future directions. Journal of Computer Information Systems, 65(1), 76–107.
- Chakraborty, U., Roy, S., & Kumar, S. (2023). Rise of Generative AI and ChatGPT: Understand how Generative AI and ChatGPT are transforming and reshaping the business world. BPB Publications.
- Deng, Z., Yang, H., & Wang, J. (2024). Can ai write classical chinese poetry like humans? an empirical study inspired by turing test. arXiv preprint arXiv: 2401.04952.
- Wang, S. B., Wang, S. I. C., & Liu, E. Z. F. (2025). The Impact of Generative AI on Chinese Poetry Instruction: Enhancing Students' Learning Interest, Collaboration, and Writing Ability. International Journal of Online Pedagogy and Course Design (IJOPCD), 15(1), 1-21.
- Liang, Q., Ma, X., Hopkins, T., & Wang, Y. LivePoem: Improving the Learning Experience of Classical Chinese Poetry with AI-Generated Musical Storyboards.
- Chen, H. C., & Chen, Z. (2023). Using ChatGPT and Midjourney to generate chinese landscape painting of tang poem 'The difficult road to Shu’. International Journal of Social Sciences, 3(2), 1-10.
- Hu, K., & Li, X. (2023). The creativity and limitations of AI neural machine translation: A corpus-based study of DeepL’s English-to-Chinese translation of Shakespeare’s plays. Babel, 69(4), 546–563.
- Nida, E. A. (2020). Toward a Science of Translating (Revised Edition)
- Zhang, Y., & Li, J. (2024). Cross-linguistic Reconstruction of Poetic Imagery by Generative AI: A Case Study of Chinese Classical Poetry. Journal of Pragmatics, 201, 45–62.
- Li, Q. (2024). Bridging Languages: The Potential and Limitations of AI in Literary Translation—A Case Study of the English Translation of A Pair of Peacocks Southeast Fly. Advances in Humanities Research, 8, 1-7.