Generative AI and Classical Chinese Moon Imagery in Translation
Journal of Computer Science and Artificial Intelligence · 28.09.2026 · 8 (3) · 30-34
DOI: 10.54097/advtk584 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science and Artificial Intelligence, online erschienen am 28.09.2026. Verfasst von Zixuan Xu. Die Arbeit nennt 11 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Generative artificial intelligence has created new possibilities for literary translation and for the international circulation of classical Chinese poetry. However, AI translation becomes problematic when poetic meaning depends on culturally dense imagery rather than direct explanation. This paper investigates how generative AI reconstructs the moon image in English translation, using Chat GPT and ERNIE Bot as two representative systems. A small experimental dataset of six classical moon-image cases is constructed, and four evaluation indicators are used: literal accuracy, cultural retention, aesthetic quality, and over-explanation risk. The results show that both systems perform strongly in literal accuracy but less consistently in cultural retention and aesthetic quality. They also tend to replace poetic ambiguity with explicit emotional explanation. The paper concludes that generative AI is useful for first-level comprehension and comparative translation practice, but human revision remains necessary for cultural judgment and aesthetic control.
Zitieren
APA
Xu, Z. (2026). Generative AI and Classical Chinese Moon Imagery in Translation. Journal of Computer Science and Artificial Intelligence, 8(3), 30-34. https://doi.org/10.54097/advtk584
Vancouver
Xu Z. Generative AI and Classical Chinese Moon Imagery in Translation. Journal of Computer Science and Artificial Intelligence. 2026;8(3):30-34. doi:10.54097/advtk584
BibTeX
@article{Xu2026,
author = {Xu, Zixuan},
title = {Generative AI and Classical Chinese Moon Imagery in Translation},
journal = {Journal of Computer Science and Artificial Intelligence},
year = {2026},
volume = {8},
number = {3},
pages = {30--34},
doi = {10.54097/advtk584}
}
EUVIMED