Abstract—At the background of the rapid development of Artificial Intelligence technology, this paper takes the two English versions of the translation of The Garlic Ballads as the research object, and under the guidance of cognitive translation theory, explores the differences between human and machine translation in metaphorical expression. Through comparative analysis of the two English versions of the translation, it is found that machine translation excels in efficiency and uniformity of terminology, but has limitations in decoding the cultural connotations of metaphors; human translation, on the other hand, can ensure the critical and aesthetic value of metaphors based on in-depth understanding and creative transformation. This study points out that Artificial Intelligence technology can improve efficiency in the initial draft generation stage, while human translation focuses more on the expression of deep semantics and literary artistry, forming a collaborative model of “AI for efficiency and human for quality”. This paper proposes human-machine collaboration strategy and the follow-up development directions of related research, so as to help the translation field achieve balanced development of efficiency and quality in the wave of technological progress.
Keywords—cognitive translation theory, human-machine translation, metaphorical expression translation, The Garlic Ballads, Howard Goldblatt, DeepSeek
Cite: Le Ma, "Differences Between Human-Machine Translation in Metaphorical Expressions within the Framework of Cognitive Translation Theory——Taking The Garlic Ballads as a Case Study,"
International Journal of Languages, Literature and Linguistics, vol. 12, no. 3, pp. 197-201, 2026.
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).