Answers are grounded in this paper and cite their sources.
Comparative study reveals superior pragmatic naturalness and idiomaticity in human versus Gemini translations of Albanian literary idioms, highlighting AI limitations in cultural nuances.
The translation of idiomatic expressions remains one of the most challenging aspects of literary translation, particularly in the context of the rapid development of Large Language Models, such as Gemini. This study scrutinizes how Albanian idiomatic expressions from Kadare’s novel “Gjenerali i Ushtrisë së Vdekur” are rendered in English by the professional human translator Derek Coltman and generated by Gemini. Guided by Baker’s taxonomy of translation strategies, it aims to identify and compare their performance in terms of translation strategies, semantic accuracy, pragmatic naturalness, and idiomaticity. Employing a qualitative content analysis method combined with the quantification of the data analysis, thirty identified idiomatic expressions were collected from Albanian and then analyzed across both translations. Findings show that while semantic accuracy is achieved by both, it is associated with different translation strategies: Coltman employs equivalence and paraphrase, whereas Gemini relies on literal translation. The divergence engenders consistent differences in pragmatic naturalness and idiomaticity, which are more consistently maintained in the human translation. These findings highlight the actual shortcomings of artificial intelligence-based chatbots, Gemini in particular, in literary translation and reinforce the significance of human expertise in handling culturally specific idiomatic expressions.
No takes yet. Share an insight, caveat, or question.
SHAQIRI et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: