The Translation of Body Part Idioms Using Chatgpt: a Comparative Analysis with Official Dictionaries

MEANING OR MIMICRY? A COMPARATIVE STUDY OF HUMAN AND GEMINI TRANSLATION OF ALBANIAN IDIOMATIC EXPRESSIONS INTO ENGLISH IN KADARE’S THE GENERAL OF THE DEAD ARMY

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. 

Translation Strategies and Difficulties in Translating English Idiomatic Expressions

Translation plays an important role in transferring meaning across languages, particularly when translating idiomatic expressions whose meanings cannot be interpreted literally. This study aimed to identify the translation strategies employed by sixth-semester students in translating English idiomatic expressions into Indonesian and to investigate the translation difficulties they encountered. The study employed a descriptive quantitative design involving 24 sixth-semester students of the English Department at UIN Fatmawati Sukarno Bengkulu. The research instrument was a translation test consisting of 15 idiomatic expressions selected from Barack Obama's speech Ignorance is Not a Virtue. The students' translations were analyzed using Baker's (1992) translation strategies, while translation difficulties were classified based on Baker (1992) and Larson (1998). The findings revealed that Translation by Paraphrase was the dominant strategy, accounting for 345 translations (95.83%), followed by Using an Idiom of Similar Meaning but Dissimilar Form with 15 translations (4.17%). No data were categorized as Using an Idiom of Similar Meaning and Form or Translation by Omission. Regarding translation difficulties, Contextual Difficulty was the most dominant category with 161 cases (73.85%), followed by Linguistic Difficulty with 33 cases (15.14%) and Cultural Difficulty with 24 cases (11.01%). The findings indicate that students experienced greater difficulty in interpreting the intended meanings of idiomatic expressions within their communicative contexts than in understanding linguistic or cultural aspects. Furthermore, 218 translations (60.55%) were classified as less accurate and inaccurate, indicating that contextual interpretation substantially influenced translation quality. The study suggests that translation instruction should emphasize contextual interpretation alongside linguistic and cultural competence to improve students' ability to translate idiomatic expressions accurately

JOURNAL OF COMMUNICATION, LANGUAGE AND CULTURE

A Comparative Assessment of ChatGPT, DeepSeek and Human Translations of Cultural References in the Moroccan Novel For Bread Alone

The translatability of cultural references (CRs) has been a major problem for human translators, let alone artificial intelligence (AI) tools. This study evaluates the effectiveness of AI vis-à-vis human translations of CRs. The dataset was mined from For Bread Alone, a unique Arabic literary autobiographical masterpiece by the Moroccan author Mohamed Choukri (2000) and translated into English (1983) by Paul Bowles. The AI English translations were generated by Chat GPT (GPT) and DeepSeek (DS), Western vs Eastern AI systems. 300 English renderings of 100 CRs were analyzed qualitatively and quantitatively. The AI translations were assessed using BLEU, METEOR and chrF metrics vis-à-vis the human translation (HT), then both AI translations and HT were evaluated using Pedersen’s (2011) taxonomy of strategies (with two added strategies specifically used for this study). BLEU produced the highest results, while METEOR and chrF scores were significantly lower, and GPT scores were higher than DS in comparison to HT. The analysis of the strategies indicates that both GPT and DS relied heavily on source language oriented strategies, while HT made more use of target language oriented ones. The findings highlight the tensions between linguistic precision and cultural adequacy in both human and AI translations.

‘Actually’ in translation: The case of English and Slovak

This pilot study examines how the English adverb actually is rendered in Slovak translation, drawing on a corpus of literary texts and their translations. As a multifunctional item, actually performs a range of syntactic and pragmatic functions in context, most notably those of emphasizer and disjunct. The analysis draws on three Slovak translations of works by the same English-speaking author. Although each translator worked on a different set of books, the corpus still makes it possible to compare translation strategies within a relatively consistent authorial style and to observe how individual translators deal with the same multifunctional source item. The study combines qualitative functional analysis with quantitative observations in order to identify recurrent Slovak renderings of actually, including lexical substitution, structural reformulation, attenuation, and omission. The findings suggest that translation difficulty arises not from the lack of Slovak expressive resources, but from differences between English and Slovak in the grammatical encoding of discourse-related meaning. In particular, functions expressed in English through sentence adverbials do not always correspond to a single formal category in Slovak, which increases the likelihood of functional shift or translation loss. The study contributes to translation studies and contrastive linguistics by showing how the pragmatic contribution of a frequent multifunctional item may be preserved, reinterpreted, weakened, or omitted in translation, and how these outcomes vary across translators.

Evaluating Artificial Intelligence Tools In Identifying Translation Techniques In Literary Texts

This study concludes that while all AI tools can transfer denotative meaning, generative models (LLMs) are superior in applying high-level translation techniques necessary for maintaining emotional nuance, discourse cohesion, and literary appeal.