2026· SINTEZA· pp. 491-495· 0 citations· 13 references
TL;DR
The results indicate that these AI tools are highly effective at the lexical and syntactic levels, but also reveal limitations in the domain of phraseology, that is, in the translation of stylistically marked linguistic units.
Abstract
: This paper examines the adequacy of translating idiomatic language in Serbian media headlines into German and Russian, with particular emphasis on set expressions using artificial intelligence tools (ChatGPT, Gemini, and Google Translate). The corpus comprises twenty-one headlines collected from online news portals, with a focus on the potential and limitations of these three tools, as well as on the relationship between literalness and expressiveness in translation. The results indicate that these AI tools are highly effective at the lexical and syntactic levels, but also reveal limitations in the domain of phraseology, that is, in the translation of stylistically marked linguistic units.
: In the era of digital transformation and the rapid advancement of generative artificial intelligence, the translation of idiomatic expressions has become a crucial benchmark for evaluating the cognitive and linguistic capabilities of Large Language Models (LLMs). This paper presents a detailed analysis of research conducted on a corpus of ten English body part idioms taken from the Pioneer B2 textbook used at Singidunum University. The aim of the research was to compare translations generated by the ChatGPT model with solutions from official idiomatic dictionaries, utilising Pavol Kvetko's classification and Mona Baker’s equivalence strategies as the theoretical framework. The analysis encompasses idioms of varying degrees of transparency, ranging from completely opaque to semi-idioms. The study results indicate a 90% accuracy rate in conveying meaning, alongside an unexpectedly high 60% correspondence of keywords in both languages. The research confirms that ChatGPT successfully identifies functional equivalents in the Serbian language, often prioritising the naturalness of expressions over literal translation. This work contributes to the discussion on the role of AI tools as assistants in translation and education, emphasising that while AI shows exceptional dexterity in mapping conceptual fields, human oversight remains essential for the final validation of stylistic nuances. The findings have significant applications for international scientific research, particularly in the domain of applying information technology in foreign language teaching.
Jelena Janackovic, Jovana Bošković, Jelena Mladenović· SINTEZA· 0 citations
This article demonstrates the benefits and pitfalls of utilizing Natural Language Processing to structure a large corpus of newspaper adverts on fugitive enslaved people from the Atlantic World between 1766 and 1821. We evaluate a model for multilingual event extraction trained specifically for fugitive ads and jail lists in its capacity to extract correctly the attributes relevant for historical analysis. Finally, we discuss how the current model may be used to expand and qualify databases concerning enslaved fugitives in the eastern Caribbean.
Gunvor Simonsen, Natacha Klein Käfer, Heather Freund et al.· Archipelagos· 0 citations
The article examines linguistic features of Ukrainian socio-political news texts generated by large language models and methods for their automated identification. The aim is to substantiate lexical, stylistic, compositional and semantic markers that may indicate AI-generated text and to outline a computational-linguistic detection framework. The study proposes combining philological interpretation with NLP procedures: preprocessing, lexical diversity assessment, clustering, vectorization and transformer-based classification. It is argued that automated detection should not replace expert linguistic analysis but should serve as an auxiliary tool for evaluating the probable origin of a text in media linguistics, fact-checking, and educational practic
N. Babkova, D. Huliieva, Z. Kochuieva et al.· Bulletin of the National Tec...· 0 citations
Backround - The rapid advancement of Artificial Intelligence (AI) in translation studies has transformed how literary texts are processed, shifting from literal word-for-word transfer to more contextually nuanced approaches. Literary fables demand particular sensitivity to personification, onomatopoeia, and moral messaging.
Urgency of Research - Despite the proliferation of AI translation tools, previous studies have predominantly focused on macro-level quality evaluation (e.g., fluency and accuracy) rather than examining the micro-linguistic strategies AI employs. There remains a significant gap in understanding how different AI models identify and apply established translation techniques within Molina and Albir's comprehensive framework of 18 translation techniques.
Research Objectives - This study aims to evaluate and compare the performance of four AI tools—ChatGPT, Gemini, Claude, and DeepL—in identifying and applying translation techniques in the literary fable "The Clever Rabbit," specifically examining how each model utilizes Molina and Albir's 18 translation techniques to achieve dynamic equivalence.
Research Method - Adopting a qualitative descriptive approach, this study employs purposive sampling to select translation units demonstrating specific techniques. Data were collected through comparative textual analysis of one English source text and four Indonesian target texts, validated through theoretical triangulation and source triangulation.
Research Findings - The findings reveal a clear strategic polarization: generative AI models (ChatGPT, Gemini, Claude) demonstrate dominance in complex transformation techniques such as Modulation (20-23%), Equivalence (12-13%), and Explicitation, reflecting deeper contextual understanding. In contrast, DeepL shows extreme reliance on Literal Translation (>65%) with minimal cultural or stylistic adaptation. ChatGPT excels in local adaptation through generalization and particularization; Gemini stands out in narrative vitality through expressive lexical variation; and Claude offers structural efficiency through precise grammatical reduction.
Research Conclusion & Novelty - 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. The novelty lies in its micro-linguistic analysis using Molina and Albir's comprehensive taxonomy across four distinct AI platforms, providing unprecedented insight into the "black box" of AI translation strategies. The findings offer practical guidance for educators, researchers, and translators in selecting appropriate AI tools, emphasizing that critical human post-editing remains indispensable for achieving true literary equivalence.
We offer a lexical analysis of the various words, phrases, and acronyms used in French to refer to components and aspects of AI (artificial intelligence) use. Most of them are Anglicisms, whose use has not really been stopped by the various ministerial terminology commissions, which are supposed to defend French as the national language. We will also analyze several discursive contexts, taken from the French press, in which these lexemes are used, in order to highlight their integration into the language. Cases of lexical derivation will also be studied, with the aim of highlighting the same process of lexico-semantic integration. We will analyze words such as chatbot, chatter, and overfitting; phrases such as feature engineering, AI governance, algorithmic audit, and digital sovereignty; and acronyms such as AI and GDPR. This brand-new, rich, and complex lexicon marks a new period of borrowing from English into French, with the massive return of Anglicisms into contemporary French.
Felicia Dumas· Dynamics of the Romance and...· 0 citations
This paper presents a corpus-based analysis of passive constructions and their translation from English and German
into Catalan. The analysis is grounded in a systematic categorization of the construction families in the three languages and
their translation correspondences, focusing on both form and meaning (content and construal) and accounting for shifts in meaning
between the source and target texts. The findings are relevant from both translation-oriented and contrastive perspectives. First,
it is shown how passive constructions in the three languages are interconnected through translation. Second, these connections
offer insights into the category of passive constructions and their variation across languages.
Ulrike Oster, I. N. Ferrando· Languages in Contrast: Inter...· 0 citations