Digital translation as a factor of variability in single-text translations: A case study of Siberian mining poetry

Techniques for translating a documentary into Russian and stylistic errors made during translation: the case of the “24 Snows” film

This article presents a linguistic analysis of the translation techniques used to translate a documentary film from Yakut into Russian, and classifies the stylistic errors made during the translation process. The documentary film “24 Snows” (2015, directed by M. B. Barynin) serves as the research material. The aim of the study was to identify, systematize, and analyze key translation strategies and typical stylistic errors that arise when translating the documentary from Yakut into Russian (using the film “24 Snows”). The theoretical basis of the study was formed by fundamental works on translation studies by N.K. Garbovsky, Y. I. Recker, V.S. Modestov, and other scholars, who laid the foundations for the classification of translation techniques and the analysis of translation errors. The primary method of analysis was comparative; empirical research methods such as comparison, classification, and generalization were used as auxiliary ones. The analysis utilized contextual analysis, descriptive-analytical methods, and semantic analysis techniques. A structured interview with the film’s director was used to reconstruct the context of the translation work. The study identified and systematized the following techniques for translating the original documentary text from Yakut into Russian: transcription, transliteration, adaptation, calque, and generalization. Furthermore, typical translator errors were discovered: omitted words, distorted meaning, as well as grammatical, syntactic, and logical errors.

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

: 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.

Controlling Translation Purpose through Prompt Engineering: A Skopos-Based Study of AI Poetry Translation

The study finds that each prompt orientation produces distinct and observable shifts in diction, imagery construction and formal expression, and re-conceptualizes prompts not only as technical input instructions, but as purposive regulators of translation, offering a translation-theoretic framework for analysing LLM behaviour and practical guidance for designing Skopos-informed prompts for AI-assisted literary translation.

Natural Language Processing, Translation, and Iraqi Poetry: Toward a Culturally Aware Digital Framework

The paper argues that NLP should operate as an interpretive assistant rather than an autonomous literary translator in translating Iraqi poetry into English, and proposes a culturally aware, human-in-the-loop framework for supporting literary translation.

A STUDY OF TRANSLATION TRANSFORMATIONS AND FUNCTIONAL EQUIVALENCE IN FANTASY LITERATURE

The translation of fantasy literature presents a number of linguistic and cultural challenges due to the representation of culture-specific elements, author-created names, mythological references, and stylistically colored language units. The object of this paper is a classic work of fantasy fiction, J. R. R. Tolkien’s The Lord of the Rings provides extensive material for investigating translation strategies and transformations. The study focuses on that the translator’s style to use lexical and grammatical transformations in translation of The Lord of the Rings considering functional equivalence. For analyzing corresponding elements of the source and target texts, comparative, descriptive, and contextual methods are applied. Transcription, transliteration, calque, modulation, concretization, generalization, transposition, and grammatical substitution are among the most frequently employed transformations. Through these transformations, the translator preserves semantic, stylistic, and cultural aspects of the original text, ensuring a high degree of functional equivalence. The study confirms that translation transformations function as essential tools for reproducing the communicative and aesthetic impact of fantasy narratives in the target language.

The Human Translator’s (In)Visibility in Times of AI: An Self-Applied Experiment in Literary Translation