UDC

004.827: 81’255.2

DOI

10.37482/2687-1505-V487

Authors

Anna A. Ilchuk¹ - Senior Lecturer, Department of Foreign Languages, Kaliningrad State Technical University (address: Sovetskiy prosp. 1, Kaliningrad, 236022, Russia).

e-mail: anikakh83@gmail.com, ORCID: https://orcid.org/0009-0000-9309-6125

Elena V. Kharitonova^2* - Cand. Sci. (Philol.), Assoc. Prof., Assoc. Prof. at the Institute of Education and the Humanities, Immanuel Kant Baltic Federal University (address: ul. A. Nevskogo 14, Kaliningrad, 236041, Russia).

e-mail: eharitonova@yandex.ru*, ORCID: https://orcid.org/0000-0002-2607-7028

Abstract

Over the past few decades, the field of translation studies has undergone significant technological evolution, progressing from computer-assisted translation (CAT) tools to neural machine translation (NMT) systems and, most recently, to large language model (LLM)-based chatbots. The latter, while not originally designed for translation tasks, demonstrate high efficacy in natural language processing and function as cognitive communication systems (dialogic artificial intelligence (AI) agents). When utilized by translators, such tools can significantly enhance productivity and output quality due to prompt engineering techniques. This study examines the ability of AI systems to process and render in translation the semantics of blurred boundaries, i.e. instances where literary authors create situations of interpretative choice that invite readers’ active meaning construction. The paper evaluates how current AI solutions can: 1) detect intentionally vague elements in a literary text and 2) render them across languages while preserving the author’s intent. Data collection was carried out using comparative analysis of translation results performed by 15 NMT systems (DeepL Translator, Google Translate, Yandex Translate, SYSTRAN, HIX, etc.) and 4 AI chatbots (ChatGPT-4o, Google Gemini, Microsoft Copilot, and Sider). The findings demonstrate that while conventional NMT systems struggle with conveying gender neutrality – a manifestation of semantic vagueness – LLM-based chatbots excel through their generative architecture. Their interactive cognition enables contextual adaptation and alternative phrasing, effectively bridging the “gender vagueness gap” in translation.

Keywords

vagueness, gender, non-isomorphism in language, literary translation, neural machine translation, artificial intelligence (AI), prompt engineering

References

1. Russell B. Vagueness. Keefe R., Smith P. (eds.). Vagueness: A Reader. Cambridge, 1997, pp. 61–68.
2. Keefe R., Smith P. (eds.). Vagueness: A Reader. Cambridge, 1997. 352 p.
3. Ronzitti G. (ed.). Vagueness: A Guide. London, 2011. 200 p. https://doi.org/10.1007/978-94-007-0375-9
4. Sagid S. Vagueness as Arbitrariness: Outline of a Theory of Vagueness. Cham, 2021. 206 p. https://doi.org/10.1007/978-3-030-66781-8
5. Cunillera Domenech M. La unidad francesa truc o la vaguedad semántica desde una perspectiva argumentativa y traductológica. Meta, 2014, vol. 59, no. 1, pp. 176–197. https://doi.org/10.7202/1026476ar
6. Moreno G.A. Fictive Orality and Semantic Vagueness from the Translational Perspective: A Case Study of the Word ‘Stuff’ and Its Translations into Spanish. Parallèles, 2014, no. 26, pp. 10–25.
7. Arntz R., Sandrini P. Präzision versus Vagheit: Das Dilemma der Rechtssprache im Lichte von Rechtsvergleich und Sprachvergleich. Antia B.E. (ed.). Indeterminacy in Terminology and LSP: Studies in Honour of Heribert Picht. Amsterdam, 2007, pp. 135–153. https://doi.org/10.1075/tlrp.8.14arn
8. Wiesmann E. Zur Vagheit in Vertragstexten: Rechtliche Funktionen und übersetzungsrelevante Dimensionen vager Wörter und Wortverbindungen. Gotti M., Šarčević S. (eds.). Insights into Specialized Translation. Bern, 2006, pp. 289–311.
9. Zolyan S.T. On the Theory of Traductological Relativity. Voprosy filosofii, 2019, vol. 9, pp. 75–86 (in Russ.). https://doi.org/10.31857/S004287440006320-7
10. Boyarskaya E. Ambiguity Matters in Linguistics and Translation. Slovo.ru: Balt. Accent, 2019, vol. 10, no. 3, pp. 81–93.
11. Boyko L.B., Kharitonova E.V. V poiskakh utrachennogo i obretennogo: zametki o perevode [In Search of the Lost and Found: Notes on Translation]. Moscow, 2024. 255 p.
12. Merzlaya A.V. Neural Machine Translation and Conveying Cold Perception (Based on Finnish-Russian Translations of Meteorological Texts). Vestnik Severnogo (Arkticheskogo) federal’nogo universiteta. Ser.: Gumanitarnye i sotsial’nye nauki, 2025, vol. 25, no. 2, pp. 73–82. https://doi.org/10.37482/2687-1505-V421
13. Miftakhova R.G., Morozkina E.A. Mashinnyy perevod. Neyroperevod [Machine Translation. Neural Translation]. Vestnik Bashkirskogo universiteta, 2019, vol. 24, no. 2, pp. 497–502.
14. Kolin K.K., Khoroshilov Al-dr A., Nikitin Yu.V., Pshenichny S.I., Khoroshilov Al-ei A. Artificial Intelligence in Machine Translation Technologies. Soc. Nov. Soc. Sci., 2021, no. 2, pp. 64–80 (in Russ.). https://doi.org/10.31249/snsn/2021.02.05
15. Aghai M. ChatGPT vs. Google Translate: Comparative Analysis of Translation Quality. Iran. J. Transl. Stud., 2024, vol. 22, no. 85, pp. 85–100. Available at: https://journal.translationstudies.ir/ts/article/view/1156 (accessed: 10 June 2025).
16. Hendy A., Abdelrehim M., Sharaf A., Raunak V., Gabr M., Matsushita H., Kim Y.J., Afify M., Awadalla H.H. How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation. ArXiv. Preprint, 2023. https://doi.org/10.48550/arXiv.2302.09210
17. Jiang Z., Zhang Z., Lv X., Lei L. Convergences and Divergences Between Automatic Assessment and Human Evaluation: Insights from Comparing ChatGPT-Generated Translation and Neural Machine Translation. ArXiv. Preprint, 2024. https://doi.org/10.13140/RG.2.2.15933.47842
18. Jiao W., Wang W., Huang J.-T., Wang X., Shi S., Tu Z. Is ChatGPT a Good Translator? Yes. With GPT-4 as the Engine. ArXiv. Preprint, 2023. https://doi.org/10.48550/arXiv.2301.08745
19. Moneus A., Sahari Y. Artificial Intelligence and Human Translation: A Contrastive Study Based on Legal Texts // Heliyon. 2024. Vol. 10, No 2. Art. No e28106. https://doi.org/10.1016/j.heliyon.2024.e28106