Nataliia Yu. Ishchuk
PhD in Education, Associate Professor,
Associate Professor at the Department of Foreign Languages for Specific Purposes
Vasyl’ Stus Donetsk National University,
Vinnytsia, Ukraine
e-mail: ischuk.n@donnu.edu.ua
ORCID ID http://orcid.org/0000-0002-4726-9432
DOI: https://doi.org/10.24195/2616-5317-2025-40.8
SUMMARY
In modern linguistics, machine translation (MT) occupies an important and increasingly prominent place, as the development of computer technology and artificial intelligence has significantly changed approaches to processing linguistic information. Due to modern MT systems, translating texts between languages has become more accurate, stylistically balanced, and contextually adequate, which was previously unattainable for traditional rules and dictionary methods. The study aims to identify the strengths and weaknesses of modern machine translation from a philological point of view, in particular in the aspects of preserving meaning, cultural context, stylistic accuracy, and to determine the role of the translator in the technological era of linguistic communication. Machine translation is the process of automatically converting texts or speech fragments from one language to another using computer programs or systems that use natural language processing algorithms. The study highlights philological challenges in machine translation: ensuring the accuracy and semantic adequacy of translation, the problem of context and ambiguity, as well as stylistics, genre features, and emotional coloring. Cultural aspects of MT remain one of the most difficult challenges for modern language technologies, because the transmission of realities, idioms, and national-cultural elements requires not only linguistic accuracy but also deep cultural understanding. Typical mistakes associated with incorrect translation of culturally specific terms and expressions in MT are lexical ambiguity, incorrect transmission of grammatical structures, in particular syntactic relations between words; loss or addition of information, stylistic flatness of translations. However, MT also has positive aspects – the speed of processing requests, the availability of a wide range of languages, and cost-effectiveness. Thanks to the use of MT tools, translators can generate the text faster and transform it. Philological expertise should become a key element in ensuring the quality of translation. The prospect of further research is to study new tools for post-editing machine translation.
Key words: machine translation, accuracy, context, culture, philology, TranslateGoogle, DeepL, ChatGPT.
REFERENCES
Brai A. Yu. (2024) Adekvatnist mashynnoho perekladu usnykh ta pysmovykh anhlomovnykh tekstiv [Adequacy of machine translation of oral and written English texts]. Kyiv : Kyivskyi politekhnichnyi instytut imeni Ihoria Sikorskoho [in Ukrainian].
Danylov H., Balakirieva V., Vasylenko K. (2021). Mashynnyi pereklad, systemy mashynnoho perekladu ta yikh spetsyfika [Machine translation, machine translation systems and their specifics]. Naukovyi visnyk PNPU im. K. D. Ushynskoho [Scientific Research Issues of South Ukrainian National Pedagogical University Named after K. D. Ushynsky: Linguistic Sciences], Vol. 33, pp. 293–310 [in Ukrainian].
Devlin J., Chang M., Lee K., Toutanova K. (2023). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Computer Science. URL: https://arxiv.org/abs/1810.04805.
Diachuk N. (2023). Do pytan adekvatnosti perekladu tekhnichnykhinstruktsii [On the issues of the adequacy of the translation of technical instructions]. Suchasni doslidzhennia z inozemnoi filolohii [Modern Studies on Foreign Philology], № 23, pp. 34–42 [in Ukrainian].
Jiao W., Wang W., Huang J, Wang X., Shi S., Tu Z. (2023). Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine. Computer Science. URL: https://arxiv.org/abs/2301.08745.
Junczys-Dowmunt M., Grundkiewicz R., Dwojak T., Hoang H., Heafield K., Neckermann, T., Seide F., Germann U., Aji A. F., Bogoychev N., Martins A. F. T., Birch A. (2018). Marian: Fast Neural Machine Translation in C++. Computer Science. URL: https://arxiv.org/abs/1804.00344.
Khomenko V., Kuhai K. (2024). Language peculiarities and cultural backgrounds: machine translation. Innovatsiini tendentsii pidhotovky fakhivtsiv v umovakh polikulturnoho ta multylinhvalnoho hlobalizovanoho svitu, pp. 352–354. URL: https://er.knutd.edu.ua/handle/123456789/27983.
Klein G., Kim Y., Deng Y., Crego J., Senellart J., Rush A. M. (2017). OpenNMT: Open-source Toolkit for Neural Machine Translation. Computer Science. URL: https://arxiv.org/abs/1709.03815.
Liubymova S. A. (2024). Problemy avtomatyzovanoho perekladu (konspekt lektsii) [Problems of automated translation (lecture notes)]. Odesa [in Ukrainian].
Moisieieva N., Dzykovych O., Shtanko A. (2023). Mashynnyi pereklad: porivniannia rezultativ ta analiz pomylok DeepL ta Google Translate [Machine translation: comparison of results and error analysis of DeepL and Google Translate]. Advanced Linguistics, № 11, pp. 78–82 [in Ukrainian].
Tupytsia O. Yu. (2024). Linhvokulturni aspekty perekladu bezekvivalentnoi leksyky [Linguistic and cultural aspects of the translation of non- equivalent vocabulary]. Naukovyi visnyk Mizhnarodnoho humanitarnoho universytetu [Scientific Bulletin of International Humanitarian University], Vol. 69 (2), pp. 38–41 [in Ukrainian].
Vanmassenhove E., Shterionov D., Way A. (2019). Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation. Computer Science. URL: https://arxiv.org/abs/1906.12068.
Vaswani A., Bengio S., Brevdo E., Chollet F., Gomez A. N., Gouws S., Jones L., Kaiser Ł., Kalchbrenner N., Parmar N., Sepassi R., Shazeer N., Uszkoreit J. (2018) Tensor2Tensor for Neural Machine Translation. Computer Science. URL: https://arxiv.org/abs/1803.07416.
Vasylenko N. V. (2024) Kros-kulturnyi aspekt perekladu dokumentiv mizhnarodnykh proiektiv: analiz vplyvu kulturnykh vidminnostei na yakist perekladu ta rekomendatsii dlia zabezpechennia tochnosti i kontekstualnoi adaptatsii [Cross- cultural aspect of translation of documents of international projects: analysis of the influence of cultural differences on the quality of translation and recommendations for ensuring accuracy and contextual adaptation]. Scientific Practice: Modern and Classical Research Methods, pp. 190–193 [in Ukrainian].
Voita E., Sennrich R., Titov I. (2018). When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion. Computer Science. URL: https://arxiv.org/abs/1905.05979.
Wheal E. (2025). Future of machine translation in 2025 and beyond. URL: https://www.rws.com/blog/future-of-machine-translation/.