Neural Machine Translation in the Military Sphere: Evaluation of Efficiency, Limitations, and Prospects of Use
https://doi.org/10.18384/2949-5075-2025-S1-29-42
Abstract
Aim. To evaluate the effectiveness of neural machine translation (NMT) for military texts of various styles in English and Vietnamese, identifying its advantages and limitations.
Methodology. An experiment was conducted with NMT systems (Google Translate, ChatGPT, Gemini) and a comparative analysis of their translations against those of professional translators. Quality was assessed based on content accuracy, terminological precision, stylistic consistency, and error rates.
Results. The study shows that NMT ensures high speed and acceptable quality for scientific and official texts but encounters difficulties with literary and conversational texts requiring stylistic expressiveness.
Research implications. This research clarifies the applicability of NMT, provides recommendations for its use in military translation, and highlights the need for domestic offline solutions to enhance translation quality and ensure data security.
About the Author
V. A. Serbin
Moscow State Linguistic University
Russian Federation
Russian Federation
Vladimir A. Serbin – Cand. Sci. (Philology), Assoc. Prof., Military Training Center
Moscow
References
1. Rarenko, M. B. (2021). Machine translation as a challehge. In: Lomonosov Translation Studies Jounal, 2, 117–126 (in Russ.).
2. Marchuk, Yu. N. (2007). Computer linguistics. Moscow: Vostok – Zapad publ. (in Russ.)
3. Kirkedal, A. (2012). Tree-based Hybrid Machine Translation. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (Avignon, France, April 23–27, 2012). Stroudsburg, PA: Association for Computational Linguistics, pp. 77–86.
4. Kolin, K. K., Khoroshilov, A. A., Nikitin, Yu. V., Pshenichny, S. I. & Khoroshilov, A. A. (2021). Artificial intelligence in machine translation technologies. In: Social Novelties and Social Sciences, 2 (4), 64–80. DOI: 10.31249/snsn/2021.02.05 (in Russ.).
5. Rarenko, M. B. (2021). Machine Translation: From Translation “by the Rules” to Neural Translation. In: Social Sciences and Humanities. Russian and Foreign Literature. Series 6: Linguistics, 3, 70–79. DOI: 10.31249/ling/2021.03.05 (in Russ.).
6. Miftakhova, R. G. & Morozkina, E. A. (2019). Machine Translation. Neural Translation. In: Bulletin of the Bashkir State University, 24 (2), 497–502 (in Russ.).
7. Kalinin, S. M. (2017). Topical approaches to the improvement of neural machine translation. In: The Bryansk State University Herald, 1 (31), 284–287 (in Russ.).
8. Garbovsky, N. K. & Kostikova, O. I. (2019). Intelligence in translation: artful and artificial? In: Lomonosov Translation Studies Jounal, 4, 3–25 (in Russ.).
9. Kasianov, V. K. & Fedulova, V. V. (2021). Main problems of neural machine translation. In: Advances in chemistry and chemical technology, 11 (246), 43–45 (in Russ.).
10. Sdobnikov, V. V. (2024). Artificial intelligence in translation: specification of concepts. In: Journal of Military Philology, 4, 38–47 (in Russ.).
11. Legostina, M. S. (2019). Metrics of quality assessment of machine translate. In: Innovations-2019: collection of materials of the XV International School-Conference of Students, Postgraduates and Young Scientists (Tomsk, April 25–27, 2019). Tomsk: STT Publ., pp. 490–493 (in Russ.).
12. Ulitkin, I. A. (2022). Automatic evaluation of machine translation quality of a scientific text: five years later.In: Bulletin of the Moscow Region State University. Series: Linguistics, 1, 47–59. DOI: 10.18384/2310- 712X-2022-1-47-59 (in Russ.).
Review
Views:
101
Email this article 
