METHOD OF CONTEXT-AWARE MACHINE TRANSLATION OF VIDEO GAME TEXTS USING NEURAL NETWORKS
DOI:
https://doi.org/10.28925/2663-4023.2026.33.1183Keywords:
machine translation; context-aware translation; neural networks; video games; localization; linguistic context; situational context; MarianMT; dialogue systems; natural language processingAbstract
This paper addresses the problem of improving the quality of machine translation of video game texts in a fragmented and context-dependent textual environment. The relevance of the study is обусловлена the limitations of modern neural machine translation systems, which typically operate at the level of individual text segments and do not account for broader linguistic and situational context, leading to semantic, terminological, and stylistic errors. The aim of the study is to develop a context-aware machine translation method for video game texts using neural networks, which improves semantic accuracy, consistency, and stylistic coherence by integrating relevant contextual information. The proposed approach is based on the formation of an extended input representation that combines the current text segment with contextual components, including dialogue history, information about the speaker and the addressee, the type of text fragment, the current scene or quest state, and a local glossary. The method is implemented using the MarianMT neural model without modifying its architecture, relying instead on preprocessing of input data. Experimental comparison with a baseline segment-level approach demonstrates that incorporating relevant context significantly improves translation quality in terms of semantic accuracy, correct pronoun resolution, terminological consistency, and stylistic coherence. The greatest improvements are observed in the translation of short dialogue utterances, interface messages, and highly context-dependent fragments. The practical significance of the results lies in the applicability of the proposed method to automated video game localization systems, particularly in scenarios where the full game script is not available. The findings confirm the importance of integrating contextual information as a key factor in improving machine translation quality and outline перспективи for further research in the direction of multimodal and adaptive context modeling.
Downloads
References
Pirrone, M., & D’Ulizia, A. (2024). The localization of software and video games: Current state and future perspectives. Information, 15(10), Article 648. https://doi.org/10.3390/info15100648
Pyae, A. (2018). Understanding the role of culture and cultural attributes in digital game localization. Entertainment Computing, 26, 105-116. https://doi.org/10.1016/j.entcom.2018.02.004
Maruf, S., Saleh, F., & Haffari, G. (2021). A survey on document-level neural machine translation: Methods and evaluation. ACM Computing Surveys, 54(2), Article 45. https://doi.org/10.1145/3441691
Castilho, S., & Knowles, R. (2025). A survey of context in neural machine translation and its evaluation. Natural Language Processing, 31(4), 986-1016. https://doi.org/10.1017/nlp.2024.7
Rivas Ginel, M. I., & Theroine, S. (2022). Machine translation and gender biases in video game localisation: A corpus-based analysis. Journal of Data Mining and Digital Humanities. https://doi.org/10.46298/jdmdh.9065
Zhao, X., Xu, H., Song, H., Chersoni, E., & Huang, C.-R. (2025). Can LLMs help Sun Wukong in his journey to the West? A case study of language models in video game localization. In Proceedings of the First Workshop on NLP and Language Models for Digital Humanities (RANLP 2025) (pp. 164-173). https://doi.org/10.26615/978-954-452-106-6-016
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems 30 (NeurIPS 2017) (pp. 5998-6008). https://doi.org/10.48550/arXiv.1706.03762
Mohammed, W., & Niculae, V. (2024). On measuring context utilization in document-level MT systems. In Findings of the Association for Computational Linguistics: EACL 2024 (pp. 1633-1643). https://doi.org/10.18653/v1/2024.findings-eacl.113
Fernandes, P., Yin, K., Neubig, G., & Martins, A. F. T. (2021). Measuring and increasing context usage in context-aware machine translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th IJCNLP (pp. 6467-6478). https://doi.org/10.18653/v1/2021.acl-long.505
Voita, E., Sennrich, R., & Titov, I. (2019). When a good translation is wrong in context: Context-aware machine translation improves on deixis, ellipsis, and lexical cohesion. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 1198-1212). https://doi.org/10.18653/v1/P19-1116
Agrawal, S., Farajian, A., Fernandes, P., Rei, R., & Martins, A. F. T. (2024). Assessing the role of context in chat translation evaluation: Is context helpful and under what conditions? Transactions of the Association for Computational Linguistics, 12, 1250-1267. https://doi.org/10.1162/tacl_a_00700
Hansen, D., & Houlmont, P.-Y. (2022). A snapshot into the possibility of video game machine translation. In Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (pp. 257-269).
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Вадим Мойсеєнко, Світлана Поперешняк
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
