Evaluating Terminological Consistency in AI-Generated English–Arabic Political Translation: Evidence From ChatGPT and Google Gemini

Osama Bala

doi:10.36602/faj.2026.n22.08

Authors

Osama Ali Bala Department of English, Faculty of Arts, Misurata University

DOI :

https://doi.org/10.36602/faj.2026.n22.08

Keywords:

Terminological consistency, AI translation, Political discourse, English–Arabic translation, Translation quality, Lexical cohesion

Abstract

Machine translation has become more fluent and contextually accurate with recent advances in artificial intelligence. However, terminological consistency has been underexplored, particularly in political and electoral discourse where lexical repetition and conceptual precision are critical for cohesion and clarity. This study investigates terminological consistency in AI-generated English–Arabic political translations produced by ChatGPT and Google Gemini Advanced. The translations were generated and analyzed between January and June 2026 using the systems’ default settings to ensure comparability and avoid potential variations resulting from user-configured parameters. The study employs a mixed-methods corpus-based approach. The study analyzes 30 political and electoral texts with 60 recurring key terms. Quantitative analysis measures the degree of consistency in the form of stability percentages, and qualitative analysis studies lexical variation and its effect on discourse cohesion and clarity. The adequacy and consistency of the translation were checked against a reference translation based on the United Nations Development Programme (UNDP) Arabic Lexicon of Electoral Terminology. The results indicate that ChatGPT achieved higher terminological consistency than Google Gemini. ChatGPT’s lexical equivalents for repeated political and electoral terms were more stable than its Gemini counterpart, which showed more lexical variation, especially in context-sensitive terms such as campaign, electoral law, and judicial review. The study concludes that terminological consistency should be considered as a separate dimension of translation quality and emphasizes the importance of terminology control and human post-editing in AI-assisted political translation

References

Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1409.0473

Baker, M. (2018). In other words: A coursebook on translation (3rd ed.). Routledge.

Freitas, A., Guerberof-Arenas, A., & Moorkens, J. (2024). Large language models and translation variation: Challenges for terminology consistency in specialized domains. Machine Translation, 38(1), 55–78.

Google DeepMind. (2023). Gemini: A family of highly capable multimodal models. https://arxiv.org/abs/2312.11805

Habash, N. (2010). Introduction to Arabic natural language processing. Morgan & Claypool Publishers. https://doi.org/10.2200/S00277ED1V01Y201008HLT010

Halliday, M. A. K., & Hasan, R. (1976). Cohesion in English. Longman.

Hendy, A., Abdelrehim, M., Sharaf, A., et al. (2023). How good are GPT models at machine translation? A comprehensive evaluation. arXiv preprint. https://arxiv.org/abs/2302.09210

House, J. (2015). Translation quality assessment: Past and present. Routledge.

Koehn, P. (2020). Neural machine translation. Cambridge University Press. https://doi.org/10.1017/9781108608485

Newmark, P. (1988). A textbook of translation. Prentice Hall.

OpenAI. (2023). GPT-4 technical report. https://arxiv.org/abs/2303.08774

Schäffner, C. (2004). Political discourse analysis from the point of view of translation studies. Journal of Language and Politics, 3(1), 117–150. https://doi.org/10.1075/jlp.3.1.07sch

Toral, A., & Sánchez-Cartagena, V. M. (2017). A multifaceted evaluation of neural versus phrase-based machine translation. Proceedings of EACL, 1063–1073.

Venuti, L. (2012). The translation studies reader (3rd ed.). Routledge.

Wang, Z., Li, Y., & Chen, X. (2024). Terminology consistency in large language model translation: A comparative evaluation of GPT-based systems. Journal of Artificial Intelligence and Language Processing, 8(2), 77–96.