Prompting Cultural Equivalence: A Comparative Analysis of Baker's Translation Models in Official and AI Translation of Thai Movie Titles
Article Sidebar
Main Article Content
Abstract
This study aimed to identify Baker’s translation strategies used to translate Thai movie titles by the official versions and compare the translations among the official versions and three different types of AI, specifically, Google Translate, ChatGPT, and Google Gemini. It also investigated how ChatGPT and Google Gemini translate movie titles differently when using various prompts, in accordance with Baker's translation strategies. The titles of the movies were selected from GTH/GDH movies under GDH 559 Co., Ltd. The population of this study was sixty-nine movie titles from the years 2004 to 2025. The rationale for selecting the titled movies was that they portray a wealth of Thai cultural themes. The purposive sampling technique was used to select movie titles. Sixty-nine movie titles were narrowed down to twenty because of the availability of the official English translation version. Baker's translation strategies were employed as a methodological tool. Percentage was used to analyze the data. The results revealed that the official version usually translates Thai movie titles using a more general word (MG) to include cultural nuance and captivate audiences. Google Translate, ChatGPT's simple prompt, and Google Gemini all employed the most paraphrased word strategy for translation (PR). This analysis indicated that these techniques focused on words, which may have translated accurately but may not have had enough cultural and emotional appeal to engage viewers. Finally, the application of simple and more complex translation instructions demonstrated different translation results. The basic prompt was translated by using paraphrase with related words, while the more elaborate prompts revealed more advanced translations.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This article is published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0), which allows others to share the article with proper attribution to the authors and prohibits commercial use or modification. For any other reuse or republication, permission from the journal and the authors is required.References
Ahrenberg, L. (2017). Comparing machine translation and human translation: A case study. In RANLP 2017: The First Workshop on Human-Informed Translation and Interpreting Technology (HiT-IT) (pp. 21-28). Association for Computational Linguistics.
Al-Wasy, B. & Mohammed, O. (2024). Strategies of translating euphemistic expressions from Arabic into English: A comparative study of artificial intelligence models with human translation. Journal of Educational Sciences and Humanities, 40, 826-855. https://doi.org/10.55074/hesj.vi40.1121
Baker, M. (2018). In Other Words: A Coursebook on Translation (3rd ed.). Routledge.
Chen, X., Zou, D., Xie, H., Cheng, G., & Liu, C. (2022). Two decades of artificial intelligence in education. Educational Technology & Society, 25(1), 28-47. https://www.jstor.org/stable/48647028
Fadwati, A. (2021, November). Baker’s Strategy in translating idiomatic expressions in Fast & Furious: Hobbs and Shaw’s movie subtitles. In 6th International Conference on Science, Education and Technology (ISET 2020) (pp. 198-204). Atlantis Press.
Futeng, Z. (2024). Intercultural communication and collision in the movie Industry. Academic Journal of Humanities & Social Sciences, 7(3), 161-165. https://doi.org/10.25236/ajhss.2024.070325
Habibi, V. R. (2025). The application of Nababan's TQA and Mona Baker's translation strategies of translating cultural words and in movie subtitle “Puss In Boots: The Last Wish”. JELL (Journal of English Language and Literature) STIBA-IEC Jakarta, 10(01), 215-224. https://doi.org/10.37110/jell.v10i01.271
Hakami, A. H., & Abomoati, G. S. (2024). Exploring the impact of prompt formulation in AI Chatbots on the translation of English-to-Arabic and Arabic-to-English idioms: A case study. Pakistan Journal of Life and Social Sciences, 22(2), 21371-21381. https://doi.org/10.57239/pjlss-2024-22.2.001508
Kanchanakas, P., & Rungruangthum, M. (2024). An Investigation of Translation Accuracy by Google Translate from English Idioms to Thai at Sentence Level. Journal of Humanities and Social Sciences for Sustainable Development, 7(1), 75-88. Retrieved from https://ssrujournal.com/index.php/hsssru/article/view/289
Koehn, P. (2020). Neural machine translation and its impact on professional translation. Language Science Press.
Maharani, N. M. D., Duriga, T. S., Barus, E. B., & Aryani, I. G. A. I. (2025). Lost and Found in Translation: Examining the English Version of Perahu Kertas. JETLEE: Journal of English Language Teaching, Linguistics, and Literature, 5(1), 84-97. https://doi.org/10.47766/jetlee.v5i1.4972
Moneus, A. M., & Sahari, Y. (2024). Artificial intelligence and human translation: A contrastive study based on legal texts. Heliyon, 10(6), e28106. https://doi.org/10.1016/j.heliyon.2024.e28106
Pan, J., Wong, B. T., & Wang, H. (2022). Navigating learner data in translator and interpreter training. Babel Revue Internationale De La Traduction / International Journal of Translation / Revista Internacional De Traducción, 68(2), 236–266. https://doi.org/10.1075/babel.00260.pan
Pasaribu, A. E. A., & Siregar, M. (2022). Translation strategies of subtitling Java Heat Movie. Ling Lit Journal Scientific Journal for Linguistics and Literature, 3(1), 24-30. https://doi.org/10.33258/linglit.v3i1.623
Saeed, A., & Hameed, S. (2024). Exploring the challenges faced by translator trainees in translating scientific and technical texts between Arabic and English: An error analysis approach. Journal of Social Studies, 30(3), 73-97. https://doi.org/10.20428/jss.v30i3.2547.
Seifi, S., Kargozari, H. R., & Arghiani, M. R. (2022). Baker's strategies applied in translation of Idioms in Persian dubbing of selected movies in comedy genre. Journal of Research in Techno-based Language Education, 2(2), 18-30. https://doi.org/10.22034/jrtle.2022.150885
Shahmerdanova, R. (2025). Artificial intelligence in translation: Challenges and opportunities. Acta Globalis Humanitatis Et Linguarum, 2(1), 62–70. https://doi.org/10.69760/aghel.02500108
Sukwises, A., Yodchim, S., Sukamonson, S., Chakorn, O. O., Ngiwline, P., & Krudthong, K. (2024). Techniques for culture-specific Item translation in Sepha Khun Chang Khun Phaen. Journal of Humanities and Social Sciences for Sustainable Development, 7(2), 5-22. Retrieved from https://ssrujournal.com/index.php/hsssru/article/view/183
Syavira, N. W., Sinaga, I. M., & Noryatin, Y. (2025). Comparing human translation with DeepL translate in translating idiom of Wednesday series. Jurnal Bahasa Asing, 18(1), 85-100. https://doi.org/10.58220/jba.v18i1.111
Wongseree, T. (2021). Translation of Thai Culture-Specific words into English in digital environment: Translators’ strategies and Use of technology. rEFLections, 28(3), 334–356. https://doi.org/10.61508/refl.v28i3.254613
Yanisky-Ravid, S., & Martens, C. (2019). From the myth of Babel to Google Translate: Confronting malicious use of artificial intelligence–Copyright and algorithmic biases in online translation systems. Seattle University Law Review, 43(1), 99–168. http://dx.doi.org/10.2139/ssrn.3345716.
Yuxiu, Y. (2024). Application of translation technology based on AI in translation teaching. Systems and Soft Computing, 6, Article 200072. https://doi.org/10.1016/j.sasc.2024.200072
Zaid, A., & Bennoudi, H. (2023). AI vs. Human Translators: Navigating the Complex World of Religious Texts and Cultural Sensitivity. International Journal of Linguistics Literature & Translation, 6(11), 173–182. https://doi.org/10.32996/ijllt.2023.6.11.21
