Contextual Accuracy and Human-AI Collaboration in Translations: A Comparative Linguistic Analysis through Synergistic Model

Abstract

In this study, the focus is placed on evaluating the capabilities of the human translator relative to the most contemporary state-of-the-art AI-assisted translation tools such as ‘ChatGPT’ and ‘DeepSeek’ in translating text from ‘English’ to ‘Urdu’. The main focus of this study is evaluating linguistic faithfulness, contextual accuracy, and cultural adjustment within these AI systems. Past literature has demonstrated that AI systems fail miserably in handling culturally rich and idiomatic texts, while human translators normally outperform them by navigating through the contextual nuance. In this regard, this study applies to the Synergistic Model in exploring the potential benefits a collaborative approach between humans and AI may bring in enhancing the quality of translation, including the Human-in-the-Loop (HITL) AI Theory, AI Augmented Translation Theory, and Hermeneutic Translation Theory. Results indicated low efficiency of the AI-assisted translation system without human help and suggested that the preservation of cultural and contextual wholeness of the translation depends highly on human intervention. This study adds to the growing literature investigating the collaboration of AI-human translation studies in which the next generation of AI translation systems should focus on strengthening their capacity for the nuances of culture and be extended across more languages and domains. The study underlines a new direction toward greater translation accuracy and cultural resonance across language barriers through fostering AI-human collaboration using the Synergistic Model. References Al Ghamdi, R. (2023). Investigating the use of politeness strategies in expressing disagreements among Saudi EFL teachers on Twitter (Doctoral dissertation, The University of Mississippi). Al-Khresheh, M. H. (2025). A back translation analysis of AI-generated Arabic–English texts using ChatGPT: Exploring accuracy and meaning retention. Dragoman Journal of Translation Studies, 17, 97–117. Badruddin, A., & Fadaei, S. (2023). The evolution of neural machine translation (NMT). Journal of Artificial Intelligence in Language Processing, 7(1), 45–60. Baroni, I., Re Calegari, G. R., Scandolari, D., & Celino, I. (2022). AI-TAM: A model to investigate user acceptance and collaborative intention in human-in-the-loop AI applications. Human Computation, 9(1), 1–21. https://doi.org/10.15346/hc.v9i1.134 Benedikt, L., Joshi, C., Nolan, L., & Henstra-Hill, R. (2020). Human-in-the-loop machine learning for translation enhancement. In Proceedings of the 16th ACM Conference on Recommender Systems (pp. 300–310). Beseiso, M., Tripathi, S., Al-Shboul, B., & Aljadid, R. (2022). Semantics-based English– Arabic machine translation evaluation. Indonesian Journal of Electrical Engineering and Computer Science, 27(1), 189–197. Chatzikoumi, E. (2020). The challenges of machine translation in literary texts. Translation and Literature Review, 15(3), 210–225. Daems, J., Vandepitte, S., Hartsuiker, R. J., & Macken, L. (2017). Comparing human translation and post-editing of machine translations. Meta, 62(2), 401–423. Farghal, M., & Haider, F. (2025). A cogno-prosodic approach to translating Arabic poetry into English: Human vs. machine. 3L: Language, Linguistics, Literature®, 31(1), 255–271. https://doi.org/10.17576/3L-2025-3101-17 Gao, R., Lin, Y., Zhao, N., & Cai, Z. G. (2024). Machine translation of Chinese classical poetry: A comparison among ChatGPT, Google Translate, and DeepL Translator. Humanities and Social Sciences, 14(2), 50–68. Gao, S., Liu, X., & Zhang, X. (2024). Comparative performance of AI-driven translations of Chinese classical poetry. Journal of Literary Studies, 39(1), 15–33. Jackson, S. (1948, June 26). The lottery. The New Yorker. https://www.newyorker.com/magazine/1948/06/26/the-lottery Karimnia, A., & Kharmandar, M. A. (2013). The impact of figurative language in literary translation: Human vs. machine translation. Procedia – Social and Behavioral Sciences, 70, 721–729. Kenny, D. (2022). Human and machine translation. In D. Kenny (Ed.), Machine translation for everyone: Empowering users in the age of artificial intelligence (pp. 23–49). Berlin: Language Science Press. Kharmandar, M. A. (2015). Ricoeur’s extended hermeneutic translation theory: Metaphysics, narrative, ethics, and politics. Études Ricoeuriennes/Ricoeur Studies, 6(2), 45–61. Lee, J., & Lee, K. (2021). AI in legal translation: Opportunities and challenges. Journal of Language and Law, 10(2), 85–104. Liu, H. (2023). Neural machine translation and cultural nuances: A review. International Journal of Translation Studies, 18(1), 45–60. Liu, X. (2023). Research on the application of artificial intelligence in comparative analysis of man–machine translation. Proceedings of the 2023 International Joint Conference on AI and NLP (pp. 110–120). Mohamed, Y. A., Khanan, A., & Bashir, M. (2024). The impact of artificial intelligence on language translation: A review. IEEE Transactions on Machine Learning, 5(2), 33– 48. Mohsen, A. (2024). Evaluating AI performance in legal and technical translation: A comparative study. AI & Language Journal, 12(1), 33–50. Mohyuddin, G. (n.d.). The Lottery [Urdu translation]. Urdu Anthology. Retrieved April 8, 2025, from https://ghulammohyuddin.urduanthology.com Moneus, A. M., & Sahari, Y. (2024). Artificial intelligence and human translation: A contrastive study based on legal texts. Heliyon, 10(1), e13125. Moneus, T., & Sahari, Y. (2024). Human-in-the-loop systems in AI translation: Bridging cultural gaps. Journal of Computational Linguistics, 29(2), 115–132. O’Brien, S. (2022). Post-editing of machine translation: Processes and applications. Cambridge University Press. O’Brien, S. (2024a). Augmented translation: Human and AI collaboration. Translation Spaces, 13(1), 9–29. O’Brien, S. (2024b). Human-Centered Augmented Translation: Against antagonistic dualisms. Perspectives: Studies in Translation Theory and Practice, 32(2), 155–173. Ren, X. (2024). We want but we can’t: Measuring EFL translation majors’ intention to use ChatGPT in their translation practice. Humanities and Social Sciences Communications, 11(1), 99. Ricoeur, P. (2015). Interpretation theory: Discourse and the surplus of meaning. Texas Christian University Press. Sahari, Y., & Alasmri, H. (2024). The limitations of AI systems in translating figurative language. Journal of Translation Studies, 18(1), 70–85. Sahari, Y., & Qasem, F. (2024). Evaluating machine translation of literary works: The challenge of translating cultural nuance. Research in Applied Linguistics, 15(2), 45– 60. Sahari, Y., et al. (2024). Evaluating machine translation of literature through rhetorical analysis. Translation Studies, 17(1), 22–40. Wang, H., Xie, Z., & Li, Y. (2022). Neural machine translation and its role in modern translation technology. Journal of Computational Linguistics, 28(3), 112–130. Kaur, P., & Moghal, A. J. (2013). Women’s resources and power dynamics in Sikh families in Malaysia. International Journal of Sociology of the Family, 77–92. Kaur, P., Au Yong, S. J., Lim, W. C., Zoferi, N. ‘A. N. B., & Jawaid, A. (2017). Adult day care provision in Kuching, Sarawak: Positive aging or social isolation? Journal of Borneo-Kalimantan, 3(2). https://doi.org/10.33736/jbk.632.2017 Kaur, P., Chai, N. F., & Jawaid, A. (2017). Recycling practices and perceptions among rural primary school children in SJK Chung Hua Asajaya, Samarahan, Sarawak. Journal of Borneo-Kalimantan, 3(2). https://doi.org/10.33736/jbk.624.2017 Kaur, P., Jawaid, A., Alvi, A. K., & Chishti, M. F. (2019). Problems faced by children with cancer in Sarawak, Malaysia. Opción: Revista de Ciencias Humanas y Sociales, (24), 668–689. Wu, X., Xiao, L., & He, L. (2022). Human-in-the-loop machine learning for improving translation accuracy. Future Generation Computer Systems, 136, 133–145. Xiao, L. (2023). Evaluating large language models in English-to-Urdu translation: Contextual accuracy and challenges. International Journal of AI and Language Translation, 10(1), 28–44. Xiao, X. C. (2023). Research on the application of artificial intelligence in comparative analysis of man–machine translation. Proceedings of the 2023 International Joint Conference on AI and NLP (pp. 130–142). Zhang, Y., Liu, X., & Liu, Y. (2023). Large pre-trained language models for translation: Insights and challenges. Journal of AI and Natural Language Processing, 9(2), 50– 68. Zhao, Z., Zhang, L., & Li, J. (2024). Exploring AI translation of cultural references in Urdu– English texts. Journal of Cross-Cultural Translation Studies, 6(1), 77–92. Zhu, J. (2009). Intentional systems and the AI hermeneutic network. Journal of Philosophy and AI, 3(1), 15–29. Zong, C. (2018). The complexities of translating idiomatic expressions. International Journal of Translation and Interpretation, 12(2), 100–115.

Ähnliche Arbeiten