OVERCOMING LINGUISTIC CHALLENGES IN UZBEK – ENGLISH AI TRANSLATION: A STUDY OF FILM REVIEW DISCOURSE
Abstract
This study was prompted by a simple question about the best tools for translation for an English lesson on films for pre-intermediate Uzbek learners. Based on this enquiry this paper explores difficulties faced in Uzbek-to- English translation specifically within the framework of film review discourse. It explores translation generated across four tools. Two from Neural Machine Translation (NMT) Google Translate, Yandex Translate and two from Large Language Models (LLMs) ChatGPT and Gemini. Reviews of six Uzbek films from authentic sources were analyzed and based on the expert input from an Uzbek language specialist this study identified failure types in terms of use of idioms, cultural terminology, register maintenance and overall cohesion. The paper concludes with a recommendation based on multi-layered intervention approach that integrate Skopos - based human editing and glossaries with human interventions to facilitate translation accuracy, especially for low resource languages.
References
1. Abiyatova, M. M. (2025). Skopos theory in translation. Samarkand State Institute of Foreign Languages.
2. Al Salem, M. N., Alghazo, S., et al. (2026). How AI translation personas reframe diplomatic texts. Studies in Media and Communication. (January 2026)
3. Berman, A. (1985). Translation and the trials of the foreign. In L. Venuti (Ed. & Trans.), The translation studies reader (pp. 276–289). Routledge.
4. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., … Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
5. Court, S., & Elsner, M. (2024). Shortcomings of LLMs for low-resource translation: Retrieval and understanding are both the problem. ACL Anthology.
6. Feng, C. (2025). Analysis of semantic deviation in AI translation and linguistic optimization paths. International Scientific Technical and Economic Research. (June 2025)
7. Goddard, C. (2020). Overcoming the linguistic challenges for ethno-epistemology. [Book chapter]. (May 2020)
8. Joshi, P., Santy, S., Budhiraja, A., Bali, K., & Choudhury, M. (2020). The state and fate of linguistic diversity and inclusion in the NLP world. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 6282–6293.
9. Jumashukurov, A. (2024). The quality of translation of Turkic languages by AI translation tools. Journal of Student Research. (November 2024)
10. Martin, J. R., & White, P. R. R. (2005). The language of evaluation: Appraisal in English. Palgrave Macmillan.
11. Nekoto, W., Marivate, V., Matsila, T., Fasubaa, T., Fagbohungbe, T., Akinola, S. O., … Bashir, A. (2020). Participatory research for low-resourced machine translation: A case study in African languages. Findings of EMNLP 2020, 2144–2160.
12. Pang, J., Ye, F., Wong, D. F., Yu, D., Shi, S., Tu, Z., & Wang, L. (2025). Salute the classic: Revisiting challenges of machine translation in the age of large language models. Transactions of the Association for Computational Linguistics, 13, 73–95. https://doi.org/10.1162/tacl_a_00730
13. Park, J. (2022). A comparative study of AI translation: Google Translate and Papago. Studies in Linguistics. (October 2022)
14. Pucinskaite, J., & Mitkov, R. (2025). Evaluating the LLM and NMT models in translating low-resourced languages. ACL Anthology.
15. Ramzan, K., Sadiq, A., & Noor, A. (2025). Comparative analysis of Google translation and human translation through the lens of Skopos theory. Journal of Applied Linguistics and TESOL (JALT), 8(1), 1938–1949.
16. Schleppegrell, M. J. (2007). The linguistic challenges of mathematics teaching and learning: A research review. Reading & Writing Quarterly. (February 2007)
17. Sergeyevna, Y. M. (2025). Overcoming linguistic challenges in translation: Strategies for success. American Journal of Philological Sciences. (April 2025)
18. Venuti, L. (1995). The translator’s invisibility: A history of translation. Routledge.
19. Zhang, F. (2025). A comparative analysis of human translation and AI translation in humorous subtitles: A case study of Her Story. Lecture Notes in Education Psychology and Public Media. (August 2025)
20. Zhong, T., et al. (2025). Opportunities and challenges of large language models for low-resource languages in humanities research.
NMT and LLM
21. Google. (2024). Google Translate. Google LLC. https://translate.google.com
22. Google DeepMind. (2023). Gemini: A family of highly capable multimodal models. Google DeepMind. https://deepmind.google/technologies/gemini
23. OpenAI. (2023). GPT-4 technical report. https://arxiv.org/abs/2303.08774
24. Yandex. (2024). Yandex Translate. Yandex LLC. https://translate.yandex.com
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Maria Mercy, Amutha Amalraj, Manzura Maxmaraximova
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Litsenziya shartlari
Bu ish Creative Commons Attribution-NoCommercial 4.0 xalqaro litsenziyasi ostida litsenziyalangan. Ushbu litsenziya nusxasini koʻrish uchun http://creativecommons.org/licenses/by-nc/4.0/ saytiga tashrif buyuring yoki Creative Commons, PO Box 1866, Mountain View, CA 94042, AQShga xat yuboring.
Ushbu litsenziyaga muvofiq, siz:
Ulashish — materialni istalgan vosita yoki formatda nusxalash va qayta tarqatish
Moslashtiring - remiks qiling, o'zgartiring va materialga asoslang
Litsenziya shartlariga rioya qilgan holda litsenziar ushbu erkinliklarni bekor qila olmaydi. Quyidagi shartlar asosida:
Atribut - Siz tegishli kredit berishingiz, litsenziyaga havolani taqdim etishingiz va o'zgartirishlar kiritilganligini ko'rsatishingiz kerak. Siz buni har qanday oqilona yo'l bilan qilishingiz mumkin, lekin litsenziar sizni yoki sizning foydalanishingizni ma'qullashini taklif qiladigan tarzda emas.
Notijorat - Siz materialdan tijorat maqsadlarida foydalana olmaysiz.
Hech qanday qo'shimcha cheklovlar yo'q - Siz boshqalarga litsenziya ruxsat bergan har qanday harakatni qonuniy ravishda cheklaydigan qonuniy shartlar yoki texnologik choralarni qo'llay olmaysiz.
