POST-EDITING (MTPE) PROBLEMS AND THEIR LINGUISTIC SOLUTIONS IN RENDERING UZBEK NATIONAL REALIA INTO ENGLISH THROUGH ARTIFICIAL INTELLIGENCE AND NEURAL MACHINE TRANSLATION

Authors

  • Azimova Sitora Orif kizi Sirdaryo region, Sirdaryo district school N:6, English teacher Author

Keywords:

post-editing, MTPE, neural machine translation, large language models, realia, culture-bound units, ISO 18587, MQM, terminology base, pre-editing, Uzbek language.

Abstract

 The article examines the problems of machine translation post-editing (MTPE) that arise when Uzbek national realia are rendered into English by neural machine translation engines and large language models. A working classification of Uzbek realia relevant to machine processing is proposed, and a typology of nine recurrent machine errors is established and mapped onto the categories of the MQM framework. The levels of post-editing intervention are analysed in accordance with ISO 18587:2017, and it is shown that the light post-editing regime is structurally incapable of resolving realia-related errors, since these belong to the cultural rather than the grammatical layer of the text. A decision procedure comprising seven linguistic solutions is proposed, together with preventive measures at the pre-editing, terminology-management and prompt-design stages. Empirical evidence from comparative evaluations of generative and neural systems on culture-bound literary material is discussed in support of a hybrid workflow in which the machine produces the draft, a controlled terminology base secures consistency, and the human post-editor retains responsibility for cultural adequacy.

References

1.ISO 18587:2017. Translation services — Post-editing of machine translation output — Requirements. – Geneva: International Organization for Standardization, 2017. – 19 p.

2.ISO 17100:2015. Translation services — Requirements for translation services. – Geneva: International Organization for Standardization, 2015. – 21 p.

3.MQM Council. The MQM error typology. – URL: https://themqm.org/error-types-2/typology/

4.Lommel A., Uszkoreit H., Burchardt A. Multidimensional Quality Metrics (MQM): A framework for declaring and describing translation quality metrics // Tradumàtica. – 2014. – №12. – P. 455–463.

5.Wang Q. Evaluating Uighur literary translation: A comparative study of ChatGPT, Google Translate, and Bing Translator // PLOS ONE. – 2025. – Vol. 20, №10. – Art. e0335261.

6.Krings H.P. Repairing texts: Empirical investigations of machine translation post-editing processes. – Kent: Kent State University Press, 2001. – 635 p.

7.O’Brien S. Towards a dynamic quality evaluation model for translation // The Journal of Specialised Translation. – 2012. – №17. – P. 55–77.

8.Koponen M. Is machine translation post-editing worth the effort? A survey of research into post-editing and effort // The Journal of Specialised Translation. – 2016. – №25. – P. 131–148.

9.Newmark P. A textbook of translation. – New York: Prentice Hall, 1988. – 292 p.

10.Vinay J.-P., Darbelnet J. Comparative stylistics of French and English: A methodology for translation. – Amsterdam: John Benjamins, 1995. – 358 p.

11.Baker M. In other words: A coursebook on translation. 3rd ed. – London: Routledge, 2018. – 390 p.

12.Pedersen J. Subtitling norms for television: An exploration focussing on extralinguistic cultural references. – Amsterdam: John Benjamins, 2011. – 242 p.

13.Venuti L. The translator’s invisibility: A history of translation. 2nd ed. – London: Routledge, 2008. – 336 p.

14.Nida E.A. Toward a science of translating. – Leiden: E.J. Brill, 1964. – 331 p.

15.Влахов С., Флорин С. Непереводимое в переводе. – М.: Международные отношения, 1980. – 343 с.

16.Комиссаров В.Н. Современное переводоведение. – М.: ЭТС, 2002. – 424 с.

17.Ranathunga S., Lee E.-S.A., Skenduli M.P., et al. Neural machine translation for low-resource languages: A survey // ACM Computing Surveys. – 2023. – Vol. 55, №11. – P. 1–37.

18.Díaz Cintas J., Remael A. Subtitling: Concepts and practices. – London: Routledge, 2021. – 292 p.

Downloads

Published

2026-08-22