The article examines the pragmatic and cultural challenges of translating English idiomatic expressions into Uzbek with artificial intelligence-based tools. Idiom translation is treated as a three-dimensional problem of semantic accuracy, pragmatic equivalence and cultural appropriateness. Emotional, interpersonal and culture-bound idioms are analysed in context and compared with literal renderings and functional Uzbek equivalents, showing how word-for-word transfer can obscure figurative meaning, shift speaker stance or register, and produce images that Uzbek does not recognise as idiomatic. The author proposes the Pragmatic-Cultural Translation Adequacy Index (PCTAI), which combines anchored five-point scales, explicit weights, a semantic gating rule, decision bands and a coding scheme for translation strategies and error types, together with a reproducible protocol for the expert evaluation of Google Translate, DeepL and ChatGPT outputs. The examples are analyst-constructed rather than recorded platform outputs, and no comparative platform scores are claimed. The framework provides a transparent basis for future empirical comparison and for culturally sensitive assessment of machine translation.

artificial intelligence, idiomatic expressions, machine translation, pragmatic equivalence, cultural appropriateness, semantic accuracy, English–Uzbek translation, translation quality assessment.

Baker M. In Other Words: A Coursebook on Translation. – London; New York: Routledge, 1992. – 304 p.

Fernando C. Idioms and Idiomaticity. – Oxford: Oxford University Press, 1996.

Dankers V., Lucas C., Titov I. Can Transformer Be Too Compositional? Analysing Idiom Processing in Neural Machine Translation // Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). – Dublin, 2022. – P. 3608–3626. – DOI: 10.18653/v1/2022.acl-long.252.

Baziotis C., Mathur P., Hasler E. Automatic Evaluation and Analysis of Idioms in Neural Machine Translation // Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. – Dubrovnik, 2023. – P. 3682–3700. – DOI: 10.18653/v1/2023.eacl-main.267.

Hendy A., Abdelrehim M., Sharaf A., Raunak V., Gabr M., Matsushita H., Kim Y.J., Afify M., Awadalla H.H. How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation // arXiv preprint. – 2023. – arXiv:2302.09210. – DOI: 10.48550/arXiv.2302.09210.

Nida E.A., Taber C.R. The Theory and Practice of Translation. – Leiden: E.J. Brill, 1969.

Rahmatullayev Sh. O‘zbek tilining izohli frazeologik lug‘ati. – Toshkent: O‘qituvchi, 1978.

Koehn P., Knowles R. Six Challenges for Neural Machine Translation // Proceedings of the First Workshop on Neural Machine Translation. – Vancouver, 2017. – P. 28–39. – DOI: 10.18653/v1/W17-3204.

Li S., Chen J., Yuan S., Wu X., Yang H., Tao S., Xiao Y. Translate Meanings, Not Just Words: IdiomKB’s Role in Optimizing Idiomatic Translation with Language Models // Proceedings of the AAAI Conference on Artificial Intelligence. – 2024. – Vol. 38, № 17. – P. 18554–18563. – DOI: 10.1609/aaai.v38i17.29817.

Papineni K., Roukos S., Ward T., Zhu W.-J. BLEU: A Method for Automatic Evaluation of Machine Translation // Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. – Philadelphia, 2002. – P. 311–318. – DOI: 10.3115/1073083.1073135.

House J. Translation Quality Assessment: Past and Present. – London; New York: Routledge, 2015.

Freitag M., Foster G., Grangier D., Ratnakar V., Tan Q., Macherey W. Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation // Transactions of the Association for Computational Linguistics. – 2021. – Vol. 9. – P. 1460–1474. – DOI: 10.1162/tacl_a_00437.

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. – DOI: 10.5565/rev/tradumatica.77.

Cohen J. Weighted Kappa: Nominal Scale Agreement with Provision for Scaled Disagreement or Partial Credit // Psychological Bulletin. – 1968. – Vol. 70, № 4. – P. 213–220. – DOI: 10.1037/h0026256.

Friedman M. The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance // Journal of the American Statistical Association. – 1937. – Vol. 32, № 200. – P. 675–701. – DOI: 10.1080/01621459.1937.10503522.