PROBLEMS AND SOLUTIONS IN AUTOMATIC TRANSLATION OF UZBEK IDIOMS AND FIGURATIVE EXPRESSIONS
DOI:
https://doi.org/10.55640/eijmrms-special-49Keywords:
machine translation, NMT, literal translation, idiomAbstract
This article analyzes the challenges encountered in the automatic translation of Uzbek idioms and figurative expressions, examines the errors of NMT models, and proposes a computational linguistic model designed to identify idioms and translate them figuratively based on UzbekWordNet and semantic networks.
References
Koehn P., Knowles R. Six challenges for neural machine translation //arXiv preprint arXiv:1706.03872. – 2017.
Bahdanau D. Neural machine translation by jointly learning to align and translate //arXiv preprint arXiv:1409.0473. – 2014.
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. – 2023. – С. 3682-3700.
https://es.wikipedia.org/wiki/WordNet
Agostini A. et al. Uzwordnet: A lexical-semantic database for the uzbek language //Proceedings of the 11th Global Wordnet conference. – 2021. – С. 8-19.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Gulshoda Abdumalikova, Charos Tukhtasinova
This work is licensed under a Creative Commons Attribution 4.0 International License.
Individual articles are published Open Access under the Creative Commons Licence: CC-BY 4.0.
