THE IMPORTANCE OF LARGE LANGUAGE MODEL IN UZBEK-ENGLISH TRANSLATION SYSTEM
DOI:
https://doi.org/10.65164/2c6pxa48Kalit so‘zlar:
rule-based approach, model fine-tuning, corpus-based traning, hybrid approachesAbstrak
The recent years there are a significant rise appling artificial intelligence across
different domains, it is used to improve performance as well to get more accurate results. In this article
delve into study carried on Uzbek-English and vice verce translation system which include models
also. Initially, in the study rule-based approach was used and get translation results. Yet, to achieve
translation quality and accuracy it is decided to do hybride approach. We used 142838 paired corpus
and did normalization before training it different 3 models. The result adduces satisfactory result as
translation system can translate various topics in Simple and complex sentences.
Havolalar
[1] Alawneh, M. F., & Sembok, T. M. (2011). Rule-based and example-based machine translation
from English to Arabic. In: Proceedings of the 2011 Sixth International Conference on Bio-
Inspired Computing: Theories and Applications (BIC-TA), pp. 343–345.
1226
https://doi.org/10.1109/BIC-TA.2011.76
[2] Mengliev, D., Barakhnin, V., & Abdurakhmonova, N. (2021). Development of intellectual web
system for morph analyzing of uzbek words. Applied Sciences, 11(19), 9117.
[3] Nazirova, E., Abdurakhmonova, N., & Usmonova, K. (2024). Challenges in corpus linguistics
and machine translation. In: Proceedings of the International Scientific-Practical Conference
“Contemporary Technologies of Computational Linguistics” (CTCL 2024), Vol. 2, No. 22.04,
MyScience Proceedings.
[4] Nagineni, V. S., Idamakanti, K., Bhoopal, N., Kumar, D. G., Rao, D. S. N. M., & Bacha, B.T.
(2023). Quality evaluation and assessment of machine translations for English to Turkish
(Google Translations vs DeepL Translations). In: Proceedings of the 2023 Global Conference
on Information Technologies and Communications (GCITC).
https://doi.org/10.1109/GCITC60406.2023.10426024
[5] Nazirova, E., & Usmonova, K. (2024). Algorithm of identifying adjectives from participles in
translation from Uzbek to English for machine translation. In: Proceedings of the 2024 IEEE
3rd International Conference on Problems of Informatics, Electronics and Radio Engineering
(PIERE), pp. 1740–1744.
[6] Nazirova, E., & Usmonova, K. (2024). Algorithmic strategies of complex word analyzing from
Uzbek to English for machine translation. AIP Conference Proceedings, 3244, 030054.
https://doi.org/10.1063/5.0242104
[7] Nazirova, E. Sh., Abidova, Sh. B., Kxolmuminov, Y. X., Boymurodov, F., Medetbayeva, N.
B., & Usmonova, K. A. (2024). Mathematical model and algorithm for grammatical editing of
given words in Uzbek language. Springer Proceedings in Mathematics & Statistics,
Mathematics for Sustainable Industry (ISMI 2024), Kuala Lumpur, Malaysia.
[8] Tutar, K., & Yıldız, O. T. (2024). Turkish question-answer dataset evaluated with deep
learning. In: Proceedings of the 2024 9th International Conference on Computer Science and
Engineering (UBMK). https://doi.org/10.1109/UBMK63289.2024.10773453
