Evaluating language models on low-resource pairs

Bodenchuk-Pastukhov, Y. V.

Публікація:
Evaluating language models on low-resource pairs

dc.contributor.author	Bodenchuk-Pastukhov, Y. V.
dc.date.accessioned	2025-05-02T16:02:51Z
dc.date.available	2025-05-02T16:02:51Z
dc.date.issued	2025
dc.description.abstract	This work is devoted to the evaluation of the Facebook M2M100_418M and Alirezamsh Small100 models for low-resource language pairs. For this study, parallel corpora were selected for the following language pairs: Japanese-Ukrainian, Korean-Ukrainian, Turkish-Ukrainian, Vietnamese-Ukrainian, and Chinese-Ukrainian. The models were assessed based on their performance in translating these language pairs. Evaluation metrics included BLEU and ChrF scores, which measure the quality of the translations. Additionally, differences between the target and translated sentences were analyzed. The study aims to highlight the strengths and weaknesses of each model when working with low-resource languages. A comparative analysis of the results provides insights into the effectiveness of these models. The findings can be useful for future improvements in machine translation for underrepresented language pairs.
dc.identifier.citation	Bodenchuk-Pastukhov Y. V. Evaluating language models on low-resource pairs / Y. V. Bodenchuk-Pastukhov ; Supervisor Cand. Tech. Sci., Assist. I. O. Kobylin // Радіоелектроніка та молодь у XXI столітті : матеріали 29-го Міжнар. молодіж. форуму, 16–19 квітня 2025 р. – Харків : ХНУРЕ, 2025. – Т. 7. – С. 17–19.
dc.identifier.uri	https://openarchive.nure.ua/handle/document/31019
dc.language.iso	en
dc.publisher	ХНУРЕ
dc.subject	language model
dc.subject	low-resource pairs
dc.subject	evaluation
dc.title	Evaluating language models on low-resource pairs
dc.type	Thesis
dspace.entity.type	Publication