Semantic textual similarity models evaluation for tasks requiring binary threshold decisions

Публікація:
Semantic textual similarity models evaluation for tasks requiring binary threshold decisions

dc.contributor.author	Nikolaichuk, A. I.
dc.date.accessioned	2025-04-28T06:24:32Z
dc.date.available	2025-04-28T06:24:32Z
dc.date.issued	2025
dc.description.abstract	This work evaluates Semantic Textual Similarity (STS) models for tasks requiring binary threshold decisions. The experiment used English and Ukrainian STS datasets, categorizing sentence pairs as successful or challenging based on a similarity score difference threshold. GTE demonstrated higher resistance to typos in English, while MPNet and MiniLM struggled more with lexical and morphological variations in Ukrainian. The analysis highlights the importance of considering task-specific and dataset-related challenges when selecting models for optimal performance.
dc.identifier.citation	Nikolaichuk A. I. Semantic textual similarity models evaluation for tasks requiring binary threshold decisions / A. I. Nikolaichuk // Радіоелектроніка та молодь у XXI столітті : матеріали 29-го Міжнар. молодіж. форуму, 16–19 квітня 2025 р. – Харків : ХНУРЕ, 2025. – Т. 6 – С. 470-472.
dc.identifier.uri	https://openarchive.nure.ua/handle/document/30833
dc.language.iso	en_US
dc.publisher	ХНУРЕ
dc.subject	semantic similarity
dc.subject	textual model
dc.subject	binary decision
dc.title	Semantic textual similarity models evaluation for tasks requiring binary threshold decisions
dc.type	Thesis
dspace.entity.type	Publication