Version 1
: Received: 29 June 2024 / Approved: 1 July 2024 / Online: 1 July 2024 (08:12:24 CEST)
How to cite:
Kriuk, B.; Kriuk, F. Multi-Objective Optimal Threshold Selection for Similarity Functions in Siamese Networks for Semantic Textual Similarity Tasks. Preprints2024, 2024070020. https://doi.org/10.20944/preprints202407.0020.v1
Kriuk, B.; Kriuk, F. Multi-Objective Optimal Threshold Selection for Similarity Functions in Siamese Networks for Semantic Textual Similarity Tasks. Preprints 2024, 2024070020. https://doi.org/10.20944/preprints202407.0020.v1
Kriuk, B.; Kriuk, F. Multi-Objective Optimal Threshold Selection for Similarity Functions in Siamese Networks for Semantic Textual Similarity Tasks. Preprints2024, 2024070020. https://doi.org/10.20944/preprints202407.0020.v1
APA Style
Kriuk, B., & Kriuk, F. (2024). Multi-Objective Optimal Threshold Selection for Similarity Functions in Siamese Networks for Semantic Textual Similarity Tasks. Preprints. https://doi.org/10.20944/preprints202407.0020.v1
Chicago/Turabian Style
Kriuk, B. and Fedor Kriuk. 2024 "Multi-Objective Optimal Threshold Selection for Similarity Functions in Siamese Networks for Semantic Textual Similarity Tasks" Preprints. https://doi.org/10.20944/preprints202407.0020.v1
Abstract
This paper presents a comparative study of fundamental similarity functions for Siamese networks in semantic textual similarity (STS) tasks. We evaluate various similarity functions using the STS Benchmark dataset, analyzing their performance and stability. Additionally, we introduce a multi-objective approach for optimal threshold selection. Our findings provide insights into the effectiveness of different similarity functions and offer a straightforward method for threshold selection optimization, contributing to the advancement of Siamese network architectures in STS applications.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.