Semantic embedding via joint loss function and composite contrastive learning

Semantic embedding via joint loss function and composite contrastive learning

Contrastive learning has shown excellent performance in semantic embeddings by capturing relationships between data samples to enhance model representation. However, its effectiveness largely depends on constructing positive samples and selecting appropriate objective functions. Positive samples mus...

Full description

Saved in:
Bibliographic Details
Main Authors: GAO Xiaoxin, LU Yao, KONG Xiangmao, LIU Yuxi, DENG Wei, YANG Songhao
Format: Article
Language:zho
Published: Beijing Xintong Media Co., Ltd 2025-07-01
Series:Dianxin kexue
Subjects:
contrastive learning
sentence embedding
semantic textual similarity
text classification
joint loss function
Online Access:http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2025142/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2025142/

Similar Items