Contrastive Learning Models for Sentence Representations
ACM Transactions on Intelligent Systems and Technology · 2023-08-31 · 14 (4) · 1-34
DOI: 10.1145/3593590 ↗At a glance
Journal article in ACM Transactions on Intelligent Systems and Technology, published online on 2023-06-15. Written by Lingling Xu and 5 co-authors. Cited 52 times so far (Crossref); 142 references. The full text is freely available (open access, CC BY-NC-SA 4.0). Funded by: Research Grants Council of the Hong Kong Special Administrative Region, China, Lam Woo Research Fund of Lingnan University.
Abstract (original language)
Sentence representation learning is a crucial task in natural language processing, as the quality of learned representations directly influences downstream tasks, such as sentence classification and sentiment analysis. Transformer-based pretrained language models such as bidirectional encoder representations from transformers (BERT) have been extensively applied to various natural language processing tasks, and have exhibited moderately good performance. However, the anisotropy of the learned embedding space prevents BERT sentence embeddings from achieving good results in the semantic textual similarity tasks. It has been shown that contrastive learning can alleviate the anisotropy problem and significantly improve sentence representation performance. Therefore, there has been a surge in the development of models that utilize contrastive learning to fine-tune BERT-like pretrained language models to learn sentence representations. But no systematic review of contrastive learning models for sentence representations has been conducted. To fill this gap, this article summarizes and categorizes the contrastive learning based sentence representation models, common evaluation tasks for assessing the quality of learned representations, and future research directions. Furthermore, we select several representative models for exhaustive experiments to illustrate the quantitative improvement of various strategies on sentence representations.
Funding
- Research Grants Council of the Hong Kong Special Administrative Region, China
- Lam Woo Research Fund of Lingnan University
Cite
APA
Xu, L., Xie, H., Li, Z., Wang, F. L., Wang, W., & Li, Q. (2023). Contrastive Learning Models for Sentence Representations. ACM Transactions on Intelligent Systems and Technology, 14(4), 1-34. https://doi.org/10.1145/3593590
Vancouver
Xu L, Xie H, Li Z, Wang FL, Wang W, Li Q. Contrastive Learning Models for Sentence Representations. ACM Transactions on Intelligent Systems and Technology. 2023;14(4):1-34. doi:10.1145/3593590
BibTeX
@article{Xu2023,
author = {Xu, Lingling and Xie, Haoran and Li, Zongxi and Wang, Fu Lee and Wang, Weiming and Li, Qing},
title = {Contrastive Learning Models for Sentence Representations},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2023},
volume = {14},
number = {4},
pages = {1--34},
doi = {10.1145/3593590}
}
EUVIMED