TY - JOUR
T1 - Contrastive Learning Models for Sentence Representations
AU - Xu, Lingling
AU - Xie, Haoran
AU - Li, Zongxi
AU - Wang, Fu Lee
AU - Wang, Weiming
AU - Li, Qing
N1 - Publisher Copyright:
© 2023 Copyright held by the owner/author(s).
PY - 2023/6/15
Y1 - 2023/6/15
N2 - 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.
AB - 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.
KW - Additional Key Words and PhrasesSentence representation learning
KW - BERT
KW - Data Augmentation
KW - contrastive learning
UR - http://www.scopus.com/inward/record.url?scp=85168809469&partnerID=8YFLogxK
U2 - 10.1145/3593590
DO - 10.1145/3593590
M3 - Article
AN - SCOPUS:85168809469
SN - 2157-6904
VL - 14
JO - ACM Transactions on Intelligent Systems and Technology
JF - ACM Transactions on Intelligent Systems and Technology
IS - 4
M1 - 67
ER -