Abstract
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.
Original language | English |
---|---|
Article number | 67 |
Pages (from-to) | 1-34 |
Journal | ACM Transactions on Intelligent Systems and Technology |
Volume | 14 |
Issue number | 4 |
DOIs | |
Publication status | Published - 15 Jun 2023 |
Keywords
- Additional Key Words and PhrasesSentence representation learning
- BERT
- contrastive learning
- Data Augmentation
ASJC Scopus subject areas
- Theoretical Computer Science
- Artificial Intelligence