Projects per year
Abstract
Sentence representation learning is a crucial task in natural language processing (NLP), as the quality of learned representations directly influences downstream tasks, such as sentence classification and sentiment analysis. Transformer-based pretrained language models (PLMs) such as bidirectional encoder representations from transformers (BERT) have been extensively applied to various NLP 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 finetune BERT-like PLMs to learn sentence representations. But no systematic review of contrastive learning models for sentence representations has been conducted. To fill this gap, this paper 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 |
---|---|
Journal | ACM Transactions on Intelligent Systems and Technology |
DOIs | |
Publication status | E-pub ahead of print - 2 May 2023 |
Bibliographical note
The research presented in this article has been supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (UGC/FDS16/E01/19) and Lam Woo Research Fund (LWP20019) of Lingnan University.Fingerprint
Dive into the research topics of 'Contrastive Learning Models for Sentence Representations'. Together they form a unique fingerprint.Projects
- 1 Active
-
Data Augmentation Techniques for Contrastive Sentence Representation Learning
XIE, H., LI, Z. & WONG, T. L.
1/08/22 → 31/07/24
Project: Grant Research