A Simple and Effective Usage of Self-supervised Contrastive Learning for Text Clustering
Haoxiang Shi, Cen Wang, Tetsuya Sakai · 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC) · 2021
Contrastive learning is a promising approach to unsupervised learning, as it inherits the advantages of well-studied deep models without a dedicated and complex model design. In this paper, based on bidirectional encoder representations from transformers, we propose self-supervised contrastive learning (SCL) as well as few-shot contrastive learning (FCL) with unsupervised data augmentation (UDA) for text clustering. SCL outperforms state-of-the-art unsupervised clustering approaches for short texts and those for long texts in terms of several clustering evaluation measures. FCL achieves performance close to supervised learning, and FCL with UDA further improves the performance for short texts.