SimCTC: A Simple Contrast Learning Method of Text Clustering (Student Abstract)

This paper presents SimCTC, a simple contrastive learning (CL) framework that greatly advances the state-of-the-art text clustering models. In pre-trained BERT model first maps input sequence to representation space, which is then followed by three different loss function heads: Clustering head, Instance-CL head and Cluster-CL head. Experimental results on multiple benchmark datasets demonstrate SimCTC remarkably outperforms 6 competitive methods with 1%-6% improvement Accuracy (ACC) 1%-4% Normalized Mutual Information (NMI). Moreover, our also show performance can be further improved setting an appropriate number of clusters in cluster-level objective.