Self-supervised Regularization for Text Classification

Abstract

Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this problem, we propose SSL-Reg, a data-dependent regularization approach based on self-supervised learning (SSL). SSL is an unsupervised learning approach which defines auxiliary tasks on input data without using any human-provided labels and learns data representations by solving these auxiliary tasks. In SSL-Reg,  a supervised classification task and an unsupervised SSL task are performed simultaneously. The SSL task is unsupervised, which is defined purely on input texts without using any human-provided labels. Training  a model using an SSL task can prevent the model from being overfitted to a limited number of class labels in the classification task.

 Experiments on 17 text classification datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/UCSD-AI4H/SSReg