SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training
Hui Chen, Wei Han, Soujanya Poria · 2022
Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning.This work presents a Simple instance-Adaptive self-Training method (SAT) for semisupervised text classification.SAT first generates two augmented views for each unlabeled data and then trains a meta-learner to automatically identify the relative strength of augmentations based on the similarity between the original view and the augmented views.The weakly-augmented view is fed to the model to produce a pseudo-label and the stronglyaugmented view is used to train the model to predict the same pseudo-label.We conducted extensive experiments and analyses on three text classification datasets and found that with varying sizes of labeled training data, SAT consistently shows competitive performance compared to existing semi-supervised learning methods.