Improved Text Classification via Contrastive Adversarial Training
share
We propose a simple and general method to regularize the fine-tuning of Transformer-based encoders for text classification tasks. Specifically, during fine-tuning we generate adversarial examples by perturbing the word embeddings of the model and perform contrastive learning on clean and adversarial examples in order to teach the model to learn noise-invariant representations. By training on both clean and adversarial examples along with the additional contrastive objective, we observe consistent improvement over standard fine-tuning on clean examples. On several GLUE benchmark tasks, our fine-tuned BERT Large model outperforms BERT Large baseline by 1.7 fine-tuned RoBERTa Large improves over RoBERTa Large baseline by 1.3 additionally validate our method in different domains using three intent classification datasets, where our fine-tuned RoBERTa Large outperforms RoBERTa Large baseline by 1-2
READ FULL TEXT