Prior Knowledge-Guided Adversarial Training

AbstractWe introduce a simple yet effective Prior Knowledge-Guided ADVersarial Training (PKG-ADV) algorithm to improve adversarial training for natural language understanding. Our method simply utilizes task-specific label distribution to guide the training process. By prioritizing the use of prior knowledge of labels, we aim to generate more informative adversarial perturbations. We apply our model to several challenging temporal reasoning tasks. Our method enables a more reliable and controllable data training process than relying on randomized adversarial perturbation. Albeit simple, our method achieved significant improvements in these tasks. To facilitate further research, we will release the code and models.