Saliency Learning: Teaching the Model Where to Pay Attention
This addresses the issue of model interpretability and trust in NLP, offering a method to enhance reliability rather than just providing explanations.
The paper tackles the problem of improving model reliability by teaching models to make predictions for the right reasons through explanation training, resulting in more reliable predictions and better performance compared to traditionally trained models.
Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches to provide insights toward the model's behaviour and predictions, which are helpful for assessing the reliability of the model's predictions. However, such methods do not improve the model's reliability. In this paper, we aim to teach the model to make the right prediction for the right reason by providing explanation training and ensuring the alignment of the model's explanation with the ground truth explanation. Our experimental results on multiple tasks and datasets demonstrate the effectiveness of the proposed method, which produces more reliable predictions while delivering better results compared to traditionally trained models.