Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers
This work addresses the need for more interpretable AI models in text classification, offering an incremental improvement by reducing reliance on prior information or human annotations.
The authors tackled the problem of improving interpretability in neural text classifiers by proposing the variational word mask (VMASK) method to automatically learn task-specific important words, which enhanced both prediction accuracy and interpretability across three models and seven datasets.
To build an interpretable neural text classifier, most of the prior work has focused on designing inherently interpretable models or finding faithful explanations. A new line of work on improving model interpretability has just started, and many existing methods require either prior information or human annotations as additional inputs in training. To address this limitation, we propose the variational word mask (VMASK) method to automatically learn task-specific important words and reduce irrelevant information on classification, which ultimately improves the interpretability of model predictions. The proposed method is evaluated with three neural text classifiers (CNN, LSTM, and BERT) on seven benchmark text classification datasets. Experiments show the effectiveness of VMASK in improving both model prediction accuracy and interpretability.