Abstract

Recent years have witnessed increasing interests in developing interpretable models in NLP . Most existing models aim at identifying input features such as words or phrases important for model predictions. Neural models developed in NLP however often compose word semantics in a hierarchical manner. Interpretation by words or phrases only thus cannot faithfully explain model decisions. In this talk, I will present our recently proposed Hierarchical Interpretable Neural Text classifier, called Hint, which is able to identify the latent semantic factors and their compositions which contribute to the model’s final decisions. This is often beyond what word-level interpretations could capture. Experimental results on both review datasets and news datasets show that our proposed approach achieves text classification results on par with existing state-of-the-art text classifiers, and generates interpretations more faithful to model predictions and better understood by humans than other interpretable neural text classifiers.