What Does a TextCNN Learn?
This work addresses the black-box nature of neural networks for researchers in NLP, but it is incremental as it builds on existing visualization methods from image CNNs.
The paper tackled the problem of interpreting TextCNN models by analyzing what convolutional kernels learn on two NLP datasets, focusing on kernel functions and correlations.
TextCNN, the convolutional neural network for text, is a useful deep learning algorithm for sentence classification tasks such as sentiment analysis and question classification. However, neural networks have long been known as black boxes because interpreting them is a challenging task. Researchers have developed several tools to understand a CNN for image classification by deep visualization, but research about deep TextCNNs is still insufficient. In this paper, we are trying to understand what a TextCNN learns on two classical NLP datasets. Our work focuses on functions of different convolutional kernels and correlations between convolutional kernels.