A generative attentional neural network model for dialogue act classification

Abstract

We propose a novel generative neural network architecture for Dialogue Act classification. Building upon the Recurrent Neural Network framework, our model incorporates a new attentional technique and a label-to-label connection for sequence learning, akin to Hidden Markov Models. Our experiments show that both of these innovations enable our model to outperform strong baselines for dialogue-act classification on the MapTask and Switchboard corpora. In addition, we analyse empirically the effectiveness of each of these innovations.