Event Representation with Sequential, Semi-Supervised Discrete Variables
Mehdi Rezaee, Francis Ferraro · 2021
Within the context of event modeling and understanding, we propose a new method for neural sequence modeling that takes partially-observed sequences of discrete, external knowledge into account.We construct a sequential neural variational autoencoder, which uses Gumbel-Softmax reparametrization within a carefully defined encoder, to allow for successful backpropagation during training.The core idea is to allow semisupervised external discrete knowledge to guide, but not restrict, the variational latent parameters during training.Our experiments indicate that our approach not only outperforms multiple baselines and the state-of-the-art in narrative script induction, but also converges more quickly.