Event Representation with Sequential, Semi-Supervised Discrete Variables
This addresses event modeling for AI applications, but it is incremental as it builds on existing variational autoencoder methods.
The paper tackled the problem of neural sequence modeling for event understanding by incorporating partially-observed discrete external knowledge, resulting in outperforming baselines and state-of-the-art in narrative script induction with faster convergence.
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 semi-supervised 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.