Event Representation with Sequential, Semi-Supervised Discrete Variables
Links to Fileshttps://arxiv.org/abs/2010.04361
MetadataShow full item record
Type of Work10 pages
journal articles preprints
Citation of Original PublicationRezaee, Mehdi; Ferraro, Francis; Event Representation with Sequential, Semi-Supervised Discrete Variables; Machine Learning (2020); https://arxiv.org/abs/2010.04361
RightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
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 that uses a carefully defined encoder, and Gumbel-Softmax reparametrization, to allow for successful backpropagation during training. We show that our approach outperforms multiple baselines and the state-of-the-art in narrative script induction on multiple event modeling tasks. We demonstrate that our approach converges more quickly.