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.
@article{arxiv.2010.04361,
title = {Event Representation with Sequential, Semi-Supervised Discrete Variables},
author = {Mehdi Rezaee and Francis Ferraro},
journal= {arXiv preprint arXiv:2010.04361},
year = {2021}
}
Comments
In Proceedings of the 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021)