论文标题
事件表示，具有连续的，半监督的离散变量
Event Representation with Sequential, Semi-Supervised Discrete Variables
论文作者
论文摘要
在事件建模和理解的背景下，我们为神经序列建模提出了一种新方法，该方法将部分观察到离散的外部知识的部分序列。我们构建了一个连续的神经变性自动编码器，该自动编码器在精心定义的编码器中使用Gumbel-Softmax Reparametrization，以便在训练过程中成功地反向传播。核心思想是允许半监督的外部离散知识指导但不限于训练期间的变异潜在参数。我们的实验表明，我们的方法不仅优于多个基线和叙事脚本诱导中最新的基线，而且更快地收敛。
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.
