For our lab meeting this week, Jetic will talk about another exciting paper from ICLR 2018. Here is the title and abstract of the paper. Title: Simulating Action Dynamics with Neural Process Networks
Abstract: Understanding procedural language requires anticipating the causal effects of actions, even when they are not explicitly stated. In this work, we introduce Neural Process Networks to understand procedural text through (neural) simulation of action dynamics. Our model complements existing memory architectures with dynamic entity tracking by explicitly modeling actions as state transformers. The model updates the states of the entities by executing learned action operators. Empirical results demonstrate that our proposed model can reason about the unstated causal effects of actions, allowing it to provide more accurate contextual information for understanding and generating procedural text, all while offering more interpretable internal representations than existing alternatives.
Wednesday, May 23rd, 10-11 AM, Location: TASC1 9408.