54 - Simulating Action Dynamics with Neural Process Networks, with Antoine Bosselut

NLP Highlights

English - March 26, 2018 19:00 - 36 minutes - 32.9 MB - ★★★★★ - 22 ratings
Science Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed

Previous Episode: 53 - Classical Structured Prediction Losses for Sequence to Sequence Learning, with Sergey and Myle

Next Episode: 55 - Matchbox: Dispatch-driven autobatching for imperative deep learning, with James Bradbury

ICLR 2018 paper, by Antoine Bosselut, Omer Levy, Ari Holtzman, Corin Ennis, Dieter Fox, and Yejin Choi.

This is not your standard NLP task. This work tries to predict which entities change state over the course of a recipe (e.g., ingredients get combined into a batter, so entities merge, and then the batter gets baked, changing location, temperature, and "cookedness"). We talk to Antoine about the work, getting into details about how the data was collected, how the model works, and what some possible future directions are.

https://www.semanticscholar.org/paper/Simulating-Action-Dynamics-with-Neural-Process-Bosselut-Levy/dc01c9401d1caab7f5e6d2f1280f5815f6919977