21 - Contextual Explanation Networks, with Maruan Al-Shedivat
https://arxiv.org/abs/1705.10301 Maruan, Avinava…
NLP Highlights · Allen Institute for Artificial Intelligence
June 15, 201719m 13s
Audio is streamed directly from the publisher (podtrac.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
https://arxiv.org/abs/1705.10301
Maruan, Avinava Dubey and Eric Xing essentially put the post-hoc decision boundary explanations from the "Why Should I Trust You?" paper* as a core component of a predictive model. Maruan comes on to tell us about it.
* https://www.semanticscholar.org/paper/Why-Should-I-Trust-You-Explaining-the-Predictions-Ribeiro-Singh/5636dca44384240ce9aff2b10b78458cd3c2f450