In this episode, Shi Feng joins us to discuss his recent work on identifying pathological behaviors of neural models for NLP tasks. Shi uses input word gradients to identify the least important word for a model's prediction, and iteratively removes that word until the model prediction changes. The reduced inputs tend to be significantly smaller than the original inputs, e.g., 2.3 words instead of 11.5 in the original in SQuAD, on average. We discuss possible interpretations of these results, and a proposed method for mitigating these pathologies. 

Shi Feng's homepage: http://users.umiacs.umd.edu/~shifeng/
Paper: https://www.semanticscholar.org/paper/Pathologies-of-Neural-Models-Make-Interpretation-Feng-Wallace/8e141b5cb01c88b315c9a94dc97e50738cc7370d
Joint work with Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez and Jordan Boyd-Graber

87 - Pathologies of Neural Models Make Interpretation Difficult, with Shi Feng

**The podcast is currently on hiatus. For more active NLP content, check out the Holistic Intelligence Podcast linked below.**

Welcome to the NLP highlights podcast, where we invite researchers to talk about their work in various areas in natural language processing. All views expressed belong to the hosts/guests, and do not represent their employers.

87 - Pathologies of Neural Models Make Interpretation Difficult, with Shi Feng

NLP Highlights