NLP Highlights cover image

123 - Robust NLP, with Robin Jia

NLP Highlights

00:00

The Cost of Making Mistakes

The idea that training equals test actually is not true in the real world for a variety of reasons. There are often times when we just like really don't want systems to make mistakes. And so there's another whole line of work in what's called distributional robustness, which looks at how machine learning models behave on different demographic groups.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app