AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
What the Human Brain Can Tell Us About NLP Models with Allyson Ettinger - #483
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Is There a Parallel to Convolutional Nornesisid?
The work that i was describing is less focused on examining the contents of the information incoted in individual layers, though there is even more recent work ta does more of that with these more recent models. But this work takes approach, a behavior based approach, that says, art, let's just look at the model's behaviors in the task for which it was optimized and say, ar this is the fairest possible way to check what the model learned. So yes, this was one of the the clearest finding. The models did pretty well on certain things, very well on certain things. Probably the starkest finding was with respect to negation. You have sentences like, a robin
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode