4min chapter

The Gradient: Perspectives on AI cover image

Yejin Choi: Teaching Machines Common Sense and Morality

The Gradient: Perspectives on AI

CHAPTER

How to Improve Predict Middle Sentence by Reading Left and Right Sentences

I like that a lot. So let's actually talk about some of these models that can do this kind of common sense reasoning that you've worked on. In particular, i think i've looked at two of them, delorian and comon. Why do they improve over existing pre trained language models to better perform common sense inference? Ye, so delorian is inference tam algoridm. It's not a mutian learning method, perse but more like, once you have learn nd model, especially language model, can you then use it off the shelf through a better agoritm so that the model can do things that originallythe model was not trained for.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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