AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Common Sense Reasoning in NLP with Vered Shwartz - #461
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
How to Estimate Conditional Probability From Language Models
There's no way to measure possibility of statements to date. I am looking at better ways to estimate this from language models, because one of the issues with this is that it factors in other things,. You can divide it by the number of words. But then now these models work at the sub word level so sometimes if you have a rare word, it's going to split it to multiple token. If you have a short word or a word that is very common, you have all these issues that are not about what is more plausible in the world.
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