AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Common Sense Reasoning in NLP with Vered Shwartz - #461
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Using Neural Language Models to Detect Causes and Effects
We wanted to do something a our inspiration was that when we reason about a sentence like this, we have this background knowledge that is impleed in this context. And then we thought that it might be beneficial toa make this knowledge explicit, and just have this as an explicit text given to the model. So we develop this, a model that we call self talk that just self asks question like, what is the purpose of vegetables? And then generates the answer and then answers it with something like, vegetables are full of vitamins. This is all based on neural language models. So the model generates the questions and the answers, and then using all these new facts to help it answer the main
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