AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
Advancing NLP with Project Debater w/ Noam Slonim - #495
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
How to Evaluate a Debate?
When we have violated in individual components, we use the standard palatime of superficial learning. We need to be very rigorous in terms of benchmak data development and things like that. But when you talk about evaluating the system as a whole, this is a different story. It's not that clear how to called the system. Its debates can last for, in our format, can last for 25 minutes. The average score of human debaters was around four. And I think the system came close to expert level on some topics.
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