The Sentience Institute Podcast cover image

Raphaël Millière on large language models

The Sentience Institute Podcast

00:00

The Power of Attention in Language Models

In NLP, words are represented as vectors in a high dimensional vector space. Vectors can capture some aspect of the meaning and potentially syntactic roles of words. And then you can look at the distance between two word vectors to give you some insight into the semantic distance between two words. So people decided that working on these word and meaning models could be very useful for machine learning.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app