4min chapter

Machine Learning Street Talk (MLST) cover image

#103 - Prof. Edward Grefenstette - Language, Semantics, Philosophy

Machine Learning Street Talk (MLST)

CHAPTER

The Contribution of Code in the Training of Large Scale Language Models

There's evidence that including code in the training of large scale language models helps them not only be better modellers of code, but also of natural language. Do you agree with Montague that our language is a formal language? Well, I've studied a lot of the last part of my PhD working on some sort of extension of a Montegoian semantics. And so they wanted to build a compositional distributional picture of language which would use this syntactic structure to decide how to produce vectors of larger units of text. This was all powered by complex mathematics, categorical framework for modeling quantum information flow and thought, hey, let's solve language with it.

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