Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Norvig Revisits Chomsky on Statistical Language Learning

AI summary

Peter Norvig’s 2011 essay responds to Noam Chomsky’s objections to statistical language models and to Steven Pinker’s discussion of their success. Norvig argues that engineering success can be evidence, though not proof, of scientific success. Citing work by Fernando Pereira and his own experiment, he shows that statistically trained finite-state models can distinguish Chomsky’s grammatical sentence from its ungrammatical permutation.

In-depth insight

The essay examines a long-standing debate over the scientific significance of statistical models: whether fitting observed linguistic data provides understanding of language or merely approximates it.

At the Brains, Minds, and Machines symposium held during MIT's 150th birthday party in 2011, Technology Review reports that Prof. Noam Chomsky

derided researchers in machine learning who use purely statistical methods to produce behavior that mimics something in the world, but who don't try to understand the meaning of that behavior.

The transcript is now available, so let's quote Chomsky himself:

It's true there's been a lot of work on trying to apply statistical models to various linguistic problems. I think there have been some successes, but a lot of failures. There is a notion of success ... which I think is novel in the history of science. It interprets success as approximating unanalyzed data.

Image 1

Noam Chomsky

#Peter Norvig#Noam Chomsky#Steven Pinker#Fernando Pereira#Chris Manning#MIT#Google

Original · 38 min readRead the original
Group chat

No comments yet. Start the conversation.