University of Cambridge > Talks.cam > Churchill CompSci Talks > Google's Transformer: A Novelty to Language Understanding

Google's Transformer: A Novelty to Language Understanding

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Matthew Ireland.

Machine translation is one of the main tasks that Natural Language Processing, especially Language Understanding, is trying to solve. The approach to machine translation has been the same for the past years: recurrent neural network architectures, sometimes coupled with attention mechanisms. Google now has come up with a new approach, the Transformer, that promises to improve machine translation by only using a self attention mechanism. If you have no idea what I am talking about, want to find out more, are bored on a Wednesday evening or you are forced to come to the talks, stay tuned for this presentation. I promise I’ll do my best.

This talk is part of the Churchill CompSci Talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity