University of Cambridge > Talks.cam > Churchill CompSci Talks > Attention in sequence-to-sequence models

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Attention in sequence-to-sequence models

Download to your calendar using vCal

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

Sequence-to-sequence models are used to map sequential data from one domain to another, and are at the core of machine translation (MT) technologies such as Google Translate. In this talk, we build up the major milestones of neural machine translation. This talk will also introduce the attention mechanism, which forms the basis of virtually all state-of-the-art machine translation techniques we have today.

This talk is part of the Churchill CompSci Talks series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

McDonald Institute Seminar Room, Downing Site Theatre, Peterhouse Average on Sundays: 7186.25581395 kWh

Other talks

Afternoon Break Task performance predicts the substitution of feedforward by feedback drive in visual cortex Geometry and Generalization: The case of Grokking Tea and Coffee Break Director's Welcome When Programmes Disagree About Programmes: Code Poetry and the Problem of Programme–Programme Communication
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity