University of Cambridge > > Machine Learning Reading Group @ CUED > Expectation Propagation for POMDP Spoken Dialogue Models

Expectation Propagation for POMDP Spoken Dialogue Models

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

If you have a question about this talk, please contact David Duvenaud.

This talk discusses the application of the partially observable Markov decision process (POMDP) to spoken dialogue and how the model can be used to build a system that interacts with users via speech. The focus of the talk will be on the use of the expectation propagation (EP) with various optimisations to efficiently learn parameters of the POMDP model, although an overview of the full system will also be provided. Interestingly, the EP algorithm provides a way to learn models of how humans behave in a dialogue with only a noisy estimate of the semantics of their utterance. No human annotations of either the state of the dialogue or the semantics are required. An evaluation of the learning algorithm as well as comparisons of the POMDP approach with other techniques will be presented.

This talk is part of the Machine Learning Reading Group @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity