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

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

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

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.

Other lists

Paediatric Endocrinology & Diabetes Postgraduate Seminar series The Globalization of Music: Origins, Development, & Consequences, c1500–1815 Type the title of a new list here

Other talks

BP KEYNOTE LECTURE: Importance of C-O Bond Activation for CO2/COUtilization - An Approach to Energy Conversion and Storage Finding the past: Medieval Coin Finds at the Fitzwilliam Museum Train and equip: British overseas security assistance in the Cold War Global South Panel Discussion: Climate Change Is Now Kolmogorov Complexity and Gödel’s Incompleteness Theorems Cyclic Peptides: Building Blocks for Supramolecular Designs “Modulating Tregs in Cancer and Autoimmunity” Refugees and Migration 'Walking through Language – Building Memory Palaces in Virtual Reality' Investigating the Functional Anatomy of Motion Processing Pathways in the Human Brain
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity