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

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

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

ℹī¸ Information

Expectation Propagation for POMDP Spoken Dialogue Models

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.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

In person only – Rooms GS4 & 5, Donald McIntyre Building, Faculty of Education, 184 Hills Road, Cambridge CB2 8PQ The Paykel Lectures CMS, MR2/MR3/MR4

Other talks

Group Work Coming soon Semiconductor-based neutron detector development at QMUL Title and abstract tba Genomic Medicine CPC Think Before you Speak: Next Gen LLMs with Global Reasoning and External Memory
 

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