|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Statistical Spoken Dialogue Systems and the Challenges for Machine Learning
If you have a question about this talk, please contact Anton Ragni.
This talk will review the principal components of a spoken dialogue system and then discuss the opportunities for applying machine learning for building robust high performance open-domain systems. The talk will be illustrated by recent work at Cambridge University using machine learning for belief tracking, reward estimation, multi-domain policy learning and natural language generation. The talk will conclude by discussing some of the key challenges in scaling these solutions to work in practical systems.
This talk is part of the CUED Speech Group Seminars series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsCaMedia (Media and Creative Industries Society) Mental Health Week 2013 SPS Society
Other talksProfessor Alain Vanderplasschen: Conserved fever pathways across vertebrates: a herpesvirus delays fish behavioural fever through expression of a decoy Tnfα receptor Dirty words a historyof swearing and abuse in Tamil Ritual, Community, and Conflict Dr Sarah Teichmann: Understanding Cellular Heterogeneity The typical and atypical development of the human social brain How ice sheets collapse: a lesson from the Laurentide Ice Sheet