B
Blaise Thomson
Researcher at University of Cambridge
Publications - 52
Citations - 4979
Blaise Thomson is an academic researcher from University of Cambridge. The author has contributed to research in topics: Partially observable Markov decision process & Dialog box. The author has an hindex of 29, co-authored 52 publications receiving 4513 citations.
Papers
More filters
Journal ArticleDOI
POMDP-Based Statistical Spoken Dialog Systems: A Review
TL;DR: This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.
Proceedings ArticleDOI
The Second Dialog State Tracking Challenge
TL;DR: The results suggest that while large improvements on a competitive baseline are possible, trackers are still prone to degradation in mismatched conditions and ensemble learning demonstrates the most accurate tracking can be achieved by combining multiple trackers.
Proceedings ArticleDOI
Word-Based Dialog State Tracking with Recurrent Neural Networks
TL;DR: A new wordbased tracking method which maps directly from the speech recognition results to the dialog state without using an explicit semantic decoder is presented, based on a recurrent neural network structure which is capable of generalising to unseen dialog state hypotheses, and which requires very little feature engineering.
Proceedings ArticleDOI
Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System
TL;DR: This paper investigates the problem of bootstrapping a statistical dialogue manager without access to training data and proposes a new probabilistic agenda-based method for simulating user behaviour and shows that the learned policy was highly competitive, with task completion rates above 90%.
Journal ArticleDOI
Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems
Blaise Thomson,Steve Young +1 more
TL;DR: The Bayesian update of dialogue state framework was shown to be a feasible and effective approach to building real-world POMDP-based dialogue systems and a method for learning in spoken dialogue systems which uses a component-based policy with the episodic Natural Actor Critic algorithm.