• Publications
  • Influence
The Second Dialog State Tracking Challenge
TLDR
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. Expand
Partially observable Markov decision processes for spoken dialog systems
TLDR
This paper cast a spoken dialog system as a partially observable Markov decision process (POMDP) and shows how this formulation unifies and extends existing techniques to form a single principled framework. Expand
POMDP-Based Statistical Spoken Dialog Systems: A Review
TLDR
This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems. Expand
The Dialog State Tracking Challenge
TLDR
The dialog state tracking challenge seeks to address this by providing a heterogeneous corpus of 15K human-computer dialogs in a standard format, along with a suite of 11 evaluation metrics, and shows that the suite of performance metrics cluster into 4 natural groups. Expand
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
TLDR
This work introduces Hybrid Code Networks (HCNs), which combine an RNN with domain-specific knowledge encoded as software and system action templates, and considerably reduce the amount of training data required, while retaining the key benefit of inferring a latent representation of dialog state. Expand
The third Dialog State Tracking Challenge
TLDR
Results from the third Dialog State Tracking Challenge are presented, a research community challenge task based on a corpus of annotated logs of human-computer dialogs, with a blind test set evaluation that studied the ability of trackers to generalize to new entities - i.e. new slots and values not present in the training data. Expand
The Dialog State Tracking Challenge Series: A Review
TLDR
This paper reviews this research area, covering both the challenge tasks themselves and summarizing the work they have enabled, including the incorporation of the speech recognition results directly into the dialog state tracker. Expand
The Fourth Dialog State Tracking Challenge
TLDR
This edition of the fourth dialog state tracking challenge again focused on human-human dialogs, but introduced the task of cross-lingual adaptation of trackers, which received a total of 32 entries from 9 research groups. Expand
Recent advances in deep learning for speech research at Microsoft
TLDR
An overview of the work by Microsoft speech researchers since 2009 is provided, focusing on more recent advances which shed light to the basic capabilities and limitations of the current deep learning technology. Expand
Factored partially observable Markov decision processes for dialogue management
TLDR
This work shows how a dialogue model can be represented as a factored Partially Observable Markov Decision Process (POMDP), and shows howA dialogue manager produced with a POMDP optimisation technique may be directly compared to a handcrafted dialogue manager. Expand
...
1
2
3
4
5
...