Statistical user simulation with a hidden agenda

@inproceedings{Schatzmann2007StatisticalUS,
  title={Statistical user simulation with a hidden agenda},
  author={Jost Schatzmann and Blaise Thomson and Steve J. Young},
  year={2007}
}
Recent work in the area of probabilistic user simulation for training statistical dialogue managers has investigated a new agenda-based user model and presented preliminary experiments with a handcrafted model parameter set. Training the model on dialogue data is an important next step, but non-trivial since the user agenda states are not observable in data and the space of possible states and state transitions is intractably large. This paper presents a summary-space mapping which greatly… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 47 CITATIONS

Data-Driven Methods for Adaptive Spoken Dialogue Systems

  • Springer New York
  • 2012
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Metrics for the evaluation of user simulations

VIEW 13 EXCERPTS
HIGHLY INFLUENCED

A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Generative Goal-Driven User Simulation for Dialog Management

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Analysis of a new simulation approach to dialog system evaluation

VIEW 6 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Data-driven user simulation for automated evaluation of spoken dialog systems

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

The Hidden Information State Approach to Dialog Management

  • 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
  • 2007
VIEW 6 EXCERPTS

Scaling up POMDPs for Dialog Management: The ``Summary POMDP'' Method

  • IEEE Workshop on Automatic Speech Recognition and Understanding, 2005.
  • 2005
VIEW 1 EXCERPT