A stochastic model of human-machine interaction for learning dialog strategies

@article{Levin2000ASM,
  title={A stochastic model of human-machine interaction for learning dialog strategies},
  author={E. Levin and R. Pieraccini and W. Eckert},
  journal={IEEE Trans. Speech Audio Process.},
  year={2000},
  volume={8},
  pages={11-23}
}
We propose a quantitative model for dialog systems that can be used for learning the dialog strategy. We claim that the problem of dialog design can be formalized as an optimization problem with an objective function reflecting different dialog dimensions relevant for a given application. We also show that any dialog system can be formally described as a sequential decision process in terms of its state space, action set, and strategy. With additional assumptions about the state transition… Expand
558 Citations
Gaussian Processes for POMDP-Based Dialogue Manager Optimization
  • Milica Gasic, S. Young
  • Computer Science
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2014
  • 114
  • PDF
A Quality-Focused Spoken Dialog System With Reinforcement Learning And Simulated User
  • 1
  • Highly Influenced
  • PDF
Learning of stochastic dialog models through a dialog simulation technique
  • 6
  • PDF
The Hidden Agenda User Simulation Model
  • 76
  • PDF
A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management Through Dynamic Stochastic State Evolution
  • Ji Wu, M. Li, C. Lee
  • Computer Science
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2015
  • 13
  • PDF
Optimizing Dialogue Strategy Learning Using Learning Automata
Planning and Acting under Uncertainty: A New Model for Spoken Dialogue System
  • 53
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 44 REFERENCES
Using Markov decision process for learning dialogue strategies
  • E. Levin, R. Pieraccini, W. Eckert
  • Computer Science
  • Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)
  • 1998
  • 178
  • PDF
Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms
  • 206
  • PDF
The TRAINS project: a case study in building a conversational planning agent
  • 378
Dialogue strategies guiding users to their communicative goals
  • 46
  • PDF
Reinforcement Learning: A Survey
  • 6,779
  • PDF
How may I help you?
  • 621
  • PDF
User modeling for spoken dialogue system evaluation
  • 204
...
1
2
3
4
5
...