User Simulation in Dialogue Systems Using Inverse Reinforcement Learning.
Senthilkumar ChandramohanMatthieu GeistFabrice LefèvreOlivier PietquinPublished in: INTERSPEECH (2011)
Keyphrases
- dialogue system
- spoken dialogue systems
- mixed initiative
- inverse reinforcement learning
- human users
- natural language
- user interaction
- user model
- partially observable environments
- cooperative
- bayesian nonparametric
- preference elicitation
- artificial intelligence
- gaussian process
- markov decision processes
- domain independent
- probabilistic model