JAIR
2002
13 years 11 months ago
2002
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a di...
NAACL
2007
14 years 1 months ago
2007
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 simula...