In which uncertainty in natural language dialogue is introduced as the central problem in the research described in this thesis. The idea of using of Bayesian networks is hypothesised as a possible solution to this problem. Dialogue acts are presented as the central notion in our approach to dialogue modelling and the task of recognising dialogue act types as the central topic in the experiments.
|Award date||3 Sep 2003|
|Place of Publication||Enschede, the Netherlands|
|Publication status||Published - 3 Sep 2003|