Dialogue act recognition with Bayesian networks for Dutch dialogues
Simon Keizer, Rieks op den Akker, Anton Nijholt · 2002
This paper presents work on using Bayesian networks for the dialogue act recognition module of a dialogue system for Dutch dialogues. The Bayesian networks can be constructed from the data in an annotated dialogue corpus. For two series of experiments - using different corpora but the same annotation scheme - recognition results are presented and evaluated.