PUB - Publikationen an der Universität Bielefeld

Expressing spatial information with iconic gestures is abundant in human communication and requires to transform information about a referent into resembling gestural form. This task is challenging as the mapping is likely to be determined by the visuo-spatial features of the referent, the overall discourse context or concomitant speech, and its outcome varies considerably across different speakers. We present work that applies machine learning to an extensive data corpus in order to model the generation of iconic gestures with Bayesian decision networks. Modeling results from a prototype implementation are presented and evaluated with regard to the performance of different structure learning algorithms.