A conversation acts model for generating spoken dialogue contributions

In this paper, we describe a generation system for spoken dialogue that not only produces coherent, informative and responsive dialogue contributions, but also explicitly models human styles of interaction. This generation system is based on conversation acts theory. It has been implemented in the TRIPS spoken dialogue system, and includes components that plan content, perform surface generation for different modalities, and coordinate output production. We discuss our implementation, and describe an evaluation of the generation output.