Overgeneration and ranking for spoken dialogue systems

Abstract

We describe an implemented generator for a spoken dialogue system that follows the 'overgeneration and ranking' approach. We find that overgeneration based on bottom-up chart generation is wellsuited to a) model phenomena such as alignment and variation in dialogue, and b) address robustness issues in the face of imperfect generation input. We report evaluation results of a first user study involving 20 subjects. © 2006 Association for Computational Linguistics.