Do We Need Deep Generatin of Disfluent Dialogue?

Most Natural Language Generation systems focus on the production of perfectly written text for visual presentation. But as NLG tries to move into other areas of language production, such as speech in dialogue systems, it is not clear that approaches for traditional applications are best. Speech exhibits particular features like disfluency that are not found in written discourse. In this paper, we thus present an initial look at what may be necessary to allow current NLG systems to seamlessly make the transition to spoken language production