Generating dialogues for virtual agents using nested textual coherence relations

Abstract

This paper describes recent advances on the Text2Dialogue system we are currently developing. Our system enables automatic transformation of monological text into a dialogue. The dialogue is then "acted out" by virtual agents, using synthetic speech and gestures. In this paper, we focus on the monologue-to-dialogue transformation, and describe how it uses textual coherence relations to map text segments to query-answer pairs between an expert and a layman agent. By creating mapping rules for a few well-selected relations, we can produce coherent dialogues with proper assignment of turns for the speakers in a majority of cases. © 2008 Springer-Verlag Berlin Heidelberg.