Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced ...
Speech repairs occur often in spontaneous spoken dialogues. The ability to detect and correct those repairs is necessary for any spoken language system. We present a framework to ...
When building a new spoken dialogue application, large amounts of domain specific data are required. This paper addresses the issue of generating in-domain training data when litt...
This article introduces a bidirectional grammar generation system called feature structure-directed generation, developed for a dialogue translation system. The system utilizes ty...
While most dialogue systems restrict themselves to the adjustment of the propositional contents, our work concentrates on the generation of stylistic variations in order to improve...