Real-Time Stochastic Language Generation for Dialogue Systems
Nathanael Chambers · 2005
Until recently, surface generation in dialogue systems has served the purpose of simply pro-viding a backend to other areas of research. The generation component of such systems usually consists of templates and canned text, providing inflexible, unnatural output. To make matters worse, the resources are typi-cally specific to the domain in question and not portable to new tasks. In contrast, domain-independent generation systems typically re-quire large grammars, full lexicons, complex collocational information, and much more. Furthermore, these frameworks have primar-ily been applied to text applications and it is not clear that the same systems could perform well in a dialogue application. This paper explores the feasibility of adapting such sys-tems to create a domain-independent genera-tion component useful for dialogue systems. It utilizes the domain independent semantic form of The Rochester Interactive Planning System (TRIPS) with a domain independent stochas-tic surface generation module. We show that a written text language model can be used to predict dialogue utterances from an over-generated word forest. We also present results from a human oriented evaluation in an emer-gency planning domain. 1