Making grammar-based generation easier to deploy in dialogue systems

Abstract

We present a development pipeline and associated algorithms designed to make grammar-based generation easier to deploy in implemented dialogue systems. Our approach realizes a practical trade-off between the capabilities of a system's generation component and the authoring and maintenance burdens imposed on the generation content author for a deployed system. To evaluate our approach, we performed a human rating study with system builders who work on a common large-scale spoken dialogue system. Our results demonstrate the viability of our approach and illustrate authoring/performance trade-offs between hand-authored text, our grammar-based approach, and a competing shallow statistical NLG technique. © 2008 Association for Computational Linguistics.