Design of a Generation Component for a Spoken Dialogue System

The paper describes the design of a generation component for a spoken dialogue system. After discussing three existing models of generation, a model based on new information focus is adopted. The design uses a pipeline architecture implemented in XML and Java. XSL templates are used to give a flexible form of template-based generation.

• Type: Conference
• Year: 2001
• Where: NLPRS
• Authors: Graham Wilcock, Kristiina Jokinen
• Keywords: Generation Component, Natural Language Processing, NLPRS 2001, Spoken Dialogue System, Template-based Generation