论文信息 - Design of a Generation Component for a Spoken Dialogue System

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.

Kristiina Jokinen | Graham Wilcock | G. Wilcock | Kristiina Jokinen

[1] Ehud Reiter,et al. Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[2] Lena Santamarta. Output Generation in a Spoken Dialogue System , 1999 .

[3] Graham Wilcock. Approaches to Surface Realization with HPSG , 1998, INLG.

[4] John Carroll,et al. An Efficient Chart Generator for (Semi-)Lexicalist Grammars , 2001 .

[5] Markku Turunen,et al. Jaspis - a framework for multilingual adaptive speech applications , 2000, INTERSPEECH.

[6] Mariët Theune,et al. From data to speech : language generation in context , 2000 .

[7] Tilman Becker,et al. "May I Speak Freely?" : between templates and free choice in natural language generation ; workshop at the 23rd German Annual Conference for Artificial Intelligence (KI'99), Bonn14.-15. September 1999 , 1999 .

[8] Graham Wilcock,et al. Pipelines, Templates and Transformations: XML for Natural Language Generation , 2001 .

[9] Kristiina Jokinen,et al. Confidence-Based Adaptivity in Response Generation for a Spoken Dialogue System , 2001, SIGDIAL Workshop.

[10] Mauri Kaipainen,et al. Self-Organizing Dialogue Management , 2001 .

[11] Hideki Tanaka,et al. Planning Dialogue Contributions With New Information , 1998, INLG.

[12] D. B. Davis,et al. Sun Microsystems Inc. , 1993 .