HYPERBUG: A Scalable Natural Language Generation Approach

A scalable natural language generation (NLG) system called HYPERBUG 1 embedded in an agent-based, multimodal dialog system is presented. To motivate this presentation, several scenarios (including a domain shift) are identified where scalability in dialog systems is really needed, and NLG is argued to be one way of easing this desired scalability. Therefore the novel approach to hybrid NLG in the HYPERBUG system is described and the scalability of its parts and resources is investigated. Concluding with a few remarks to discourse generation, we argue that NLG can both contribute to and benefit from scalability in dialog systems.

[1]  Richard Power,et al.  Generation as a Solution to Its Own Problem , 1998, INLG.

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

[3]  Alexander I. Rudnicky,et al.  Stochastic Language Generation for Spoken Dialogue Systems , 2000 .

[4]  Werner Kießling,et al.  Design and implementation of COSIMA-a smart and speaking e-sales assistant , 2001, Proceedings Third International Workshop on Advanced Issues of E-Commerce and Web-Based Information Systems. WECWIS 2001.

[5]  Gertjan van Noord.  An overview of head-driven bottom-up generation , 1990 .

[6]  Michael Gamon,et al.  An Overview of Amalgam: A Machine-learned Generation Module , 2002, INLG.

[7]  Bernd Ludwig,et al.  A Natural Language Multi-Agent System for Controlling Model Trains , 2002 .

[8]  Amanda J. Stent,et al.  Dialogue Systems as Conversational Partners: Applying Conversation Acts Theory to Natural Language G , 2001 .

[9]  Tomek Strzalkowski,et al.  From Discourse to Logic , 1991 .

[10]  John A. Bateman,et al.  Enabling technology for multilingual natural language generation: the KPML development environment , 1997, Natural Language Engineering.

[11]  Wolfgang Wahlster,et al.  Verbmobil: Foundations of Speech-to-Speech Translation , 2000, Artificial Intelligence.

[12]  Emiel Krahmer,et al.  From data to speech: a general approach , 2001, Natural Language Engineering.

[13]  Kristiina Jokinen,et al.  Generating Responses and Explanations from RDF/XML and DAML+OIL , 2003 .

[14]  Günter Neumann,et al.  Applying Explanation-based Learning to Control and Speeding-up Natural Language Generation , 1997, ACL.