Abstract
Natural Language Generation (NLG) systems are increasingly becoming available as “market-ready” products, mainly due to the now-removed boundary between shallow and deep generation and the emergence of hybrid systems as a de-facto standard. In this paper, we present Hyperbug, a novel approach towards hybrid NLG, coupling shallow and deep processing not only with respect to the resources used for parsing and generation, but also on the architectural level to increase the generative power of the shallow generation branch and the processing efficiency of the whole generation system. The architecture is discussed both in theory and in practice, using a comprehensive example spanning the complete output part of our dialog system.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Oh, A., Rudnicky, A.: Stochastic language generation for spoken dialogue systems. In: Proc. ANLP/NAACL 2000 Workshop on Conversational Systems, Seattle (2000)
Corston-Oliver, S.: An overview of amalgam: A machine-learned generation module. In: Proc. INLG 2002, New York (2002)
Wilcock, G.: Integrating natural language generation with xml web technology. In: Proc. EACL 2003 Demo Sessions, Budapest (2003)
Busemann, S.: A shallow formalism for defining personalized text. In: Proc. KI 1998 Workshop, Bremen (1998)
Wahlster, W.: Verbmobil: Foundations of Speech-to-Speech Translation, Berlin, Heidelberg, New York (2000)
Kamp, H., Reyle, U.: From Disourse To Logic, Dordrecht (1993)
van Noord, G.: An overview of head-driven bottom-up generation. In: Dale, R., Mellish, C., Zock, M. (eds.) Current Research in Natural Language Generation, Berlin, Heidelberg, New York (1990)
Ludwig, B.: Dialogue understanding in dynamic domains. In: Kühnlein, P., Rieser, H., Zevat, H. (eds.) Perspectives on Dialogue in the New Millennium, John Benjamins Publishing Company, Amsterdam (2003)
Stent, A.J.: Dialogue Systems as Conversational Partners: Applying Conversation Acts Theory to Natural Language Generation for Task-Oriented Mixed-Initiative Spoken Dialogue. PhD thesis, University of Massachusetts Amherst (2001)
Neumann, G.: Applying explanation-based learning to control and speeding-up natural language generation. In: Proc. ACL/EACL 1997, Madrid (1997)
Möller, R., Haarslev, V.: Description logics for the semantic web: Racer as a basis for building agent systems. KI - Zeitschrift für Künstliche Intelligenz (special issue on Semantic Web), 3 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Klarner, M. (2004). Hybrid NLG in a Generic Dialog System. In: Belz, A., Evans, R., Piwek, P. (eds) Natural Language Generation. INLG 2004. Lecture Notes in Computer Science(), vol 3123. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27823-8_22
Download citation
DOI: https://doi.org/10.1007/978-3-540-27823-8_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22340-5
Online ISBN: 978-3-540-27823-8
eBook Packages: Springer Book Archive