| Enabling Resource Sharing in Language Generation: An Abstract Reference Architecture
May 2000
Christine D. Doran, The MITRE Corporation
L. Cahill, University of Brighton
R. Evans, University of Brighton
R. Kibble, University of Brighton
C. Mellish, University of Edinburgh
D. Paiva, University of Brighton
M. Reape, University of Edinburgh
D. Scott, University of Brighton
N. Tipper, University of Brighton
ABSTRACT
The RAGS project aims to develop a reference architecture for natural
language generation, to facilitate modular development of NLG systams
as well as evaluation of components, systems and algorithms. This paper
gives an overview of the proposed framework, describing an abstract
data model with five levels of representation: Conceptual, Semantic,
Rhetorical, Document and Syntactic. We report on a re-implementation
of an existing system using the RAGS data model.
» Download Paper [PDF, 88KB]
Additional Search Keywords
N/A
|
