Abstract
In the preceding chapters, we have focused our attention on developing representations: domain model, SitSpec and SemSpec, lexicon entries, and lexical rules for deriving verb alternations. Now, we turn to the generation procedure that uses all the representations and derives verbalizations from SitSpecs. After reviewing our general approach to lexicalization, we will discuss the overall computational problem, give an overview of the generation architecture, and then discuss the individual steps in more detail. Then, we describe ‘MOOSE’, an implementation of a prototype realizing the architecture. The chapter is concluded by a summary and a list of open issues that would deserve some further attention but cannot be discussed here.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer Science+Business Media New York
About this chapter
Cite this chapter
Stede, M. (1999). A System Architecture for Multilingual Generation. In: Lexical Semantics and Knowledge Representation in Multilingual Text Generation. The Springer International Series in Engineering and Computer Science, vol 492. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5179-9_8
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5179-9_8
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7359-9
Online ISBN: 978-1-4615-5179-9
eBook Packages: Springer Book Archive