Some issues in generation from a semantic representation

Authors:
Laurence Danlos
Affiliations:
Laboratoire d'Automatique Documentaire et Linguistique, CNRS, Yale University
Venue:
IJCAI'83 Proceedings of the Eighth international joint conference on Artificial intelligence - Volume 1
Year:
1983

Citing 3
Cited 0

Dynamic Memory: A Theory of Reminding and Learning in Computers and People

Dynamic Memory: A Theory of Reminding and Learning in Computers and People
Inside Computer Understanding: Five Programs Plus Miniatures

Inside Computer Understanding: Five Programs Plus Miniatures
Generating natural language text in response to questions about database structure

Generating natural language text in response to questions about database structure

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper investigates certain problems in the production of text from a languaqe-free representation and proposes a model of generation to treat these problems. We deal with generation of connected text. We show that the generation of a connected text cannot be reduced to a simple combination of phrases expressing sub-parts of the representation, but must be based on patterns of discourse structure reflecting the whole representation.