Organizational issues arising from the integration of the lexicon and concept network in a text understanding system

Authors:
Padraig Cunningham;Tony Veale
Affiliations:
Hitachi Dublin Laboratory, Trinity College, Dublin 2, Ireland;Hitachi Dublin Laboratory, Trinity College, Dublin 2, Ireland
Venue:
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Year:
1991

Citing 2
Cited 1

Naive Semantics for Natural Language Understanding

Naive Semantics for Natural Language Understanding
Language As a Cognitive Process: Syntax

Language As a Cognitive Process: Syntax

Cross modal comprehension in ZARDOZ an English to sign-language translation system

INLG '94 Proceedings of the Seventh International Workshop on Natural Language Generation

Quantified Score

Hi-index	0.00

Visualization

Abstract

A knowledge based system for text understanding will incorporate both lexical and encyclopaedic information. The lexical information is the basis of the parsing process while the encyclopaedic information forms the target representation and is used in the knowledge acquisition process. This paper describes TWIG, a text understanding system where these two knowledge bases arc integrated into one representation. There is some theoretical justification for this and it has the advantage of reducing duplication of information in the system. This integration also has the advantage of making conceptual information available during the parsing process. Most of all this integration of diverse information forms a natural basis for a blackboard architecture.