Employing Knowledge Resources in a New Text Planner Architecture

Abstract

We describe in this paper a new text planner that has been designed to address several problems we had encountered in previous systems. Motivating factors include a clearer and more explicit separation of the declarative and procedural knowledge used in a text generation systems as well as the identification of the distinct types of knowledge necessary to generate coherent discourse, such as communicative goals, text types, schemas, discourse structure relations, and theme development patterns. This knowledge is encoded as separate resources and integrated under a flexible planning process that draws from appropriate resources whatever knowledge is needed to construct a text. We describe the resources and the planning process and illustrate the ideas with an example. Natural language generation, Declarative architecture, Textual resources, Text planner.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1993
Accession Number
ADA269669

Entities

People

  • Cecile L. Paris
  • Eduard Hovy
  • Elisabeth A. Maier
  • Julia Lavid
  • Vibhu O. Mittal

Organizations

  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Classification
  • Cognitive Science
  • Computational Linguistics
  • Computer Science
  • Contracts
  • Demographic Cohorts
  • Domestic
  • Grammars
  • Hierarchies
  • Information Science
  • Instructions
  • Language
  • Linguistics
  • Materials
  • Natural Languages
  • Taxonomy

Readers

  • Computational Linguistics
  • Joint Military Operations and Doctrine.
  • Theoretical Analysis.