SARA: an experiment in natural language processing with event-type knowledge representation

  • Authors:

  • Mark Armstrong;Carol A. Perkins;Glenn Smith

  • Affiliations:

  • N.C. State;N.C. State;N.C. State

  • Venue:
  • ACM-SE 16 Proceedings of the 16th annual Southeast regional conference
  • Year:
  • 1978

Quantified Score

Hi-index 0.00

Visualization

Abstract

Recent development in natural language processing have shown that the inclusion of world knowledge in a processing system will inhance the understanding capabilities of the computer. This paper describes a system, called SARA, that implements some of the recent techniques used to organize the computers view of the world. An ability to understand events is demonstrated by generating a paraphrase of a short input story. The systems limitations are discussed as a function of the unsolved problems in designing a universal scheme for an adaquate knowledge representation.