Equipment Simulation for Language Understanding, Revision

Abstract

This paper considers the task of analyzing reports regarding the failure, diagnosis and repair of equipment. The authors show that a general knowledge of equipment is not sufficient for a full understanding of such reports. As an alternative, they describe a system - PROTEUS (Prototype Text Understanding System) - which relies on a detailed simulation model to support language understanding. They describe the structure of the model and emphasize features specifically required for language understanding. It is shown how this model can be used in analyzing and determining the referents for complex noun phrases. The authors point out the importance of identifying the implicit temporal and causal relations in the text and show how the simulation capabilities of the model support this task. Finally, it is indicated how PROTEUS may be extended to facilitate the entry of new equipment models and to assist in equipment diagnosis.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 20, 1988
Accession Number
ADA203608

Entities

People

  • Ralph David Grishman
  • Tomasz Ksiezyk

Organizations

  • New York University

Tags

Communities of Interest

  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Air Compressors
  • Air Pressure
  • Artificial Intelligence
  • Causal Reasoning
  • Compressors
  • Computer Science
  • Couplings
  • Expert Systems
  • Gas Turbines
  • High Pressure
  • Language
  • Measuring Instruments
  • Natural Language Understanding
  • Natural Languages
  • Reasoning
  • Simulations
  • Time Intervals

Readers

  • Artificial Intelligence
  • Computational Linguistics
  • Systems Analysis and Design