Structural Domain Modeling for Understanding Equipment Failure Messages.

Abstract

The goal of natural language understanding computer systems is to analyze and make use of the information contained in English or other natural language discourse. Understanding texts that discuss complex pieces of equipment such as Navy equipment failure reports (CASREPs), requires the possession not only of general knowledge about the types of objects and predicates in the domain, but also detailed knowledge about the particular equipment in question. This more expert level of knowledge is needed to deference the names and descriptions of equipment referred to in the text, and to infer their causal relations and operational states when these are only implicitly expressed by the message writer. Knowing the structural configuration of the equipment is useful in both tasks, and a structural domain model can be extracted readily from equipment manuals and their accompanying parts lists, thus easing the "knowledge acquisition bottleneck" problem and making practical applications more feasible.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 12, 1995
Accession Number
ADA294035

Entities

People

  • Kenneth Wauchope

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Air Compressors
  • Artificial Intelligence
  • Assembly
  • Compressors
  • Drive Shafts
  • Gas Turbines
  • Grammars
  • Language
  • Malfunctions
  • Mechanical Equipment
  • Natural Language Understanding
  • Natural Languages
  • Particles
  • Propulsion Systems
  • Simulations
  • Structural Analysis
  • Turbines

Readers

  • Artificial Intelligence
  • Computational Linguistics
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation