TRAINS-96 System Evaluation.

Abstract

In this report we describe an experiment designed to: (1) evaluate the performance of the TRAINS-96 system as a whole; (2) examine the utility of a new robust post-parser module, recently added to the TRAINS system, and (3) explore the benefit to the user of receiving system feedback on speech input. The evaluation uses the same task-based methodology as was used for the TRAINS-95 evaluation, in which the user and computer cooperatively solve a given problem. Success is measured in terms of task performance measures such as time to completion of a task, and the quality of the final plan produced.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 19, 1997
Accession Number
ADA329865

Entities

People

  • Amanda J. Stent
  • James F. Allen

Organizations

  • University of Rochester

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Acoustic Signals
  • Automated Speech Recognition
  • Classification
  • Computer Science
  • Computers
  • Experimental Design
  • Information Systems
  • Instructions
  • Language
  • Natural Language Processing
  • Natural Languages
  • New York
  • Phase
  • Recognition
  • Test And Evaluation
  • Word Recognition

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Computational Modeling and Simulation
  • Military Training and Readiness Simulation