When is an Embedded MT System 'Good Enough' for Filtering?

Abstract

This paper proposes an end-to-end process analysis template with replicable measures to evaluate the filtering performance of a Scan-OCR-MT system. Preliminary results across three language-specific FALCon2 systems show that, with one exception, the derived measures consistently yield the same performance ranking: Haitian Creole at the low end, Arabic in the middle, and Spanish at the high end.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2000
Accession Number
ADA459850

Entities

People

  • Carol Van Ess-dykema
  • Clare R. Voss

Organizations

  • United States Army Research Laboratory

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Character Recognition
  • Department Of Defense
  • Filters
  • Filtration
  • Foreign Languages
  • Hard Copy
  • Information Processing
  • Judgment
  • Language
  • Machine Translation
  • Measures Of Effectiveness
  • Military Research
  • Motor Skills
  • Natural Language Processing
  • Natural Languages
  • Systems Engineering
  • Translations

Readers

  • Computational Linguistics
  • Computational Modeling and Simulation
  • Systems Analysis and Design