When is an embedded MT system "good enough" for filtering?

  • Authors:

  • Clare R. Voss;Carol Van Ess-Dykema

  • Affiliations:

  • Army Research Laboratory, Adelphi, MD;Ft. Meade, MD

  • Venue:
  • EmbedMT '00 ANLP-NAACL 2000 Workshop: Embedded Machine Translation Systems
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

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 FALCon 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.