Can we relearn an RBMT system?

  • Authors:
  • Loïc Dugast;Jean Senellart;Philipp Koehn

  • Affiliations:
  • SYSTRAN S.A., La Grande Arche, Paris, France and University of Edinburgh, Edinburgh, United Kingdom;SYSTRAN S.A., La Grande Arche, Paris, France;University of Edinburgh, Edinburgh, United Kingdom

  • Venue:
  • StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes SYSTRAN submissions for the shared task of the third Workshop on Statistical Machine Translation at ACL. Our main contribution consists in a French-English statistical model trained without the use of any human-translated parallel corpus. In substitution, we translated a monolingual corpus with SYSTRAN rule-based translation engine to produce the parallel corpus. The results are provided herein, along with a measure of error analysis.