The BM-I2R Haitian-Créole-to-English translation system description for the WMT 2011 evaluation campaign

  • Authors:
  • Marta R. Costa-jussà;Rafael E. Banchs

  • Affiliations:
  • Barcelona Media Innovation Center, Barcelona;Institute for Infocomm Research, Singapore

  • Venue:
  • WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

This work describes the Haitian-Créole to English statistical machine translation system built by Barcelona Media Innovation Center (BM) and Institute for Infocomm Research (I2R) for the 6th Workshop on Statistical Machine Translation (WMT 2011). Our system carefully processes the available data and uses it in a standard phrase-based system enhanced with a source context semantic feature that helps conducting a better lexical selection and a feature orthogonalization procedure that helps making MERT optimization more reliable and stable. Our system was ranked first (among a total of 9 participant systems) by the conducted human evaluation.