LIMSI @ WMT'12

  • Authors:
  • Hai-Son Le;Thomas Lavergne;Alexandre Allauzen;Marianna Apidianaki;Li Gong;Aurélien Max;Artem Sokolov;Guillaume Wisniewski;François Yvon

  • Affiliations:
  • Univ. Paris-Sud, Orsay cedex, France and LIMSI-CNRS, Orsay cedex, France;LIMSI-CNRS, Orsay cedex, France;Univ. Paris-Sud, Orsay cedex, France and LIMSI-CNRS, Orsay cedex, France;LIMSI-CNRS, Orsay cedex, France;Univ. Paris-Sud, Orsay cedex, France and LIMSI-CNRS, Orsay cedex, France;Univ. Paris-Sud, Orsay cedex, France and LIMSI-CNRS, Orsay cedex, France;LIMSI-CNRS, Orsay cedex, France;Univ. Paris-Sud, Orsay cedex, France and LIMSI-CNRS, Orsay cedex, France;Univ. Paris-Sud, Orsay cedex, France and LIMSI-CNRS, Orsay cedex, France

  • Venue:
  • WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes LIMSI's submissions to the shared translation task. We report results for French-English and German-English in both directions. Our submissions use n-code, an open source system based on bilingual n-grams. In this approach, both the translation and target language models are estimated as conventional smoothed n-gram models; an approach we extend here by estimating the translation probabilities in a continuous space using neural networks. Experimental results show a significant and consistent BLEU improvement of approximately 1 point for all conditions. We also report preliminary experiments using an "on-the-fly" translation model.