Local phrase reordering models for statistical machine translation

  • Authors:
  • Shankar Kumar;William Byrne

  • Affiliations:
  • Johns Hopkins University, Baltimore, MD;Cambridge University, Cambridge, U.K.

  • Venue:
  • HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

We describe stochastic models of local phrase movement that can be incorporated into a Statistical Machine Translation (SMT) system. These models provide properly formulated, non-deficient, probability distributions over reordered phrase sequences. They are implemented by Weighted Finite State Transducers. We describe EM-style parameter re-estimation procedures based on phrase alignment under the complete translation model incorporating reordering. Our experiments show that the reordering model yields substantial improvements in translation performance on Arabic-to-English and Chinese-to-English MT tasks. We also show that the procedure scales as the bitext size is increased.