Context-Sensitive Syntactic Source-Reordering by Statistical Transduction

  title={Context-Sensitive Syntactic Source-Reordering by Statistical Transduction},
  author={Maxim Khalilov and Khalil Sima'an},
How well can a phrase translation model perform if we permute the source words to fit target word order as perfectly as word alignment might allow? And how well would it perform if we limit the allowed permutations to ITGlike tree-transduction operations on the source parse tree? First we contribute oracle results showing great potential for performance improvement by source-reordering, ranging from 1.5 to 4 BLEU points depending on language pair. Although less outspoken, the potential of tree… CONTINUE READING