Comparing Reordering Constraints for SMT Using Efficient BLEU Oracle Computation
| Citations: | 4 - 1 self |
BibTeX
@MISC{Dreyer_comparingreordering,
author = {Markus Dreyer and Keith Hall and Sanjeev Khudanpur},
title = {Comparing Reordering Constraints for SMT Using Efficient BLEU Oracle Computation},
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper describes a new method to compare reordering constraints for Statistical Machine Translation. We investigate the best possible (oracle) BLEU score achievable under different reordering constraints. Using dynamic programming, we efficiently find a reordering that approximates the highest attainable BLEU score given a reference and a set of reordering constraints. We present an empirical evaluation of popular reordering constraints: local constraints, the IBM constraints, and the Inversion Transduction Grammar (ITG) constraints. We present results for a German-English translation task and show that reordering under the ITG constraints can improve over the baseline by more than 7.5 BLEU points. 1
