Google Research

Automatically Learning Source-side Reordering Rules for Large Scale Machine Translation

COLING-2010

Abstract

We describe an approach to automatically learn reordering rules to be applied as a preprocessing step in phrase-based machine translation. We learn rules for 8 different language pairs, showing BLEU improvements for all of them, and demonstrate that many important order transformations (SVO to SOV or VSO, head-modifier, verb movement) can be captured by this approach.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work