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

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, headmodifier, verb movement) can be captured by this approach.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Dmitriy Genzel
• Keywords: BLEU Improvements, COLING 2010, Computational Linguistics, Important Order Transformations, Phrase-based Machine Translation