A Phrase Orientation Model for Hierarchical Machine Translation

We introduce a lexicalized reordering model for hierarchical phrase-based machine translation. The model scores monotone, swap, and discontinuous phrase orientations in the manner of the one presented by Tillmann (2004). While this type of lexicalized reordering model is a valuable and widely-used component of standard phrase-based statistical machine translation systems (Koehn et al., 2007), it is however commonly not employed in hierarchical decoders. We describe how phrase orientation probabilities can be extracted from wordaligned training data for use with hierarchical phrase inventories, and show how orientations can be scored in hierarchical decoding. The model is empirically evaluated on the NIST Chinese→English translation task. We achieve a significant improvement of +1.2 %BLEU over a typical hierarchical baseline setup and an improvement of +0.7 %BLEU over a syntax-augmented hierarchical setup. On a French→German translation task, we obtain a gain of up to +0.4 %BLEU.