Non-projective Dependency-based Pre-Reordering with Recurrent Neural Network for Machine Translation
Antonio Valerio Miceli Barone, Giuseppe M. Attardi · 2015
The quality of statistical machine trans-lation performed with phrase based ap-proaches can be increased by permuting the words in the source sentences in an order which resembles that of the target language. We propose a class of recur-rent neural models which exploit source-side dependency syntax features to re-order the words into a target-like order. We evaluate these models on the German-to-English language pair, showing signif-icant improvements over a phrase-based Moses baseline, obtaining a quality simi-lar or superior to that of hand-coded syn-tactical reordering rules. 1