Discriminative Phrase-based Lexicalized Reordering Models using Weighted Reordering Graphs
Ling Wang, Joäo Graça, David Martins de Matos, Isabel M. Trancoso, Alan W. Black · International Joint Conference on Natural Language Processing · 2011
Lexicalized reordering models play a central role in phrase-based statistical machine translation systems. Starting from the distance-based reordering model, improvements have been made by considering adjacent words in word-based models, adjacent phrases pairs in phrasebased models, and finally, all phrases pairs in a sentence pair in the reordering graphs. However, reordering graphs treat all phrase pairs equally and fail to weight the relationships between phrase pairs. In this work, we propose an extension to the reordering models, named weighted reordering models, that allows discriminative behavior to be defined in the estimation of the reordering model orientations. We apply our extension using the weighted alignment matrices to weight phrase pairs, based on the consistency of their alignments, and define a distance metric to weight relationships between phrase pairs, based on their distance in the sentence. Experiments on the IWSLT 2010 evaluation dataset for for the Chinese-English language pair yields an improvement of 0.38 (2%) and 0.94 (3.7%) BLEU points over the state-of-the-art work’s results using weighted alignment matrices.