Maximum Entropy Based Lexical Reordering Model for Hierarchical Phrase-based Machine Translation

The hierarchical phrase-based (HPB) model on the basis of a synchronous context-free grammar (SCFG) is prominent in solving global reorderings. However, the HPB model is inadequate to supervise the reordering process so that sometimes positions of different lexicons are switched due to the incorrect SCFG rules. In this paper, we consider the order of two lexicons as a classification problem and propose a novel lexical reordering model based on a maximum entropy classifier. Our model employs the word alignment and translation during the decoding process. Experimental results on the Chinese-to-English task showed that our method outperformed the baseline system in BLEU score significantly. Moreover, the translation results further proved the effectiveness of our approach.