RM-structure alignment based statistical machine translation model

A novel model based on structure alignments is proposed for statistical machine translation in this paper. Meta-structure and sequence of meta-structure for a parse tree are defined. During the translation process, a parse tree is decomposed to deal with the structure divergence and the alignments can be constructed at different levels of recombination of meta-structure (RM). This method can perform the structure mapping across the sub-tree structure between languages. As a result, we get not only the translation for the target language, but sequence of meta-structure of its parse tree at the same time. Experiments show that the model in the framework of log-linear model has better generative ability and significantly outperforms Pharaoh, a phrase-based system.