RM-structure alignment based statistical machine translation model

摘要

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