Dependency Parsing on Source Language with Reordering Information in SMT

In statistical machine translation, many translation errors may easily occur especially when the word orders are very different between source language and target language, especially with asymmetric morphological structures. The paper investigates combining a rule-based reordering model with conventional dependency parsing at the source side, which can alleviate both the asymmetry of morphological structures and the word orders between source language and target language. Experiments show that this method can improve the performance of the statistical machine translation system.