A Multi-Level Reordering Model For Statistical Machine Translation Using Source Side Parse Trees

In translating between a pair of languages, reordering is a major task, which is roughly defined as finding the right order of words in target language. Word reordering is a key element affecting the machine translation quality and one of its serious difficulties as well. In this paper, we present a new reordering model based on POS tags and syntactical information that exists in source sentence's parse trees. In order to use this information properly, we proposed an innovative method that reorders sentences on two different levels (i.e., phrase and word level). This method considers relationships among the words in a sentence and performs reordering with respect to the sentence structure, unlike only POS-based models. We examined this model on English-Persian language pair. Our experiments showed that this model can improve the measure of precision and reorder sentences more reliably than previous approaches.