Context-extended Phrase Reordering Model for Pivot-based Statistical Machine Translation

For translation between language pairs which is lack of bilingual data, pivot-based SMT uses a pivot language as a "bridge" to generate source-target translation, inducing from source-pivot and pivot-target translation. However, due to the missing of the context information, the reordering model was hard to obtain with the conventional methods. In this paper, we present a context-extended phrase reordering model for pivot-based statistical machine translation by extending the context information in source, pivot and target language. Experimental results show that our method leads to significant improvements over the baseline system on European Parliament data.