Word-reordering for Statistical Machine Translation Using Trigram Language Model

In this paper we study the word-reordering problem in the decoding part of statistical machine translation, but independently from the target language generating process. In this model, a permuted sentence is given and the goal is to recover the correct order. We introduce a greedy algorithm called Local-(k, l)-Step, and show that it performs better than the DP-based algorithm. Our word-reordering algorithm can be used in the statistical machine translation process for improving the quality of the translation. Furthermore, motivated by the rank evaluation method, we introduce a novel way for evaluating the results of word-reordering by calculating the inversion pair cardinality.