This paper surveys several state-of-the-art reordering techniques employed in Statistical Machine Translation systems. Reordering is understood as the word-order redistribution of the translated words. In original SMT systems, this differert order is only modeled within the limits of translation units. Relying only in the reordering provided by translation units may not be goolii enough in most language pairs, which might require longer reordering Therefore, additional techniques may be deployed to face the reordering thallenge. The Statistical Machine Translation community has been very actve recently in developing reordering techniques. This paper gives a brief survey and classification of several well-known reordering approaches.
展开▼