String-to-dependency statistical machine translation

Abstract

We propose a novel string-to-dependency algorithm for statistical machine translation. This algorithm employs a target dependency language model during decoding to exploit long distance word relations, which cannot be modeled with a traditional n-gram language model. Experiments show that the algorithm achieves significant improvement in MT performance over a state-ofthe- art hierarchical string-to-string system on NIST MT06 and MT08 newswire evaluation sets. © 2010 Association for Computational Linguistics.