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-of-the-art hierarchical string-to-string system on NIST MT06 and MT08 newswire evaluation sets.

This content is only available as a PDF.

Author notes

*

10 Moulton Street, Cambridge, MA 02138. E-mail: libinshen@gmail.com.

**

10 Moulton Street, Cambridge, MA 02138. E-mail: jxu@bbn.com.

10 Moulton Street, Cambridge, MA 02138. E-mail: weisched@bbn.com.