A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model

In this paper, we propose a novel string-todependency algorithm for statistical machine translation. With this new framework, we employ a target dependency language model during decoding to exploit long distance word relations, which are unavailable with a traditional n-gram language model. Our experiments show that the string-to-dependency

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Libin Shen, Jinxi Xu, Ralph M. Weischedel
• Keywords: ACL 2008, Computational Linguistics, Dependency Language Model, Language Model, N-gram Language Model