Effective Use of Linguistic and Contextual Information for Statistical Machine Translation

Current methods of using lexical features in machine translation have difficulty in scaling up to realistic MT tasks due to a prohibitively large number of parameters involved. In this paper, we propose methods of using new linguistic and contextual features that do not suffer from this problem and apply them in a state-ofthe-art hierarchical MT system. The features used in this work are non-terminal labels, non-terminal length distribution, source string context and source dependency LM scores. The effectiveness of our techniques is demonstrated by significant improvements over a strong baseline. On Arabic-to-English translation, improvements in lower-cased BLEU are

• Type: Journal
• Year: 2009
• Where: EMNLP
• Authors: Libin Shen, Jinxi Xu, Bing Zhang, Spyros Matsoukas, Ralph M. Weischedel
• Keywords: EMNLP 2009, Natural Language Processing, Non-terminal Length Distribution, Realistic Mt Tasks, State-ofthe-art Hierarchical Mt