Tree-based statistical machine translation models have made significant progress in recent years, especially when replacing 1-best trees with packed forests. However, as the parsing accuracy usually goes down dramatically with the increase of sentence length, translating long sentences often takes long time and only produces degenerate translations. We propose a new method named subsentence division that reduces the decoding time and improves the translation quality for tree-based translation. Our approach divides long sentences into several sub-sentences by exploiting tree structures. Large-scale experiments on the NIST 2008 Chinese-toEnglish test set show that our approach achieves an absolute improvement of .
