Paper: Sub-Sentence Division for Tree-Based Machine Translation

ACL ID P09-2035
Title Sub-Sentence Division for Tree-Based Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2009

Tree-based statistical machine translation models have made significant progress in re- cent years, especially when replacing 1-best trees with packed forests. However, as the parsing accuracy usually goes down dramati- cally with the increase of sentence length, translating long sentences often takes long time and only produces degenerate transla- tions. We propose a new method named sub- sentence 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 ex- periments on the NIST 2008 Chinese-to- English test set show that our approach achieves an absolute improvement of 1.1 BLEU points over the baseline system in 50% less ti...