Accurate Non-Hierarchical Phrase-Based Translation

A principal weakness of conventional (i.e., non-hierarchical) phrase-based statistical machine translation is that it can only exploit continuous phrases. In this paper, we extend phrase-based decoding to allow both source and target phrasal discontinuities, which provide better generalization on unseen data and yield significant improvements to a standard phrase-based system (Moses). More interestingly, our discontinuous phrasebased system also outperforms a state-of-the-art hierarchical system (Joshua) by a very significant

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Michel Galley, Christopher D. Manning
• Keywords: Computational Linguistics, NAACL 2010, Phrase-based Statistical Machine, Significant Improvements, Target Phrasal Discontinuities