Hierarchical Phrase-Based Translation

David Chiang
2007 Computational Linguistics  
We present a statistical machine translation model that uses hierarchical phrases-phrases that contain subphrases. The model is formally a synchronous context-free grammar but is learned from a parallel text without any syntactic annotations. Thus it can be seen as combining fundamental ideas from both syntax-based translation and phrase-based translation. We describe our system's training and decoding methods in detail, and evaluate it for translation speed and translation accuracy. Using BLEU
more » ... ccuracy. Using BLEU as a metric of translation accuracy, we find that our system performs significantly better than the Alignment Template System, a state-of-the-art phrasebased system. *
doi:10.1162/coli.2007.33.2.201 fatcat:gujz3zltzreqdohn2d6vrr4qgy