Hierarchical Phrase-Based Translation

TLDR

It combines fundamental ideas from both syntax-based translation and phrase-based translation. We present a statistical machine translation model that uses hierarchical phrases containing subphrases. The model is a synchronous context-free grammar learned from parallel text without syntactic annotations, and we detail its training and decoding methods while evaluating translation speed and accuracy. Using BLEU, our system performs significantly better than the Alignment Template System, a state-of-the-art phrase-based system.

Abstract

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 as a metric of translation accuracy, we find that our system performs significantly better than the Alignment Template System, a state-of-the-art phrase-based system.