Joint Phrase Alignment and Extraction for Statistical Machine Translation

The phrase table, a scored list of bilingual phrases, lies at the center of phrase-based machine translation systems. We present a method to directly learn this phrase table from a parallel corpus of sentences that are not aligned at the word level. The key contribution of this work is that while previous methods have generally only modeled phrases at one level of granularity, in the proposed method phrases of many granularities are included directly in the model. This allows for the direct learning of a phrase table that achieves competitive accuracy without the complicated multistep process of word alignment and phrase extraction that is used in previous research. The model is achieved through the use of non-parametric Bayesian methods and inversion transduction grammars (ITGs), a variety of synchronous context-free grammars (SCFGs). Experiments on several language pairs demonstrate that the proposed model matches the accuracy of the more traditional two-step word alignment/phrase extraction approach while reducing its phrase table to a fraction of its original size.