Paper: Syntactic Re-Alignment Models for Machine Translation

ACL ID D07-1038
Title Syntactic Re-Alignment Models for Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2007

We present a method for improving word alignment for statistical syntax-based ma- chine translation that employs a syntacti- cally informed alignment model closer to the translation model than commonly-used word alignment models. This leads to ex- traction of more useful linguistic patterns and improved BLEU scores on translation experiments in Chinese and Arabic. 1 Methods of statistical MT Roughly speaking, there are two paths commonly taken in statistical machine translation (Figure 1). The idealistic path uses an unsupervised learning algorithm such as EM (Demptser et al. , 1977) to learn parameters for some proposed translation model from a bitext training corpus, and then di- rectly translates using the weighted model. Some examples of the idealistic approach are the direct IBM word ...