Search-Aware Tuning for Hierarchical Phrase-based Decoding

Parameter tuning is a key problem for statistical machine translation (SMT). Most popular parameter tuning algorithms for SMT are agnostic of decoding, resulting in parameters vulnerable to search errors in decoding. The recent research of “search-aware tuning” (Liu and Huang, 2014) addresses this problem by considering the partial derivations in every decoding step so that the promising ones are more likely to survive the inexact decoding beam. We extend this approach from phrase-based translation to syntaxbased translation by generalizing the evaluation metrics for partial translations to handle tree-structured derivations in a way inspired by inside-outside algorithm. Our approach is simple to use and can be applied to most of the conventional parameter tuning methods as a plugin. Extensive experiments on Chinese-to-English translation show significant BLEU improvements on MERT, MIRA and PRO.