Unsupervised Discriminative Induction of Synchronous Grammar for Machine Translation
Xinyan Xiao, Deyi Xiong, Yang Liu, Qun Liu, Shouxun Lin · 2012
We present a global log-linear model for synchronous grammar induction, which is capable of incorporating arbitrary features. The parameters in the model are trained in an unsupervised fashion from parallel sentences without word alignments. To make parameter training tractable, we also propose a novel and efficient cube pruning based synchronous parsing algorithm. Using learned synchronous grammar rules with millions of features that contain rule level, word level and translation boundary information, we significantly outperform a competitive hierarchical phrased-based baseline system by +1.4 BLEU on average on three NIST test sets.