An Improving Feature Extraction Algorithm for Maximum Entropy Based Phrase Reordering Model
Meng Sun · Zhongwen xinxi xuebao · 2011
This paper presents an improved feature extraction algorithm for maximum entropy based phrase reordering model.The algorithm can extract more accurate feature information of phrase reordering,particularly the feature of inverted phrases.It solves the problem of uneven distribution of feature information and increases the rate of correct translation.We use BLEU as a metric on Chinese-to-English translation,and the proposed algorithm obtains a relative improvement of 0.65% over baseline system.