该文针对统计机器翻译中基于最大熵短语重排序模型特征抽取算法,提出一种改进算法。该算法能够抽取出更多准确的短语重排序信息,特别是逆序短语的特征信息,解决了原算法中最大熵训练时特征数据不平衡的问题,提高了翻译中短语重排序的准确率。以NIST MT 05作为汉语到英语翻译的测试集,实验结果表明改进后的系统BLEU值比原系统提高0.65%。
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.