一种基于统计和模板的双层翻译研究

为了提高翻译系统的翻译准确率,在短语基础上结合模板的方法自动抽取模板结构;解码时,首先进行模板匹配,套用模板结构进行翻译,然后再按照Beam Search搜索算法进行后续翻译。因此,该方法可以有效地解决单一的统计翻译中语序错误。以汉蒙翻译为例,实验结果显示此方法可以有效地提高翻译效果,翻译效率比基于短语的统计翻译方法提高10%。

A Research on Statistical and Template for Double Tiers Chinese Mongolian Machine Translation

To improve the accuracy of the translation of the Chinese-National language Machine Translation System,this paper proposes the methods that combine the Phrase-Based Statistical Machine Translation and template based machine translation,using different methods automatically extracted template structure;Decoding,the first for template matching,use the template structure of the translation,and then according to Beam Search search algorithm to a follow-up translation.Thus,the method can be effectively resolved Word Order errors in a single statistical translation.Take A Chinese-Mongolian translation as an example,the experimental results show that this method can effectively improve translation effects.The translation efficiency increased by 10% than phrase-based statistical machine translation methods.