对齐模板在标准短语统计机器翻译模型中的应用

在统计机器翻译领域,基于短语的翻译模型性能上优于基于词的翻译模型。基于对齐模板的短语翻译模型和标准短语翻译模型是短语翻译模型中的典型代表,二者在翻译过程中分别使用对齐模板和短语对。对齐模板和短语对各有优势,对齐模板能够较好处理数据稀疏的问题,短语对可以使翻译更加精确。本文提出在基于最大熵的标准短语翻译模型下模拟对齐模板,模拟的对齐模板被作为一个单独的特征函数加入到此翻译模型中。实验在中英翻译和法英翻译上进行,实验结果证明,本文方法明显改善了标准短语翻译模型的翻译效果。

Using alignment template in standard phrase-based statistical machine translation model

In statistical machine translation field,the phrase-based translation model outperforms the word-based translation model.The alignment template phrase-based translation model and the standard phrase-based translation model are the two typical presentations.These two models use alignment template and phrase pair respectively in translation process.Alignment template and phrase-pair have their advantages respectively.Alignment template can handle data sparseness problem better,and phrase pair can make the translation process more exactly.This paper proposes a method to simulate alignment template at the standard phrase-based translation model based on maximum entropy.The simulation of alignment template is considered as a feature and is added into this translation model.The experiments on Chinese-English and French-English translation tasks show that this method improves the performance distinctly in standard phrase-based translation model.