汉语语言模型的规模对统计机器翻译系统的影响

The Scale of Chinese Language Models for Statistical Machine Translation System

本文专门研究了汉语语言模型的规模大小,语法元数在英汉统计机器翻译系统中的影响。实验表明,对于同样的语言模型,基于层次短语的翻译系统明显比基于短语的翻译系统性能要好。对于不同的语言模型,它的元数和规模对翻译的结果有较大的影响,但不一定元数或者规模越大,所得到结果就越好。

This paper presents the effects of Chinese language models’ scale and n-gram’s dimension in English-Chinese machine translation systems. Experiments shows that for the same language models, hierarchical phrase -based MT system is better than phrase-based MT system, but for the same MT system, Language models’ scale and dimension effects the BLEU value obviously. It is not sure that a larger scale and higher dimension language model has a better result.