基于复述技术的汉语成语翻译方法研究  

Chinese Idiom Translation Based on Paraphrasing

作　　者：罗凌[1] 陈毅东[1] 史晓东[1] 苏劲松[2] 

机构地区：[1]厦门大学智能科学与技术系,福建厦门361005 [2]厦门大学软件学院,福建厦门361005

出　　处：《中文信息学报》2015年第4期166-174,共9页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61005052);国家科技支撑计划(2012BAH14F03);中央高校基本科研业务费专项资金(2010121068);福建省自然科学基金(2011J01369)

摘　　要：汉语成语是汉语的精华,拥有特有的语言形式,并经常出现在汉语中。但是由于汉英统计机器翻译训练语料中成语的稀疏性和现今大多机器翻译系统并没有对成语进行特殊的处理和研究,在汉英机器翻译中成语的翻译并不理想。针对该问题,本文提出了基于复述技术的两种方法来提高汉英统计机器翻译系统中成语翻译的能力。方法1:测试集成语复述替换;方法2:训练集成语复述替换。实验结果表明,方法1可以解决成语未登录词问题,提高成语翻译能力。方法2可以解决训练语料中成语稀疏问题,改善翻译训练模型。Chinese idioms are frequently used in all kinds of Chinese texts. However, since Chinese idioms are rela- tively sparse in most training corpora for Chinese-English SMT systems, translation quality of the idioms are not satisfactory. And to the best of our knowledge, there is very little research on handling the translation of Chinese id- ioms. This paper proposes two methods to improve the translation of Chinese idioms by paraphrases in Chinese-Eng- lish SMT. In the first method, we paraphrase the Chinese idioms in the test set, while in the second method, we paraphrase the Chinese idioms in the training set. The experimental results show that both methods could signifi- cantly improve the performance of the Chinese-English SMT system.

关 键 词：统计机器翻译 成语翻译 复述 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]