机器翻译自动评价综述  

A Survey of Automatic Machine Translation Evaluation

作　　者：李良友[1,2] 贡正仙[1,2] 周国栋[1,2] 

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006 [2]苏州大学自然语言处理实验室,江苏苏州215006

出　　处：《中文信息学报》2014年第3期81-91,共11页Journal of Chinese Information Processing

基　　金：国家自然科学基金(90920004)

摘　　要：随着机器翻译的发展,对其质量进行评测的自动评价方法也越来越受重视。发展至今,各种评价方法与技术层出不穷,采用何种分类标准来组织和描述它们也是一个很大的挑战。根据核心技术的不同,该文重点介绍了三类主流的自动评价方法,包括:基于语言学检测点的方法、字符串匹配的方法和基于机器学习的方法。论文分别阐述了这些类别中颇具代表性的方法的工作原理并分析了各自的优缺点。此外,受限参考译文下的评价技术虽然不是主流的方法,但是其对提高自动化程度和评价性能的作用不能忽视,所以该文将其作为特殊的类别做了阐述。然后,汇报了近年来衡量自动评价方法的国际评测结果。最后,总结了自动评价的发展趋势和有待进一步解决的相关问题。With the development of machine translation, the automatic evaluation methods have been paid more and more attention. Since so marly related methods and technologies have been proposed, it is a big challenge to organize and describe them with a scientific classification. This paper focuses on three types of methods, i.e. Checkpoint- based methods, String-matching methods and Machine Learning based method. This paper enumerates several rep- resentative approaches for each type of method, describing the principle of metrics and analyzing advantages and shortcomings of them. In addition, the sub-branch of evaluation with limited references is also introduced as a spe- cial catalog, which plays an important role in increasing the degree of automation as well as boosting the perform- ance. Furthermore, some famous evaluation metric campaigns are introduced. Finally, we show the trend of current researches on automatic evaluation and point out some relevant problems for future study.

关 键 词：机器翻译 自动评价 自动评价分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]