机器翻译测评的实践与分析  

Practice and Analysis in Evaluation of Machine Translation

作　　者：曹冬林[1] 李堂秋[1] 史晓东[1] 蔡经球[1] 

机构地区：[1]厦门大学计算机科学系,福建厦门361005

出　　处：《计算机应用研究》2004年第3期29-32,共4页Application Research of Computers

基　　金：国家"863"计划项目(2001AA114110);福建省科技计划重点项目(2001H023)

摘　　要：机器翻译是人工智能领域中一项有挑战性的研究课题 ,而对机器翻译系统的测评也越来越受到重视。为了考察现今机器翻译系统的翻译质量及其出现的问题 ,提出了采用大规模语料库作为测试集的方法 ,对六个机器翻译系统进行了半自动测评 ,分析了机器翻译系统在词法和句法上存在的问题 ,并将测评结果与NIST自动测评进行比较 。Machine Translation is one of the most challenging problems in artificial intelligence and recently its evaluation gets more and more attention.In order to assess the translation quality and to pinpoint the problems in current Machine Translation System,this paper presents a method of using a large-scale corpus as a testing set by which we have semi-automatically evaluated six Machine Translation Systems.Finally we have analysed the problems of morphology and syntax in Machine Translation Systems,and have proved the objectivity of our evaluation result by comparing with automatic evaluation of NIST.

关 键 词：句子长度 错误类型 自动测评 分级 

分 类 号：TP391.2[自动化与计算机技术—计算机应用技术]