英语关系从句机译汉语评价——以谷歌机器翻译为例  

Evaluation of Translating English Relative Clauses into Chinese: A Case Study of Google Translate

作　　者：贺文照[1] 李德凤[2] HE Wenzhao;LI Defeng

机构地区：[1]嘉兴学院外国语学院,嘉兴市314001 [2]澳门大学人文艺术学院,澳门特别行政区

出　　处：《中国科技翻译》2019年第3期30-34,共5页Chinese Science & Technology Translators Journal

基　　金：澳门大学跨年研究项目(MYRG2015-00150-FAH,MYRG2016-00096-FAH,MYRG2017-00139-FAH)资助

摘　　要：关系从句在心理语言学、句法学、二语习得以及翻译转换中受到重视。新一代神经网络机器翻译在翻译质量上有了很大改进。为了了解新一代机器翻译在翻译英语关系从句的进展与存在的问题,我们对机器翻译译文进行了定量和定性评价。结果表明,机器翻译译文可接受性总体上仍然比人工译文低,机器翻译译文可接受度起伏较大。文章同时分析了谷歌机器翻译在汉译英语关系从句中的进展和存在问题。Relative clause has been studied intensively in linguistic typology, psycholinguistics, syntax, second language acquisition and translation studies because of its unique features. Google’s new generation of neural machine translation is reported to work better than the previous MT systems. This evaluation study aims at learning progress and potential problems of MT in translating English relative clauses into Chinese. In order to evaluate the progress as well as the potential problems in the new system, both a quantitative and qualitative investigation have been carried out. The result shows that the Chinese translation by MT is significantly different from human translation, though some products of MT are very close to human translation in respect of acceptability.

关 键 词：机器翻译 英语关系从句 汉语关系从句 谷歌机器翻译 

分 类 号：H315.9[语言文字—英语] H085