摘要
通过对近年来公开发表在中国知网上以机器翻译质量评估为主题的相关论文进行统计分析,总结出人工评估法、有参考译文的自动评估法以及无参考译文的自动评估法的发展历史、评估标准、原理以及相关算法。在此基础上分析三者的优缺点、适用场合以及人工评估与自动评估的局限性和不平衡性,旨在找出现在机器翻译译文质量评估所存在的问题,展望未来的机器翻译评估标准发展。
Machine translation based on artificial intelligence technology is a new hot spot in translation research.How to evaluate the translation quality of machine translation is one of the focus in this hot spot.The paper aims at having statistical analysis on the relevant published papers of machine translation quality evaluation from CNKI.According to these papers,three methods can be concluded,namely manual evaluation,automatic evaluation based on reference translation and automatic evaluation without reference translation.The history,criteria and theories of three methods are elaborated in this paper and the advantages and disadvantages of them are also mentioned.Furthermore,future trend of machine translation evaluation is discussed.
作者
马鸣皓
MA Minghao(School of Foreign Languages,Shanghai University of International Business and Economics,Shanghai 201620,China)
出处
《宁波教育学院学报》
2019年第6期76-78,93,共4页
Journal of Ningbo Institute of Education
关键词
机器翻译
译文翻译质量
人工评估
神经网络
自动评估
machine translation
translation quality
manual evaluation
neural network
automatic evaluation