基于混合语义空间的汉译英自动评分模型  

Automated Chinese-English translation scoring model based on hybrid semantic space

作　　者：潘婷婷 黄桂敏[1] 刘剑 PAN Tingting;HUANG Guimin;LIU Jian(School of Information and Communication,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004

出　　处：《桂林电子科技大学学报》2018年第6期459-463,共5页Journal of Guilin University of Electronic Technology

基　　金：国家自然科学基金(61662012);认知无线电与信息处理省部共建教育部重点实验室基金(CRKL150105)

摘　　要：针对传统翻译自动评分方法分析不够全面且准确率不高的问题,提出一种基于混合语义空间的汉译英自动评分模型。该模型通过规则与统计相结合的语法检错算法对待测译文进行语法分析,并基于混合语义空间的语义相关度算法对待测译文与标准译文进行分析,然后赋予相应的权重,从而对待测译文进行自动评分。实验结果表明,该方法与人工评分的平均误差仅为1.13,皮尔逊相关系数为0.87,具有较高的准确率。Aiming at the case that traditional automatic correction method for English translation is not overall and in low accuracy,an automatic correction model of Chinese-English translation which is based on hybrid semantic space is studied and designed.The model can analyze the grammar errors of the Chinese-English essay by a syntactic error detection algorithm which combines rules and statistics,it also can compare the translation essay with the standard by a semantic relevancy algorithm which is based on hybrid semantic space.Meanwhile,the corresponding weights will be calculated.Then the efficient automatic scoring of the translation essay can get.Via experimenting with real data sets,the results show that the the average error between the proposed method and manual scoring is only 1.13,the pearson correlation coefficient of the method is 0.87 and the method has high accuracy and good practicability in automatic translation scoring field.

关 键 词：翻译自动评分 混合语义空间 语法检错 语义相关度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]