首页 | 本学科首页   官方微博 | 高级检索  
     

一种面向句子的汉英口语翻译自动评分方法
引用本文:李心广,陈帅,龙晓岚. 一种面向句子的汉英口语翻译自动评分方法[J]. 中文信息学报, 2021, 35(7): 54-62
作者姓名:李心广  陈帅  龙晓岚
作者单位:1.广东外语外贸大学 语言工程与计算(广东省)重点实验室, 广东 广州 510006;
2.广东外语外贸大学 信息科学与技术学院, 广东 广州 510006
基金项目:国家自然科学基金(61877013);全国科学技术名词审定委员会2019年度科研项目(WT2019006);广东省科技创新战略专项资金(Pdjh2021a0170,Pdjh2021b0176)
摘    要:该文提出一种面向句子的汉英口语翻译自动评分方法,选取语义关键词、句子大意和口语流利度作为评分的主要参数.为了提高关键词评分的准确度,该文使用同义词辨析方法,识别考生答题关键词中的同义词;在句子层面,使用可伸展递归自编码(unfolding recursive auto-encoder,URAE)神经网络模型分析考生对句...

关 键 词:汉英口语翻译自动评分  同义词辨析  URAE神经网络  口语流利度
收稿时间:2020-04-23

Sentence Based Automatic Scoring Method for Chinese-English Oral Translation
LI Xinguang,CHEN Shuai,LONG Xiaolan. Sentence Based Automatic Scoring Method for Chinese-English Oral Translation[J]. Journal of Chinese Information Processing, 2021, 35(7): 54-62
Authors:LI Xinguang  CHEN Shuai  LONG Xiaolan
Affiliation:1.Laboratory of Language Engineering and Computing, Guangdong University of Foreign Studies, Guangzhou, Guangdong 510006, China;2.School of Information Science and Technology, Guangdong University of Foreign Studies, Guangzhou, Guangdong 510006, China
Abstract:This paper proposes a sentence-based automatic scoring method for Chinese-English oral translation. Three main indicators are designed for evaluating keywords, general idea of sentences and fluency. As for keywords, this paper applies the synonym analysis to identify synonyms in candidate keywords. At the sentence level, the translation of sentences is evaluated by Unfolding Recursive Auto-Encoder (URAE). Then, fluency is scored by the speed of the speech. Finally, the weighted sum of the three indicators is generated as the overall translation quality score. The experimental results demonstrated that this automatic scoring method bears good consistency with manual scoring method.
Keywords:automatic scoring method of oral Chinese-English translation    synonym analysis    Unfolding Recursive Auto-Encoder (URAE) neural network    fluency  
点击此处可从《中文信息学报》浏览原始摘要信息
点击此处可从《中文信息学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号