特征提取算法下的英汉翻译系统研究  

Study of English-Chinese Translation System Based on Feature Extraction Algorithm

作　　者：米婧[1] Mi Jing(Xianyang Vocational Technical College,Xianyang 712000,China)

机构地区：[1]咸阳职业技术学院

出　　处：《单片机与嵌入式系统应用》2020年第3期54-56,共3页Microcontrollers & Embedded Systems

摘　　要：在英汉翻译系统中,特征提取算法可以提取最优语境和特征语义,提升翻译准确度。本文对特征提取算法下的英汉翻译系统进行研究,并对比了常用的TF-IDF特征提取算法和LDA特征提取算法下的英汉翻译系统翻译效果。仿真结果表明,相对于传统的英汉翻译系统,采用特征提取算法,英汉翻译系统的准确率以及召回率较高,翻译精度高,且LDA特征提取算法具有更高的翻译精度、更高的文本准确率和召回率。In English-Chinese translation system,feature extraction algorithm can extract the optimal context and feature semantics and improve the translation accuracy.In the paper,the English-Chinese translation system based on feature extraction algorithm is studied,and compares the translation effects of the commonly used TF-IDF feature extraction algorithm and LDA feature extraction algorithm.The results show that compared with the traditional English-Chinese translation system,the feature extraction algorithm has a higher accuracy,recall rate and translation accuracy.Moreover,LDA feature extraction algorithm has higher translation accuracy,higher text accuracy and recall rate.

关 键 词：特征提取算法 英汉翻译系统 TF-IDF LDA 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]