基于机器学习的陕西旅游文化法英翻译资源库构建方法  

An Approach to the Construction of French-English Translation Resource Database for Shaanxi Tourism Culture Based on Machine Learning

作　　者：王玉 WANG Yu(School of Foreign Languages, Xianyang Normal University, Xianyang 712000, China)

机构地区：[1]咸阳师范学院外国语学院,陕西咸阳712000

出　　处：《微型电脑应用》2021年第12期87-90,共4页Microcomputer Applications

基　　金：咸阳师范学院专项科研基金项目(XSYK18033)。

摘　　要：对于我国丰富的旅游资源,传统的人工翻译已经无法满足人们的需求,为此,基于机器学习构建陕西旅游文化法英翻译资源库。确定资源库的总体架构和功能架构,利用朴素贝叶斯分类算法对资源训练,根据计算得出的文本属性权重大小对资源文本分类划分,通过机器学习自学习过程补充和完善资源库中的资源属性,保证资源库中资源具有较高的准确性,至此完成资源库的构建。通过性能测试结果可知,应用所提方法后法英翻译资源库在忠实度、流畅度和可理解度方面均有了明显提升,为旅游翻译工作者提供了强有力的基础保障。Because of China’s abundant tourism resources,the traditional manual translation has been unable to meet the needs of people.Therefore,based on machine learning,this paper constructs the French-English translation resource library of Shaanxi tourism culture.It determines the overall architecture and functional architecture of the resource database,uses naive Bayesian classification algorithm to train the resources,classifies the resource text according to the weights of the calculated text attributes,supplements and improves the resource attributes in the resource database through machine learning process,and ensures the high accuracy of the resources in the resource database,so as to complete the construction of the resource database.The performance test results show that the application of the proposed method can significantly improve the faithfulness,frequency and comprehensibility of the French-English translation repository,which provides a strong foundation for tourism translators.

关 键 词：机器学习 法英翻译资源库 朴素贝叶斯分类算法 陕西旅游文化 资源训练集 

分 类 号：H315.9[语言文字—英语] H325.9