面向英文阅读难度分类的神经网络设计与实现  

Design and implementation of neural network for English reading difficulty classification

作　　者：徐诗语 张谦[1] 邬依林[1] Xu Shiyu;Zhang Qian;Wu Yilin(School of Computer Science,Guangdong University of Education,Guangzhou 510300,China)

机构地区：[1]广东第二师范学院计算机学院,广州510300

出　　处：《现代计算机》2024年第2期52-59,112,共9页Modern Computer

基　　金：广东省自然科学基金(2022A1515010485);广东省2020年高等教育教学改革项目(440);广东第二师范学院2022年度大学生创新创业训练计划项目(202214278013)。

摘　　要：阅读文本是影响英语阅读材料难度的重要因素,有效地评估英文文本难度可以为不同阅读能力的学习者提供相匹配的阅读材料,帮助教师科学选择合适的教学资源,为考试命题者提供科学指导。基于神经动力学方法(NDA)的收敛差分神经网络(CDNN),将文本数据进行特征选择、加权和样本归一化预处理,用于训练不同映射函数的网络,再将网络的输出通过投票规则进行增强泛化,从而实现了一种结合投票收敛差分神经网络(Voting-CDNN,V-CDNN)的英文文本阅读难度分类方法,提高了计算效率和分类预测准确率。实验结果表明,V-CDNN的分类准确率最高值和平均值分别达到98.81%和95.45%,其在计算时间、平均精度和最高精度等方面进一步证实了V-CDNN是一个高性能的分类器。Reading text is one of the most important factors which influence English reading.Effective evaluation to the diffi⁃culty of English text can provide different reading materials to the learners with different reading abilities,help teachers to scientifi⁃cally select appropriate teaching resources,and provide scientific guidance for test proposers.In this paper,based on the neural dy⁃namics algorithm(NDA)method of convergent difference neural network(CDNN),the text data are preprocessed with feature selec⁃tion,weighting and sample normalization for training networks with different mapping functions,and then the output of the network is enhanced and generalized by voting rules for augmented generalization,thus realizing a reading difficulty classification method for English text combined by a voting convergent difference neural network(Voting⁃CDNN,V⁃CDNN),which improves the compu⁃tational efficiency and classification accuracy.The experimental results show that the highest and average values of classification accuracy of V⁃CDNN reach 98.81%and 95.45%,respectively,which further confirm that V⁃CDNN is a high⁃performance classifier in terms of computation time,average accuracy and maximum accuracy.

关 键 词：文本分类 投票策略 收敛差分神经网络 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]