适用于特殊类型自然语言分类的自适应特征谱神经网络  

Adaptive feature spectrum neural networks for special types of natural language classification

作　　者：王一峰 孙丽茹 崔良乐 赵毅 WANG Yifeng;SUN Liru;CUI Liangle;ZHAO Yi(School of Science,Harbin Institute of Technology(Shenzhen),Shenzhen 518055,China)

机构地区：[1]哈尔滨工业大学(深圳)理学院,广东深圳518055 [2]哈尔滨工业大学(深圳)应用数学研究中心,广东深圳518055

出　　处：《大数据》2020年第4期92-104,共13页Big Data Research

基　　金：学位与研究生教育资助项目(N o.2017 Y0902);深圳市教育科学规划2015年度重大招标课题重点资助项目(N o.zdzz15001);哈尔滨工业大学(深圳)高等教育教学改革资助项目。

摘　　要：计算机算力的提升使得深度学习算法迅速发展,然而由于古诗文特殊的语序、用词、结构、句式、文法结构、表达方式,深度学习模型需要消耗更多的算力进行特征提取等工作,因此并未在这一领域取得广泛的应用。为此,提出了一种新型的神经网络结构——自适应特征谱神经网络。该算法有效减少了运算时间,可以自适应地选择对分类最有用的特征,形成最高效的特征谱,得到的分类结果具有一定的可解释性,而且由于其运行速度快、内存占用小,因此非常适用于学习辅助软件等方面。以此算法为基础,开发了相应的个性化学习平台。该算法使古诗文分类的准确率由93.84%提升到了99%。The improvement of computer computing power has led to the rapid development of deep learning algorithms.However,due to the special word order,wording,structure,sentence structure,grammatical structure,and expression of ancient poetry,deep learning models need to consume more computing power for feature extraction,etc.Therefore,it has not been widely used in this field.As a result,a new kind neural network:the adaptive feature spectrum neural network was proposed,which can considerably reduce the computation and adaptively select the features that are the most useful for classification in order to form the most efficient feature spectrum.The classification results obtained have certain interpretability.Moreover,its fast running speed and lower RAM consumption make it very suitable for learning aids software,and other fields.Based on this algorithm,a corresponding personalized learning platform was developed.This algorithm improves the classification accuracy of ancient Chinese poetry from 93.84%to 99%.

关 键 词：自适应特征谱 神经网络 文本分类 古诗词 拉普拉斯矩阵 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] O29[自动化与计算机技术—控制科学与工程]