{"title":"中文文本可读性的CNN模型","authors":"Han Feng, Sizai Hou, Le-Yin Wei, Ding-Xuan Zhou","doi":"10.3934/mfc.2022021","DOIUrl":null,"url":null,"abstract":"<p style='text-indent:20px;'>Readability of Chinese texts considered in this paper is a multi-class classification problem with <inline-formula><tex-math id=\"M1\">\\begin{document}$ 12 $\\end{document}</tex-math></inline-formula> grade classes corresponding to <inline-formula><tex-math id=\"M2\">\\begin{document}$ 6 $\\end{document}</tex-math></inline-formula> grades in primary schools, <inline-formula><tex-math id=\"M3\">\\begin{document}$ 3 $\\end{document}</tex-math></inline-formula> grades in middle schools, and <inline-formula><tex-math id=\"M4\">\\begin{document}$ 3 $\\end{document}</tex-math></inline-formula> grades in high schools. A special property of this problem is the strong ambiguity in determining the grades. To overcome the difficulty, a measurement of readability assessment methods used empirically in practice is adjacent accuracy in addition to exact accuracy. In this paper we give mathematical definitions of these concepts in a learning theory framework and compare these two quantities in terms of the ambiguity level of texts. A deep learning algorithm is proposed for readability of Chinese texts, based on convolutional neural networks and a pre-trained BERT model for vector representations of Chinese characters. The proposed CNN model can extract sentence and text features by convolutions of sentence representations with filters and is efficient for readability assessment, which is demonstrated with some numerical experiments.</p>","PeriodicalId":93334,"journal":{"name":"Mathematical foundations of computing","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"19","resultStr":"{\"title\":\"CNN models for readability of Chinese texts\",\"authors\":\"Han Feng, Sizai Hou, Le-Yin Wei, Ding-Xuan Zhou\",\"doi\":\"10.3934/mfc.2022021\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p style='text-indent:20px;'>Readability of Chinese texts considered in this paper is a multi-class classification problem with <inline-formula><tex-math id=\\\"M1\\\">\\\\begin{document}$ 12 $\\\\end{document}</tex-math></inline-formula> grade classes corresponding to <inline-formula><tex-math id=\\\"M2\\\">\\\\begin{document}$ 6 $\\\\end{document}</tex-math></inline-formula> grades in primary schools, <inline-formula><tex-math id=\\\"M3\\\">\\\\begin{document}$ 3 $\\\\end{document}</tex-math></inline-formula> grades in middle schools, and <inline-formula><tex-math id=\\\"M4\\\">\\\\begin{document}$ 3 $\\\\end{document}</tex-math></inline-formula> grades in high schools. A special property of this problem is the strong ambiguity in determining the grades. To overcome the difficulty, a measurement of readability assessment methods used empirically in practice is adjacent accuracy in addition to exact accuracy. In this paper we give mathematical definitions of these concepts in a learning theory framework and compare these two quantities in terms of the ambiguity level of texts. A deep learning algorithm is proposed for readability of Chinese texts, based on convolutional neural networks and a pre-trained BERT model for vector representations of Chinese characters. The proposed CNN model can extract sentence and text features by convolutions of sentence representations with filters and is efficient for readability assessment, which is demonstrated with some numerical experiments.</p>\",\"PeriodicalId\":93334,\"journal\":{\"name\":\"Mathematical foundations of computing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"19\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Mathematical foundations of computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3934/mfc.2022021\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, THEORY & METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mathematical foundations of computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3934/mfc.2022021","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 19
摘要
Readability of Chinese texts considered in this paper is a multi-class classification problem with \begin{document}$ 12 $\end{document} grade classes corresponding to \begin{document}$ 6 $\end{document} grades in primary schools, \begin{document}$ 3 $\end{document} grades in middle schools, and \begin{document}$ 3 $\end{document} grades in high schools. A special property of this problem is the strong ambiguity in determining the grades. To overcome the difficulty, a measurement of readability assessment methods used empirically in practice is adjacent accuracy in addition to exact accuracy. In this paper we give mathematical definitions of these concepts in a learning theory framework and compare these two quantities in terms of the ambiguity level of texts. A deep learning algorithm is proposed for readability of Chinese texts, based on convolutional neural networks and a pre-trained BERT model for vector representations of Chinese characters. The proposed CNN model can extract sentence and text features by convolutions of sentence representations with filters and is efficient for readability assessment, which is demonstrated with some numerical experiments.
Readability of Chinese texts considered in this paper is a multi-class classification problem with \begin{document}$ 12 $\end{document} grade classes corresponding to \begin{document}$ 6 $\end{document} grades in primary schools, \begin{document}$ 3 $\end{document} grades in middle schools, and \begin{document}$ 3 $\end{document} grades in high schools. A special property of this problem is the strong ambiguity in determining the grades. To overcome the difficulty, a measurement of readability assessment methods used empirically in practice is adjacent accuracy in addition to exact accuracy. In this paper we give mathematical definitions of these concepts in a learning theory framework and compare these two quantities in terms of the ambiguity level of texts. A deep learning algorithm is proposed for readability of Chinese texts, based on convolutional neural networks and a pre-trained BERT model for vector representations of Chinese characters. The proposed CNN model can extract sentence and text features by convolutions of sentence representations with filters and is efficient for readability assessment, which is demonstrated with some numerical experiments.