CNN MODELS FOR READABILITY OF CHINESE TEXTS

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

9 Scopus Citations
View graph of relations

Author(s)

  • Han FENG
  • Sizai HOU
  • Le-Yin WEI
  • Ding-Xuan ZHOU

Detail(s)

Original languageEnglish
Pages (from-to)351-362
Journal / PublicationMathematical Foundations of Computing
Volume5
Issue number4
Online publishedJul 2022
Publication statusPublished - Nov 2022

Abstract

Readability of Chinese texts considered in this paper is a multi-class classification problem with 12 grade classes corresponding to 6 grades in primary schools, 3 grades in middle schools, and 3 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.

Research Area(s)

  • Adjacent accuracy, Cnn, Filters, Neural networks, Readability of Chinese texts

Citation Format(s)

CNN MODELS FOR READABILITY OF CHINESE TEXTS. / FENG, Han; HOU, Sizai; WEI, Le-Yin et al.
In: Mathematical Foundations of Computing, Vol. 5, No. 4, 11.2022, p. 351-362.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review