Chinese teaching material readability assessment with contextual information

Hao Liu, Si Li, Jianbo Zhao, Zuyi Bao, Xiaopeng Bai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Readability of an article indicates its level in terms of reading comprehension in general. Readability assessment is a process that measures the reading level of a piece of text, which can help in finding reading materials suitable for readers. In this paper, we aim to evaluate the readability about the Chinese teaching material aimed at second language (L2) learners. We introduce the neural network models to the readability assessment task for the first time. In order to capture the contextual information for readability assessment, we employ Convolutional Neural Network (CNN) to capture hidden local features. Then we use bi-directional Long Short-Term Memory Networks (bi-LSTM) neural network to combine the past and future information together. Experiment results show that our model achieves competitive performance.

Original languageEnglish
Title of host publicationProceedings of the 2017 International Conference on Asian Language Processing, IALP 2017
EditorsRong Tong, Yue Zhang, Yanfeng Lu, Minghui Dong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages66-69
Number of pages4
ISBN (Electronic)9781538619803
DOIs
StatePublished - 2 Jul 2017
Event21st International Conference on Asian Language Processing, IALP 2017 - Singapore, Singapore
Duration: 5 Dec 20177 Dec 2017

Publication series

NameProceedings of the 2017 International Conference on Asian Language Processing, IALP 2017
Volume2018-January

Conference

Conference21st International Conference on Asian Language Processing, IALP 2017
Country/TerritorySingapore
CitySingapore
Period5/12/177/12/17

Keywords

  • Convolutional Neural Network
  • Long Short-Term Memory Networks
  • Readability Assessment

Fingerprint

Dive into the research topics of 'Chinese teaching material readability assessment with contextual information'. Together they form a unique fingerprint.

Cite this