Chinese grammatical error detection using a CNN-LSTM model

Lung Hao Lee, Bo Lin Lin, Liang Chih Yu, Yuen Hsien Tseng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we proposed a Convolution Neural Network with Long Short-Term Memory (CNN-LSTM) model for Chinese grammatical error detection. The TOCFL learner corpus is adopted to measure the system performance of indicating whether a sentence contains errors or not. Our model performs better than other neural network based methods in terms of accuracy for identifying an erroneous sentence written by Chinese language learners.

Original languageEnglish
Title of host publicationProceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings
EditorsAhmad Fauzi Mohd Ayub, Antonija Mitrovic, Jie-Chi Yang, Su Luan Wong, Wenli Chen
PublisherAsia-Pacific Society for Computers in Education
Pages919-921
Number of pages3
ISBN (Print)9789869401265
Publication statusPublished - 2017 Jan 1
Event25th International Conference on Computers in Education, ICCE 2017 - Christchurch, New Zealand
Duration: 2017 Dec 42017 Dec 8

Publication series

NameProceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings

Other

Other25th International Conference on Computers in Education, ICCE 2017
CountryNew Zealand
CityChristchurch
Period17/12/417/12/8

Fingerprint

Error detection
Convolution
neural network
Neural networks
language
performance
Long short-term memory

Keywords

  • Chinese as a foreign language
  • Deep neural networks
  • Grammatical error diagnosis

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Science Applications
  • Information Systems
  • Hardware and Architecture
  • Education

Cite this

Lee, L. H., Lin, B. L., Yu, L. C., & Tseng, Y. H. (2017). Chinese grammatical error detection using a CNN-LSTM model. In A. F. Mohd Ayub, A. Mitrovic, J-C. Yang, S. L. Wong, & W. Chen (Eds.), Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings (pp. 919-921). (Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings). Asia-Pacific Society for Computers in Education.

Chinese grammatical error detection using a CNN-LSTM model. / Lee, Lung Hao; Lin, Bo Lin; Yu, Liang Chih; Tseng, Yuen Hsien.

Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings. ed. / Ahmad Fauzi Mohd Ayub; Antonija Mitrovic; Jie-Chi Yang; Su Luan Wong; Wenli Chen. Asia-Pacific Society for Computers in Education, 2017. p. 919-921 (Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, LH, Lin, BL, Yu, LC & Tseng, YH 2017, Chinese grammatical error detection using a CNN-LSTM model. in AF Mohd Ayub, A Mitrovic, J-C Yang, SL Wong & W Chen (eds), Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings. Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings, Asia-Pacific Society for Computers in Education, pp. 919-921, 25th International Conference on Computers in Education, ICCE 2017, Christchurch, New Zealand, 17/12/4.
Lee LH, Lin BL, Yu LC, Tseng YH. Chinese grammatical error detection using a CNN-LSTM model. In Mohd Ayub AF, Mitrovic A, Yang J-C, Wong SL, Chen W, editors, Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings. Asia-Pacific Society for Computers in Education. 2017. p. 919-921. (Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings).
Lee, Lung Hao ; Lin, Bo Lin ; Yu, Liang Chih ; Tseng, Yuen Hsien. / Chinese grammatical error detection using a CNN-LSTM model. Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings. editor / Ahmad Fauzi Mohd Ayub ; Antonija Mitrovic ; Jie-Chi Yang ; Su Luan Wong ; Wenli Chen. Asia-Pacific Society for Computers in Education, 2017. pp. 919-921 (Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings).
@inproceedings{c9160897ab184274a0debe3441e0dbbd,
title = "Chinese grammatical error detection using a CNN-LSTM model",
abstract = "In this paper, we proposed a Convolution Neural Network with Long Short-Term Memory (CNN-LSTM) model for Chinese grammatical error detection. The TOCFL learner corpus is adopted to measure the system performance of indicating whether a sentence contains errors or not. Our model performs better than other neural network based methods in terms of accuracy for identifying an erroneous sentence written by Chinese language learners.",
keywords = "Chinese as a foreign language, Deep neural networks, Grammatical error diagnosis",
author = "Lee, {Lung Hao} and Lin, {Bo Lin} and Yu, {Liang Chih} and Tseng, {Yuen Hsien}",
year = "2017",
month = "1",
day = "1",
language = "English",
isbn = "9789869401265",
series = "Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings",
publisher = "Asia-Pacific Society for Computers in Education",
pages = "919--921",
editor = "{Mohd Ayub}, {Ahmad Fauzi} and Antonija Mitrovic and Jie-Chi Yang and Wong, {Su Luan} and Wenli Chen",
booktitle = "Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings",

}

TY - GEN

T1 - Chinese grammatical error detection using a CNN-LSTM model

AU - Lee, Lung Hao

AU - Lin, Bo Lin

AU - Yu, Liang Chih

AU - Tseng, Yuen Hsien

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In this paper, we proposed a Convolution Neural Network with Long Short-Term Memory (CNN-LSTM) model for Chinese grammatical error detection. The TOCFL learner corpus is adopted to measure the system performance of indicating whether a sentence contains errors or not. Our model performs better than other neural network based methods in terms of accuracy for identifying an erroneous sentence written by Chinese language learners.

AB - In this paper, we proposed a Convolution Neural Network with Long Short-Term Memory (CNN-LSTM) model for Chinese grammatical error detection. The TOCFL learner corpus is adopted to measure the system performance of indicating whether a sentence contains errors or not. Our model performs better than other neural network based methods in terms of accuracy for identifying an erroneous sentence written by Chinese language learners.

KW - Chinese as a foreign language

KW - Deep neural networks

KW - Grammatical error diagnosis

UR - http://www.scopus.com/inward/record.url?scp=85053866985&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053866985&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789869401265

T3 - Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings

SP - 919

EP - 921

BT - Proceedings of the 25th International Conference on Computers in Education, ICCE 2017 - Main Conference Proceedings

A2 - Mohd Ayub, Ahmad Fauzi

A2 - Mitrovic, Antonija

A2 - Yang, Jie-Chi

A2 - Wong, Su Luan

A2 - Chen, Wenli

PB - Asia-Pacific Society for Computers in Education

ER -