Multi-Channel CNN-BiLSTM for Chinese grammatical error detection

Lung Hao Lee; Yuh Shyang Wang; Po Chen Lin; Chih Te Hung; Yuen Hsien Tseng

Multi-Channel CNN-BiLSTM for Chinese grammatical error detection

Lung Hao Lee, Yuh Shyang Wang, Po Chen Lin, Chih Te Hung, Yuen Hsien Tseng

Department of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

In this paper, we proposed a Multi-Channel Convolutional Neural Network with Bidirectional Long Short-Term Memory (MC-CNN-BiLSTM) model for Chinese grammatical error detection. The TOCFL learner corpus is adopted to measure the system capability of indicating whether a sentence contains errors or not. Our model performs better than a previous CNN-LSTM model that reflects the effectiveness of multi-channel embedding representation.

Original language	English
Title of host publication	ICCE 2020 - 28th International Conference on Computers in Education, Proceedings
Editors	Hyo-Jeong So, Ma. Mercedes Rodrigo, Jon Mason, Antonija Mitrovic, Daniel Bodemer, Weichao Chen, Zhi-Hong Chen, Brendan Flanagan, Marc Jansen, Roger Nkambou, Longkai Wu
Publisher	Asia-Pacific Society for Computers in Education
Pages	558-560
Number of pages	3
ISBN (Electronic)	9789869721455
State	Published - 23 Nov 2020
Event	28th International Conference on Computers in Education, ICCE 2020 - Virtual, Online Duration: 23 Nov 2020 → 27 Nov 2020

Publication series

Name	ICCE 2020 - 28th International Conference on Computers in Education, Proceedings
Volume	1

Conference

Conference	28th International Conference on Computers in Education, ICCE 2020
City	Virtual, Online
Period	23/11/20 → 27/11/20

Keywords

Chinese as a foreign language
Deep neural networks
Grammatical error diagnosis

Chinese Knowledge Base Construction and Applications for Medical Healthcare Domain(2/3)
Lee, L.-H. (PI)
1/05/20 → 30/04/21
Project: Research

Cite this

Lee, L. H., Wang, Y. S., Lin, P. C., Hung, C. T., & Tseng, Y. H. (2020). Multi-Channel CNN-BiLSTM for Chinese grammatical error detection. In H.-J. So, M. M. Rodrigo, J. Mason, A. Mitrovic, D. Bodemer, W. Chen, Z.-H. Chen, B. Flanagan, M. Jansen, R. Nkambou, & L. Wu (Eds.), ICCE 2020 - 28th International Conference on Computers in Education, Proceedings (pp. 558-560). (ICCE 2020 - 28th International Conference on Computers in Education, Proceedings; Vol. 1). Asia-Pacific Society for Computers in Education.

Lee, Lung Hao ; Wang, Yuh Shyang ; Lin, Po Chen et al. / Multi-Channel CNN-BiLSTM for Chinese grammatical error detection. ICCE 2020 - 28th International Conference on Computers in Education, Proceedings. editor / Hyo-Jeong So ; Ma. Mercedes Rodrigo ; Jon Mason ; Antonija Mitrovic ; Daniel Bodemer ; Weichao Chen ; Zhi-Hong Chen ; Brendan Flanagan ; Marc Jansen ; Roger Nkambou ; Longkai Wu. Asia-Pacific Society for Computers in Education, 2020. pp. 558-560 (ICCE 2020 - 28th International Conference on Computers in Education, Proceedings).

@inproceedings{5b3c2862f39c46a387c5ea189c832f75,

title = "Multi-Channel CNN-BiLSTM for Chinese grammatical error detection",

abstract = "In this paper, we proposed a Multi-Channel Convolutional Neural Network with Bidirectional Long Short-Term Memory (MC-CNN-BiLSTM) model for Chinese grammatical error detection. The TOCFL learner corpus is adopted to measure the system capability of indicating whether a sentence contains errors or not. Our model performs better than a previous CNN-LSTM model that reflects the effectiveness of multi-channel embedding representation.",

keywords = "Chinese as a foreign language, Deep neural networks, Grammatical error diagnosis",

author = "Lee, {Lung Hao} and Wang, {Yuh Shyang} and Lin, {Po Chen} and Hung, {Chih Te} and Tseng, {Yuen Hsien}",

note = "Publisher Copyright: {\textcopyright} ICCE 2020 - 28th International Conference on Computers in Education, Proceedings. All rights reserved.; 28th International Conference on Computers in Education, ICCE 2020 ; Conference date: 23-11-2020 Through 27-11-2020",

year = "2020",

month = nov,

day = "23",

language = "???core.languages.en_GB???",

series = "ICCE 2020 - 28th International Conference on Computers in Education, Proceedings",

publisher = "Asia-Pacific Society for Computers in Education",

pages = "558--560",

editor = "Hyo-Jeong So and Rodrigo, {Ma. Mercedes} and Jon Mason and Antonija Mitrovic and Daniel Bodemer and Weichao Chen and Zhi-Hong Chen and Brendan Flanagan and Marc Jansen and Roger Nkambou and Longkai Wu",

booktitle = "ICCE 2020 - 28th International Conference on Computers in Education, Proceedings",

}

Lee, LH, Wang, YS, Lin, PC, Hung, CT & Tseng, YH 2020, Multi-Channel CNN-BiLSTM for Chinese grammatical error detection. in H-J So, MM Rodrigo, J Mason, A Mitrovic, D Bodemer, W Chen, Z-H Chen, B Flanagan, M Jansen, R Nkambou & L Wu (eds), ICCE 2020 - 28th International Conference on Computers in Education, Proceedings. ICCE 2020 - 28th International Conference on Computers in Education, Proceedings, vol. 1, Asia-Pacific Society for Computers in Education, pp. 558-560, 28th International Conference on Computers in Education, ICCE 2020, Virtual, Online, 23/11/20.

Multi-Channel CNN-BiLSTM for Chinese grammatical error detection. / Lee, Lung Hao; Wang, Yuh Shyang; Lin, Po Chen et al.
ICCE 2020 - 28th International Conference on Computers in Education, Proceedings. ed. / Hyo-Jeong So; Ma. Mercedes Rodrigo; Jon Mason; Antonija Mitrovic; Daniel Bodemer; Weichao Chen; Zhi-Hong Chen; Brendan Flanagan; Marc Jansen; Roger Nkambou; Longkai Wu. Asia-Pacific Society for Computers in Education, 2020. p. 558-560 (ICCE 2020 - 28th International Conference on Computers in Education, Proceedings; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-Channel CNN-BiLSTM for Chinese grammatical error detection

AU - Lee, Lung Hao

AU - Wang, Yuh Shyang

AU - Lin, Po Chen

AU - Hung, Chih Te

AU - Tseng, Yuen Hsien

PY - 2020/11/23

Y1 - 2020/11/23

N2 - In this paper, we proposed a Multi-Channel Convolutional Neural Network with Bidirectional Long Short-Term Memory (MC-CNN-BiLSTM) model for Chinese grammatical error detection. The TOCFL learner corpus is adopted to measure the system capability of indicating whether a sentence contains errors or not. Our model performs better than a previous CNN-LSTM model that reflects the effectiveness of multi-channel embedding representation.

AB - In this paper, we proposed a Multi-Channel Convolutional Neural Network with Bidirectional Long Short-Term Memory (MC-CNN-BiLSTM) model for Chinese grammatical error detection. The TOCFL learner corpus is adopted to measure the system capability of indicating whether a sentence contains errors or not. Our model performs better than a previous CNN-LSTM model that reflects the effectiveness of multi-channel embedding representation.

KW - Chinese as a foreign language

KW - Deep neural networks

KW - Grammatical error diagnosis

UR - http://www.scopus.com/inward/record.url?scp=85099484280&partnerID=8YFLogxK

M3 - 會議論文篇章

AN - SCOPUS:85099484280

T3 - ICCE 2020 - 28th International Conference on Computers in Education, Proceedings

SP - 558

EP - 560

BT - ICCE 2020 - 28th International Conference on Computers in Education, Proceedings

A2 - So, Hyo-Jeong

A2 - Rodrigo, Ma. Mercedes

A2 - Mason, Jon

A2 - Mitrovic, Antonija

A2 - Bodemer, Daniel

A2 - Chen, Weichao

A2 - Chen, Zhi-Hong

A2 - Flanagan, Brendan

A2 - Jansen, Marc

A2 - Nkambou, Roger

A2 - Wu, Longkai

PB - Asia-Pacific Society for Computers in Education

T2 - 28th International Conference on Computers in Education, ICCE 2020

Y2 - 23 November 2020 through 27 November 2020

ER -

Lee LH, Wang YS, Lin PC, Hung CT, Tseng YH. Multi-Channel CNN-BiLSTM for Chinese grammatical error detection. In So HJ, Rodrigo MM, Mason J, Mitrovic A, Bodemer D, Chen W, Chen ZH, Flanagan B, Jansen M, Nkambou R, Wu L, editors, ICCE 2020 - 28th International Conference on Computers in Education, Proceedings. Asia-Pacific Society for Computers in Education. 2020. p. 558-560. (ICCE 2020 - 28th International Conference on Computers in Education, Proceedings).

Multi-Channel CNN-BiLSTM for Chinese grammatical error detection

Abstract

Publication series

Conference

Keywords

Fingerprint

Projects

Chinese Knowledge Base Construction and Applications for Medical Healthcare Domain(2/3)

Cite this