Multi-Channel CNN-BiLSTM for Chinese grammatical error detection

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

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

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 languageEnglish
Title of host publicationICCE 2020 - 28th International Conference on Computers in Education, Proceedings
EditorsHyo-Jeong So, Ma. Mercedes Rodrigo, Jon Mason, Antonija Mitrovic, Daniel Bodemer, Weichao Chen, Zhi-Hong Chen, Brendan Flanagan, Marc Jansen, Roger Nkambou, Longkai Wu
PublisherAsia-Pacific Society for Computers in Education
Pages558-560
Number of pages3
ISBN (Electronic)9789869721455
StatePublished - 23 Nov 2020
Event28th International Conference on Computers in Education, ICCE 2020 - Virtual, Online
Duration: 23 Nov 202027 Nov 2020

Publication series

NameICCE 2020 - 28th International Conference on Computers in Education, Proceedings
Volume1

Conference

Conference28th International Conference on Computers in Education, ICCE 2020
CityVirtual, Online
Period23/11/2027/11/20

Keywords

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

Fingerprint

Dive into the research topics of 'Multi-Channel CNN-BiLSTM for Chinese grammatical error detection'. Together they form a unique fingerprint.

Cite this