Chinese Grammatical Error Diagnosis Based on CRF and LSTM-CRF model

Yujie Zhou, Yinan Shao, Yong Zhou


Abstract
When learning Chinese as a foreign language, the learners may have some grammatical errors due to negative migration of their native languages. However, few grammar checking applications have been developed to support the learners. The goal of this paper is to develop a tool to automatically diagnose four types of grammatical errors which are redundant words (R), missing words (M), bad word selection (S) and disordered words (W) in Chinese sentences written by those foreign learners. In this paper, a conventional linear CRF model with specific feature engineering and a LSTM-CRF model are used to solve the CGED (Chinese Grammatical Error Diagnosis) task. We make some improvement on both models and the submitted results have better performance on false positive rate and accuracy than the average of all runs from CGED2018 for all three evaluation levels.
Anthology ID:
W18-3724
Volume:
Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi
Venue:
NLP-TEA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
165–171
Language:
URL:
https://aclanthology.org/W18-3724
DOI:
10.18653/v1/W18-3724
Bibkey:
Cite (ACL):
Yujie Zhou, Yinan Shao, and Yong Zhou. 2018. Chinese Grammatical Error Diagnosis Based on CRF and LSTM-CRF model. In Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications, pages 165–171, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Chinese Grammatical Error Diagnosis Based on CRF and LSTM-CRF model (Zhou et al., NLP-TEA 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-3724.pdf