Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model
Chinese grammatical error correction (CGEC) is practically useful for learners of Chinese as a second language, but it is a rather challenging task due to the complex and flexible nature of Chinese language so that existing methods for English cannot be directly applied. In this paper, we introduce...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8717692/ |
| _version_ | 1818621623429758976 |
|---|---|
| author | Si Li Jianbo Zhao Guirong Shi Yuanpeng Tan Huifang Xu Guang Chen Haibo Lan Zhiqing Lin |
| author_facet | Si Li Jianbo Zhao Guirong Shi Yuanpeng Tan Huifang Xu Guang Chen Haibo Lan Zhiqing Lin |
| author_sort | Si Li |
| collection | DOAJ |
| description | Chinese grammatical error correction (CGEC) is practically useful for learners of Chinese as a second language, but it is a rather challenging task due to the complex and flexible nature of Chinese language so that existing methods for English cannot be directly applied. In this paper, we introduce a convolutional sequence to sequence model into the CGEC task for the first time, since many Chinese grammatical errors are concentrated between three and four words and convolutional neural network can better capture the local context. A convolution-based model can obtain the representations of the context by fixed size kernel. By stacking convolution layers, long-term dependences can be obtained. We also propose two optimization methods, shared embedding and policy gradient, to optimize the convolutional sequence to sequence model through sharing parameters and reconstructing loss function. Besides, we collate the existing Chinese grammatical correction corpus in detail. The results show that the models we proposed two different optimization methods both achieve large improvement compared with the natural machine translation model based on a recurrent neural network. |
| first_indexed | 2024-12-16T18:12:13Z |
| format | Article |
| id | doaj.art-fb098062980849e5a89824b3694cfe1f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T18:12:13Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fb098062980849e5a89824b3694cfe1f2022-12-21T22:21:44ZengIEEEIEEE Access2169-35362019-01-017729057291310.1109/ACCESS.2019.29176318717692Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence ModelSi Li0Jianbo Zhao1https://orcid.org/0000-0003-3755-4691Guirong Shi2Yuanpeng Tan3Huifang Xu4Guang Chen5Haibo Lan6Zhiqing Lin7School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, ChinaState Grid Jibei Electric Power Company Limited, Beijing, ChinaChina Electric Power Research Institute, Beijing, ChinaChina Electric Power Research Institute, Beijing, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, ChinaState Grid Jibei Electric Power Company Limited, Beijing, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, ChinaChinese grammatical error correction (CGEC) is practically useful for learners of Chinese as a second language, but it is a rather challenging task due to the complex and flexible nature of Chinese language so that existing methods for English cannot be directly applied. In this paper, we introduce a convolutional sequence to sequence model into the CGEC task for the first time, since many Chinese grammatical errors are concentrated between three and four words and convolutional neural network can better capture the local context. A convolution-based model can obtain the representations of the context by fixed size kernel. By stacking convolution layers, long-term dependences can be obtained. We also propose two optimization methods, shared embedding and policy gradient, to optimize the convolutional sequence to sequence model through sharing parameters and reconstructing loss function. Besides, we collate the existing Chinese grammatical correction corpus in detail. The results show that the models we proposed two different optimization methods both achieve large improvement compared with the natural machine translation model based on a recurrent neural network.https://ieeexplore.ieee.org/document/8717692/Chinese grammatical error correctionsequence to sequenceconvolutional |
| spellingShingle | Si Li Jianbo Zhao Guirong Shi Yuanpeng Tan Huifang Xu Guang Chen Haibo Lan Zhiqing Lin Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model IEEE Access Chinese grammatical error correction sequence to sequence convolutional |
| title | Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model |
| title_full | Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model |
| title_fullStr | Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model |
| title_full_unstemmed | Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model |
| title_short | Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model |
| title_sort | chinese grammatical error correction based on convolutional sequence to sequence model |
| topic | Chinese grammatical error correction sequence to sequence convolutional |
| url | https://ieeexplore.ieee.org/document/8717692/ |
| work_keys_str_mv | AT sili chinesegrammaticalerrorcorrectionbasedonconvolutionalsequencetosequencemodel AT jianbozhao chinesegrammaticalerrorcorrectionbasedonconvolutionalsequencetosequencemodel AT guirongshi chinesegrammaticalerrorcorrectionbasedonconvolutionalsequencetosequencemodel AT yuanpengtan chinesegrammaticalerrorcorrectionbasedonconvolutionalsequencetosequencemodel AT huifangxu chinesegrammaticalerrorcorrectionbasedonconvolutionalsequencetosequencemodel AT guangchen chinesegrammaticalerrorcorrectionbasedonconvolutionalsequencetosequencemodel AT haibolan chinesegrammaticalerrorcorrectionbasedonconvolutionalsequencetosequencemodel AT zhiqinglin chinesegrammaticalerrorcorrectionbasedonconvolutionalsequencetosequencemodel |