Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model
| Autor: | Tan Yuanpeng, Guang Chen, Zhiqing Lin, Haibo Lan, Guirong Shi, Jianbo Zhao, Si Li, Xu Huifang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Sequence
General Computer Science Machine translation Computer science General Engineering 020206 networking & telecommunications Context (language use) 02 engineering and technology computer.software_genre Convolutional neural network Convolution Recurrent neural network Kernel (image processing) Chinese grammatical error correction sequence to sequence 0202 electrical engineering electronic engineering information engineering Embedding 020201 artificial intelligence & image processing General Materials Science lcsh:Electrical engineering. Electronics. Nuclear engineering convolutional Algorithm computer lcsh:TK1-9971 |
| Zdroj: | IEEE Access, Vol 7, Pp 72905-72913 (2019) |
| ISSN: | 2169-3536 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|