Feng Wang, Xingyi Cheng, Taifeng Wang, Yuan Qi, Weidi Xu, Wei Chu, Kunlong Chen, Shaohua Jiang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Chinese Spelling Check (CSC) is a task to detect and correct spelling errors in Chinese natural language. Existing methods have made attempts to incorporate the similarity knowledge between Chinese characters. However, they take the similarity knowledge as either an external input resource or just heuristic rules. This paper proposes to incorporate phonological and visual similarity knowledge into language models for CSC via a specialized graph convolutional network (SpellGCN). The model builds a graph over the characters, and SpellGCN is learned to map this graph into a set of inter-dependent character classifiers. These classifiers are applied to the representations extracted by another network, such as BERT, enabling the whole network to be end-to-end trainable. Experiments 1 are conducted on three human-annotated datasets. Our method achieves superior performance against previous models by a large margin.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.14166")
get_code_for_paper("2004.14166")
have("2004.14166")
Connect an agent — have() is free.