SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check

Abstract

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 (The dataset and all code for this paper are available at https://github.com/ACL2020SpellGCN/SpellGCN) are conducted on three human-annotated datasets. Our method achieves superior performance against previous models by a large margin.

arXiv commentAccepted by ACL2020

References in corpus (2)

• Decoupled Weight Decay Regularization
• Symmetric Regularization based BERT for Pair-wise Semantic Reasoning

Cited by in corpus (4)

• Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
• Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models
• Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
• An Alignment-Agnostic Model for Chinese Text Error Correction