An Error-Guided Correction Model for Chinese Spelling Error Correction

TL;DR

This paper introduces an error-guided correction model for Chinese spelling correction that leverages BERT for zero-shot error detection, incorporates a new loss function, and supports parallel decoding, significantly improving accuracy and speed.

Contribution

The paper presents a novel error-guided correction model with zero-shot error detection and a new loss function, enhancing Chinese spelling correction accuracy and efficiency.

Findings

Achieves superior correction performance over state-of-the-art methods.

Demonstrates high correction accuracy on benchmark datasets.

Supports highly parallel decoding for real-time applications.

Abstract

Although existing neural network approaches have achieved great success on Chinese spelling correction, there is still room to improve. The model is required to avoid over-correction and to distinguish a correct token from its phonological and visually similar ones. In this paper, we propose an error-guided correction model (EGCM) to improve Chinese spelling correction. By borrowing the powerful ability of BERT, we propose a novel zero-shot error detection method to do a preliminary detection, which guides our model to attend more on the probably wrong tokens in encoding and to avoid modifying the correct tokens in generating. Furthermore, we introduce a new loss function to integrate the error confusion set, which enables our model to distinguish easily misused tokens. Moreover, our model supports highly parallel decoding to meet real application requirements. Experiments are conducted on widely used benchmarks. Our model achieves superior performance against state-of-the-art approaches by a remarkable margin, on both the correction quality and computation speed.