An Error-Guided Correction Model for Chinese Spelling Error Correction
This work addresses the challenge of avoiding over-correction and distinguishing correct tokens from similar ones in Chinese spelling correction, which is incremental but offers practical improvements for language processing applications.
The paper tackles the problem of Chinese spelling error correction by proposing an error-guided correction model (EGCM) that improves accuracy and speed, achieving superior performance against state-of-the-art approaches with notable gains in both correction quality and computation speed.
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.