An Unsupervised Domain-Adaptive Framework for Chinese Spelling Checking

Chinese Spelling Check (CSC) is a meaningful task in the area of natural language processing, which aims at detecting spelling errors in Chinese texts and then correcting these errors. Current typical CSC models have shown impressive performance in general datasets with the help of pretrained language models such as BERT, but they suffer great performance loss in downstream tasks with domain-specific terms because they are primarily trained on general corpora. To verify the cross-domain adaptation ability of these models, we build three new datasets with abundant domain-specific terms on financial, medical, and legal domains and conduct empirical investigations on them in the corresponding domain-specific test datasets to verify the cross-domain adaptation ability. In response to the poor performance of the existing models, we propose a framework named uChecker, which utilizes an unsupervised method in spelling error detection and correction. Experimental results prove that uChecker can perform well in domain-specific test datasets while not losing its performance in the general domain.