Block the Label and Noise: An N-Gram Masked Speller for Chinese Spell Checking. (arXiv:2305.03314v1 [cs.CL])

Recently, Chinese Spell Checking(CSC), a task to detect erroneous characters
in a sentence and correct them, has attracted extensive interest because of its
wide applications in various NLP tasks. Most of the existing methods have
utilized BERT to extract semantic information for CSC task. However, these
methods directly take sentences with only a few errors as inputs, where the
correct characters may leak answers to the model and dampen its ability to
capture distant context; while the erroneous characters may …

applications arxiv bert characters chinese extract information nlp noise semantic spell