A Comprehensive Evaluation and Analysis Study for Chinese Spelling Check
This work addresses the evaluation limitations in CSC for researchers and practitioners, but it is incremental as it focuses on analysis rather than introducing new methods.
The study tackled the problem of evaluating Chinese Spelling Check (CSC) models by constructing comprehensive test sets and analyzing nine model structures, finding that models are sensitive to error distributions and that the SIGHAN benchmark is unreliable for performance assessment.
With the development of pre-trained models and the incorporation of phonetic and graphic information, neural models have achieved high scores in Chinese Spelling Check (CSC). However, it does not provide a comprehensive reflection of the models' capability due to the limited test sets. In this study, we abstract the representative model paradigm, implement it with nine structures and experiment them on comprehensive test sets we constructed with different purposes. We perform a detailed analysis of the results and find that: 1) Fusing phonetic and graphic information reasonably is effective for CSC. 2) Models are sensitive to the error distribution of the test set, which reflects the shortcomings of models and reveals the direction we should work on. 3) Whether or not the errors and contexts have been seen has a significant impact on models. 4) The commonly used benchmark, SIGHAN, can not reliably evaluate models' performance.