EdaCSC: Two Easy Data Augmentation Methods for Chinese Spelling Correction
This work addresses limitations in Chinese spelling correction for real-world applications, though it is incremental as it builds on existing data augmentation techniques.
The paper tackles the problem of Chinese spelling correction by proposing two data augmentation methods to improve model performance on sentences with multiple typos and reduce overcorrection, achieving state-of-the-art results on the SIGHAN15 test set.
Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in Chinese sentences caused by phonetic or visual similarities. While current CSC models integrate pinyin or glyph features and have shown significant progress,they still face challenges when dealing with sentences containing multiple typos and are susceptible to overcorrection in real-world scenarios. In contrast to existing model-centric approaches, we propose two data augmentation methods to address these limitations. Firstly, we augment the dataset by either splitting long sentences into shorter ones or reducing typos in sentences with multiple typos. Subsequently, we employ different training processes to select the optimal model. Experimental evaluations on the SIGHAN benchmarks demonstrate the superiority of our approach over most existing models, achieving state-of-the-art performance on the SIGHAN15 test set.