Chinese Spell Checking (CSC) task aims to detect and correct Chinese spelling errors. Recently, related researches focus on introducing character similarity from confusion set to enhance the CSC models, ignoring the context of characters that contain richer information. To make better use of contextual information, we propose a simple yet effective Curriculum Learning (CL) framework for the CSC task. With the help of our model-agnostic CL framework, existing CSC models will be trained from easy to difficult as humans learn Chinese characters and achieve further performance improvements. Extensive experiments and detailed analyses on widely used SIGHAN datasets show that our method outperforms previous state-of-the-art methods. More instructively, our study empirically suggests that contextual similarity is more valuable than character similarity for the CSC task.

翻译：中文拼写检查（CSC）任务旨在检测并纠正中文拼写错误。近年来，相关研究聚焦于从混淆集引入字符相似性以增强CSC模型，却忽略了包含更丰富信息的字符上下文。为更充分利用上下文信息，我们提出了一种简单而有效的课程学习（Curriculum Learning, CL）框架用于CSC任务。借助我们这种与模型无关的CL框架，现有CSC模型将像人类学习汉字一样，从易到难进行训练，并实现性能的进一步提升。在广泛使用的SIGHAN数据集上进行的大量实验和详细分析表明，我们的方法优于先前的最优方法。更具启发性的是，我们的研究实证表明，对于CSC任务，上下文字符相似性比字符相似性更有价值。