VisCGEC: Benchmarking the Visual Chinese Grammatical Error Correction

Chinese Grammatical Error Correction (CGEC) plays a significant role in providing automatic feedback to students' writing, especially for Chinese as a Foreign Language Learner (CFL). Particularly, rudimentary CFLs write Chinese characters where phonological and visual confusion is constantly involved. However, existing CGEC studies ignore the multi-modality and potential faked errors (i.e., non-existent characters created due to writing errors), which pushes the techniques far away from real-world scenarios. To address this gap, we develop a dataset, namely VisCGEC, to benchmark the visual Chinese grammatical error correction for Chinese as a Foreign Language Learner (CFL). The dataset contains 2,451 images of handwritten sentences with grammatical errors and corresponding correction texts, which Chinese language experts meticulously annotate. In addition, we propose baseline approaches on VisCGEC and conduct experiments with two CGEC frameworks (i.e., a two-stage pipeline and an end-to-end system), providing a strong baseline for future research. Extensive empirical results and analyses demonstrate that VisCGEC is high-quality but challenging, where the best approach achieves an F_0.5 score of only 28.9%. Our dataset and baseline methods are available at https://github.com/xiaoAugenstern/VisCGEC.