The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking
This work addresses a specific issue in Chinese spell checking for users of Chinese text, but it is incremental as it builds on existing CSC methods.
The paper tackles the problem of Chinese Spell Checking (CSC) by addressing the gap between pre-trained language models' semantic focus and the need for ground-truth corrections, proposing the ECOPO framework that refines model knowledge to avoid common erroneous predictions, achieving better performance on SIGHAN datasets.
Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors, which are mainly caused by the phonological or visual similarity. Recently, pre-trained language models (PLMs) promote the progress of CSC task. However, there exists a gap between the learned knowledge of PLMs and the goal of CSC task. PLMs focus on the semantics in text and tend to correct the erroneous characters to semantically proper or commonly used ones, but these aren't the ground-truth corrections. To address this issue, we propose an Error-driven COntrastive Probability Optimization (ECOPO) framework for CSC task. ECOPO refines the knowledge representations of PLMs, and guides the model to avoid predicting these common characters through an error-driven way. Particularly, ECOPO is model-agnostic and it can be combined with existing CSC methods to achieve better performance. Extensive experiments and detailed analyses on SIGHAN datasets demonstrate that ECOPO is simple yet effective.