Mining Error Templates for Grammatical Error Correction
This work addresses the labor-intensive process of rule creation for GEC systems, offering an automated solution that enhances correction accuracy, particularly in data-scarce scenarios, though it is incremental as it builds on existing rule-based approaches.
The authors tackled the problem of manually defining rules for grammatical error correction (GEC) by proposing an automatic method to mine error templates from the Internet, accumulating 1,119 templates for Chinese GEC and showing that combining these templates improves performance on a benchmark, especially for error types with limited training data.
Some grammatical error correction (GEC) systems incorporate hand-crafted rules and achieve positive results. However, manually defining rules is time-consuming and laborious. In view of this, we propose a method to mine error templates for GEC automatically. An error template is a regular expression aiming at identifying text errors. We use the web crawler to acquire such error templates from the Internet. For each template, we further select the corresponding corrective action by using the language model perplexity as a criterion. We have accumulated 1,119 error templates for Chinese GEC based on this method. Experimental results on the newly proposed CTC-2021 Chinese GEC benchmark show that combing our error templates can effectively improve the performance of a strong GEC system, especially on two error types with very little training data. Our error templates are available at \url{https://github.com/HillZhang1999/gec_error_template}.