Model ensemble has been in widespread use for Grammatical Error Correction (GEC), boosting model performance. We hypothesize that model ensemble based on the perplexity (PPL) computed by pre-trained language models (PLMs) should benefit the GEC system. To this end, we explore several ensemble strategies based on strong PLMs with four sophisticated single models. However, the performance does not improve but even gets worse after the PLM-based ensemble. This surprising result sets us doing a detailed analysis on the data and coming up with some insights on GEC. The human references of correct sentences is far from sufficient in the test data, and the gap between a correct sentence and an idiomatic one is worth our attention. Moreover, the PLM-based ensemble strategies provide an effective way to extend and improve GEC benchmark data. Our source code is available at https://github.com/JamyDon/PLM-based-CGEC-Model-Ensemble.

翻译：模型集成已广泛用于语法纠错任务中，能够提升模型性能。我们假设基于预训练语言模型计算的困惑度进行模型集成应能促进语法纠错系统。为此，我们探索了基于强预训练语言模型结合四种精良单模型的多种集成策略。然而，采用基于预训练语言模型的集成后，性能非但未提升反而下降。这一出乎意料的结果促使我们对数据进行详细分析，并提出关于语法纠错的一些见解。测试数据中正确句子的标准参考答案存在严重不足，且正确句子与地道句子之间的差异值得关注。此外，基于预训练语言模型的集成策略为扩展和改善语法纠错基准数据提供了有效途径。我们的源代码可在 https://github.com/JamyDon/PLM-based-CGEC-Model-Ensemble 获取。