Chinese Grammatical Correction Using BERT-based Pre-trained Model
Chinese Grammatical Correction Using BERT-based Pre-trained Model
复制标题
DOI：
--
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Hongfei Wang;Michiki Kurosawa;Satoru Katsumata;Mamoru Komachi
中科院分区：
文献类型：
--
作者：
Hongfei Wang;Michiki Kurosawa;Satoru Katsumata;Mamoru Komachi
近年来，预训练模型得到了广泛的研究，一些下游任务也受益于它们的利用。在本研究中，我们验证了两种将预训练模型合并到编码器-解码器模型中的方法在中文语法纠错任务上的有效性。我们还分析了错误类型并得出结论，句子级错误尚未得到解决。
In recent years, pre-trained models have been extensively studied, and several downstream tasks have benefited from their utilization. In this study, we verify the effectiveness of two methods that incorporate a pre-trained model into an encoder-decoder model on Chinese grammatical error correction tasks. We also analyze the error type and conclude that sentence-level errors are yet to be addressed.