GECToR --语法错误更正：标记，不重写
GECToR -- Grammatical Error Correction: Tag, Not Rewrite
摘要：
在本文中，我们提出了一个简单而有效的GEC序列标签使用Transformer编码器。我们的系统在合成数据上进行预训练，然后分两个阶段进行微调：第一阶段是在有错误的语料库上，第二阶段是在有错误和无错误的并行语料库的组合上。我们设计了自定义的令牌级转换，以将输入令牌映射到目标更正。我们最好的单模型/集合GEC标记器在CoNLL-2014（测试）上实现了65.3/66.5的$F_{0.5}$，在NLL-2019（测试）上实现了72.4/73.6的$F_{0.5}$。它的推理速度是基于transformer的seq 2seq GEC系统的10倍。代码和训练模型是公开的。
英文摘要：
In this paper, we present a simple and efficient GEC sequence tagger using a Transformer encoder. Our system is pre-trained on synthetic data and then fine-tuned in two stages: first on errorful corpora, and second on a combination of errorful and error-free parallel corpora. We design custom token-level transformations to map input tokens to target corrections. Our best single-model/ensemble GEC tagger achieves an $F_{0.5}$ of 65.3/66.5 on CoNLL-2014 (test) and $F_{0.5}$ of 72.4/73.6 on BEA-2019 (test). Its inference speed is up to 10 times as fast as a Transformer-based seq2seq GEC system. The code and trained models are publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
