Alirector：对齐增强的中文语法错误纠正器
Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector
AI总结：
本文提出一种适用于Seq2Seq模型和仅解码器LLMs的对齐增强纠正器，通过初始纠正、双向对齐及知识迁移有效缓解中文语法错误纠正中的过度纠正问题并提升整体性能。
摘要：
中文语法错误纠正（CGEC）在采用自回归生成模型（如序列到序列（Seq2Seq）模型和仅解码器大语言模型（LLMs））时，面临严重的过度纠正挑战。虽然先前的方法旨在解决 Seq2Seq 模型中的过度纠正问题，但它们难以适应仅解码器 LLMs。在本文中，我们提出了一种对齐增强纠正器来解决过度纠正问题，适用于 Seq2Seq 模型和仅解码器 LLMs。我们的方法首先训练一个纠正模型，生成源句子的初始纠正。然后，将源句子与初始纠正结合，输入对齐模型进行另一轮纠正，旨在强制对齐模型关注潜在的过度纠正。此外，为了增强模型识别细微差别的能力，我们进一步探索了源句子与初始纠正的逆向对齐。最后，我们将两个对齐模型的对齐知识迁移到纠正模型，指导其如何避免过度纠正。在三个 CGEC 数据集上的实验结果证明了我们的方法在缓解过度纠正和提升整体性能方面的有效性。我们的代码已公开。
英文摘要：
Chinese grammatical error correction (CGEC) faces serious overcorrection challenges when employing autoregressive generative models such as sequence-to-sequence (Seq2Seq) models and decoder-only large language models (LLMs). While previous methods aim to address overcorrection in Seq2Seq models, they are difficult to adapt to decoder-only LLMs. In this paper, we propose an alignment-enhanced corrector for the overcorrection problem that applies to both Seq2Seq models and decoder-only LLMs. Our method first trains a correction model to generate an initial correction of the source sentence. Then, we combine the source sentence with the initial correction and feed it through an alignment model for another round of correction, aiming to enforce the alignment model to focus on potential overcorrection. Moreover, to enhance the model's ability to identify nuances, we further explore the reverse alignment of the source sentence and the initial correction. Finally, we transfer the alignment knowledge from two alignment models to the correction model, instructing it on how to avoid overcorrection. Experimental results on three CGEC datasets demonstrate the effectiveness of our approach in alleviating overcorrection and improving overall performance. Our code has been made 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。
