通过插件模块增强模型对专业术语的纠错能力。
Research on Domain-Specific Chinese Spelling Correction Method Based on Plugin Extension Modules
- 设计可扩展的插件模块，学习领域专用术语特征。
- 在医疗、法律、公文领域纠错准确率显著提升。
- 不牺牲通用纠错能力，适合垂直领域应用。
本文提出一种基于插件扩展模块的中文拼写纠错方法，旨在解决现有模型在处理领域文本时性能不佳的问题。传统中文拼写纠错模型通常在通用领域数据集上训练，导致在遇到专业术语时表现较差。为此，我们设计了一个能够学习领域专用术语特征的扩展模块，从而提升模型在特定领域的纠错能力。该扩展模块可在不损害模型通用纠错性能的前提下，为模型提供领域知识，显著提高其在专业领域的准确性。实验结果表明，集成医疗、法律和公文领域扩展模块后，模型的纠错性能相比无扩展模块的基线模型有明显提升。
原文摘要 · Abstract (English)
This paper proposes a Chinese spelling correction method based on plugin extension modules, aimed at addressing the limitations of existing models in handling domain-specific texts. Traditional Chinese spelling correction models are typically trained on general-domain datasets, resulting in poor performance when encountering specialized terminology in domain-specific texts. To address this issue, we design an extension module that learns the features of domain-specific terminology, thereby enhancing the model's correction capabilities within specific domains. This extension module can provide domain knowledge to the model without compromising its general spelling correction performance, thus improving its accuracy in specialized fields. Experimental results demonstrate that after integrating extension modules for medical, legal, and official document domains, the model's correction performance is significantly improved compared to the baseline model without any extension modules.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。