用检索增强迭代修正，提升中文拼写纠错在专业领域的表现
RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction
- 构建领域自适应检索语料库，通过微调检索器捕捉纠错模式
- 支持变长纠错，显著提升LLM在专业场景下的纠错准确率
- 适合需要精准领域纠错的NLP应用，如医疗、法律文本处理
中文拼写纠错（CSC）旨在检测并修正句子中的错误词汇。传统方法聚焦等长纠错，依赖预训练语言模型（PLMs）。尽管大语言模型（LLMs）在识别和纠正潜在错误方面表现优异，但在面对专业领域术语时往往难以适应。为此，我们提出一种检索增强的迭代修正框架（RAIR）。该方法从领域特定训练数据与词典中自适应构建检索语料库，并使用微调后的检索器确保捕获纠错模式。同时，将等长纠错扩展至变长纠错场景。大量实验表明，该框架在领域拼写纠错任务上优于现有方法，并显著提升LLMs在变长场景下的性能。
原文摘要 · Abstract (English)
Chinese Spelling Correction (CSC) aims to detect and correct erroneous tokens in sentences. Traditional CSC focuses on equal length correction and uses pretrained language models (PLMs). While Large Language Models (LLMs) have shown remarkable success in identifying and rectifying potential errors, they often struggle with adapting to domain-specific corrections, especially when encountering terminologies in specialized domains. To address domain adaptation, we propose a \textbf{R}etrieval-\textbf{A}ugmented \textbf{I}terative \textbf{R}efinement (RAIR) framework. Our approach constructs a retrieval corpus adaptively from domain-specific training data and dictionaries, employing a fine-tuned retriever to ensure that the retriever catches the error correction pattern. We also extend equal-length into variable-length correction scenarios. Extensive experiments demonstrate that our framework outperforms current approaches in domain spelling correction and significantly improves the performance of LLMs in variable-length scenarios.
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。