修订:一种在实际信息系统中利用数据污染策略修订OCR文本的框架
Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy
AI总结:
本文提出Revise框架,通过修正OCR文本的字符、词和结构层面错误,提升文档信息的结构化表示和管理能力,从而增强文档检索和问答任务的性能。
摘要:
近年来,大语言模型(LLMs)的进展显著提升了文档AI领域,展示了在文档理解任务如问答中的出色表现。然而,现有方法主要专注于解决特定任务,缺乏对文档信息进行结构化组织和管理的能力。为解决这一限制,我们提出了Revise框架,该框架系统性地修正OCR引入的字符、词和结构层面的错误。具体而言,Revise采用了一种全面的层次化常见OCR错误分类法,并采用合成数据生成策略来真实模拟此类错误,以训练一个有效的修正模型。实验结果表明,Revise能够有效修正OCR输出,使文档内容的表示更加结构化和系统化。因此,我们的方法显著提高了文档检索和问答任务的下游性能,突显了克服现有文档AI框架结构管理限制的潜力。
英文摘要:
Recent advances in Large Language Models (LLMs) have significantly improved the field of Document AI, demonstrating remarkable performance on document understanding tasks such as question answering. However, existing approaches primarily focus on solving specific tasks, lacking the capability to structurally organize and manage document information. To address this limitation, we propose Revise, a framework that systematically corrects errors introduced by OCR at the character, word, and structural levels. Specifically, Revise employs a comprehensive hierarchical taxonomy of common OCR errors and a synthetic data generation strategy that realistically simulates such errors to train an effective correction model. Experimental results demonstrate that Revise effectively corrects OCR outputs, enabling more structured representation and systematic management of document contents. Consequently, our method significantly enhances downstream performance in document retrieval and question answering tasks, highlighting the potential to overcome the structural management limitations of existing Document AI frameworks.
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。