文件解析揭示：結構化資訊提取的技術、挑戰和前景

Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction

October 28, 2024

作者: Qintong Zhang, Victor Shea-Jay Huang, Bin Wang, Junyuan Zhang, Zhengren Wang, Hao Liang, Shawn Wang, Matthieu Lin, Wentao Zhang, Conghui He

cs.AI

摘要

文件解析對於將非結構化和半結構化文件（如合同、學術論文和發票）轉換為結構化、可供機器讀取的數據至關重要。文件解析從非結構化輸入中提取可靠的結構化數據，為眾多應用提供了巨大的便利。特別是隨著大型語言模型的最新成就，文件解析在知識庫構建和訓練數據生成中發揮著不可或缺的作用。本調查全面回顧了當前文件解析的狀態，涵蓋了從模塊化管道系統到由大型視覺語言模型驅動的端到端模型的關鍵方法論。詳細研究了佈局檢測、內容提取（包括文本、表格和數學表達式）以及多模態數據集成等核心組件。此外，本文討論了模塊化文件解析系統和視覺語言模型在處理複雜佈局、集成多個模塊和識別高密度文本方面面臨的挑戰。強調了發展更大更多樣化數據集的重要性，並概述了未來的研究方向。

English

Document parsing is essential for converting unstructured and semi-structured documents-such as contracts, academic papers, and invoices-into structured, machine-readable data. Document parsing extract reliable structured data from unstructured inputs, providing huge convenience for numerous applications. Especially with recent achievements in Large Language Models, document parsing plays an indispensable role in both knowledge base construction and training data generation. This survey presents a comprehensive review of the current state of document parsing, covering key methodologies, from modular pipeline systems to end-to-end models driven by large vision-language models. Core components such as layout detection, content extraction (including text, tables, and mathematical expressions), and multi-modal data integration are examined in detail. Additionally, this paper discusses the challenges faced by modular document parsing systems and vision-language models in handling complex layouts, integrating multiple modules, and recognizing high-density text. It emphasizes the importance of developing larger and more diverse datasets and outlines future research directions.