AI RESEARCH
Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction
arXiv CS.AI
•
ArXi:2410.21169v5 Announce Type: replace-cross Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG). This survey provides a comprehensive and timely review of document parsing research. We propose a systematic taxonomy that organizes existing approaches into modular pipeline-based systems and unified models driven by Vision-Language Models (VLMs.