高精度解析PDF图文元素，提升文档理解与问答效果
Lightweight and Production-Ready PDF Visual Element Parsing
- 融合空间规律、版面分析与语义相似度，精准识别图文元素
- 检测准确率超96%，图注关联准确率达93%，优于现有方法
- 轻量部署于生产环境，推理延迟降低两倍以上，适合实际应用
PDF文档包含关键视觉元素如图表、表格和表单，其准确提取对文档理解及多模态检索增强生成（RAG）至关重要。现有解析工具常遗漏复杂图形、提取无用元素（如水印、标志）、导致元素碎片化，且无法可靠关联图注与对应内容，影响下游检索与问答性能。本文提出一种轻量级、可投入生产的PDF解析框架，结合空间规则、版面分析与语义相似性，实现视觉元素的精准检测与图注关联。在主流基准数据集及内部产品数据上，该方案视觉元素检测准确率≥96%，图注关联准确率达93%。作为多模态RAG预处理步骤，显著优于当前最优解析器与大型视觉语言模型，在内部数据与MMDocRAG基准上表现更优，同时延迟降低超过2倍。系统已在复杂生产环境中成功部署。
原文摘要 · Abstract (English)
PDF documents contain critical visual elements such as figures, tables, and forms whose accurate extraction is essential for document understanding and multimodal retrieval-augmented generation (RAG). Existing PDF parsers often miss complex visuals, extract non-informative artifacts (e.g., watermarks, logos), produce fragmented elements, and fail to reliably associate captions with their corresponding elements, which degrades downstream retrieval and question answering. We present a lightweight and production level PDF parsing framework that can accurately detect visual elements and associates captions using a combination of spatial heuristics, layout analysis, and semantic similarity. On popular benchmark datasets and internal product data, the proposed solution achieves $\geq96\%$ visual element detection accuracy and $93\%$ caption association accuracy. When used as a preprocessing step for multimodal RAG, it significantly outperforms state-of-the-art parsers and large vision-language models on both internal data and the MMDocRAG benchmark, while reducing latency by over $2\times$. We have deployed the proposed system in challenging production environment.
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。