When reading a document, glancing at the spatial layout of a document is an initial step to understand it roughly. Traditional document layout analysis (DLA) methods, however, offer only a superficial parsing of documents, focusing on basic instance detection and often failing to capture the nuanced spatial and logical relations between instances. These limitations hinder DLA-based models from achieving a gradually deeper comprehension akin to human reading. In this work, we propose a novel graph-based Document Structure Analysis (gDSA) task. This task requires that model not only detects document elements but also generates spatial and logical relations in form of a graph structure, allowing to understand documents in a holistic and intuitive manner. For this new task, we construct a relation graph-based document structure analysis dataset (GraphDoc) with 80K document images and 4.13M relation annotations, enabling training models to complete multiple tasks like reading order, hierarchical structures analysis, and complex inter-element relation inference. Furthermore, a document relation graph generator (DRGG) is proposed to address the gDSA task, which achieves performance with 57.6% at mAP$_g$@0.5 for a strong benchmark baseline on this novel task and dataset. We hope this graphical representation of document structure can mark an innovative advancement in document structure analysis and understanding. The new dataset and code will be made publicly available at https://yufanchen96.github.io/projects/GraphDoc.
PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
Xuzhou Medical University(徐州医科大学);Ping An Property & Casualty Insurance Company(平安产险公司)
最近,具有最先进深度学习模型的计算机视觉在光学字符识别(OCR)领域(包括文本检测和识别任务)取得了巨大成功。然而,作为OCR下游任务的文档关键信息抽取(Key Information Extraction,KIE)在现实世界中有着大量的使用场景,但由于文档中不仅有OCR系统提取的文本特征,而且还有语义视觉特征,这些特征在KIE中起着至关重要的作用,尚未得到充分利用,因此KIE仍然是一个挑战。在有效地充分利用文件的文字和视觉特征方面所做的工作太少。在本文中,我们介绍了PICK,一个框架,是有效的和强大的处理复杂的文档布局KIE通过结合图学习与图卷积运算,产生一个更丰富的语义表示包含文本和视觉功能和全局布局没有歧义。在真实数据集上进行了大量的实验,结果表明,我们的方法明显优于基线方法。我们的代码可在https://github.com/wenwenyu/PICK-pytorch上获得。
Multimodal Graph RAG for Long-range Visually Rich Document Understanding
Department of Computer Science and Information Engineering, National Taiwan University(国家台湾大学计算机科学与信息工程系);FinTech Center, National Taiwan University(国家台湾大学金融科技中心)