论文标题
DOC2Graph：一个任务不可知论文档理解基于图形神经网络的框架
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
论文作者
论文摘要
几何深度学习最近对包括文档分析在内的广泛的机器学习领域引起了极大的兴趣。图形神经网络（GNN）的应用在各种与文档相关的任务中变得至关重要，因为它们可以揭示重要的结构模式，这是关键信息提取过程的基础。文献中的先前作品提出了任务驱动的模型，并且没有考虑到图形的全部功能。我们建议Doc2Graph是一种基于GNN模型的任务无关文档理解框架，以解决给定不同类型的文档的不同任务。我们在两个具有挑战性的数据集上评估了我们的方法，以了解形式理解，发票布局分析和表检测的关键信息提取。我们的代码可以在https://github.com/andreagemelli/doc2graph上自由访问。
Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection. Our code is freely accessible on https://github.com/andreagemelli/doc2graph.
