Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks. (arXiv:2208.11168v1 [cs.CV])

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 …

arxiv cv document understanding framework graph graph neural networks networks neural networks understanding