Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks
This work addresses document analysis for researchers and practitioners by offering a flexible framework, though it appears incremental as it builds on existing GNN methods.
The authors tackled the problem of document understanding by proposing Doc2Graph, a task-agnostic framework based on Graph Neural Networks, which achieved competitive results on key information extraction tasks such as invoice layout analysis and table detection.
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.