Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis
This addresses the problem of parsing unstructured digital documents into structured formats for downstream applications, representing an incremental improvement by incorporating previously ignored context and relational information.
The paper tackles document layout analysis by integrating heterogeneous information like syntactic, semantic, density, and visual aspects using graph convolutional networks, achieving new state-of-the-art results on three widely used datasets.
Recognizing the layout of unstructured digital documents is crucial when parsing the documents into the structured, machine-readable format for downstream applications. Recent studies in Document Layout Analysis usually rely on computer vision models to understand documents while ignoring other information, such as context information or relation of document components, which are vital to capture. Our Doc-GCN presents an effective way to harmonize and integrate heterogeneous aspects for Document Layout Analysis. We first construct graphs to explicitly describe four main aspects, including syntactic, semantic, density, and appearance/visual information. Then, we apply graph convolutional networks for representing each aspect of information and use pooling to integrate them. Finally, we aggregate each aspect and feed them into 2-layer MLPs for document layout component classification. Our Doc-GCN achieves new state-of-the-art results in three widely used DLA datasets.