# PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis

arXiv: https://arxiv.org/abs/2304.11810 · HTML: https://mlsanity.com/paper/2304.11810/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 24 Apr 2023.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [DiT: Self-supervised Pre-training for Document Image Transformer](https://mlsanity.com/paper/2203.02378/) (2022)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [Complicated Table Structure Recognition](https://mlsanity.com/paper/1908.04729/) (2019)
- [Graph Convolution for Multimodal Information Extraction from Visually Rich Documents](https://mlsanity.com/paper/1903.11279/) (2019)
- [Unified Pretraining Framework for Document Understanding](https://mlsanity.com/paper/2204.10939/) (2022)
- [Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection](https://mlsanity.com/paper/2003.07493/) (2020)
- [Table Structure Recognition using Top-Down and Bottom-Up Cues](https://mlsanity.com/paper/2010.04565/) (2020)
- [Learning representations of irregular particle-detector geometry with distance-weighted graph networks](https://mlsanity.com/paper/1902.07987/) (2019)
- [TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition](https://mlsanity.com/paper/2106.10598/) (2021)
- [ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction](https://mlsanity.com/paper/2106.10786/) (2021)
- [GFTE: Graph-based Financial Table Extraction](https://mlsanity.com/paper/2003.07560/) (2020)
- [Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis](https://mlsanity.com/paper/2208.10970/) (2022)
- [Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks](https://mlsanity.com/paper/2208.11168/) (2022)
- [Post-OCR Paragraph Recognition by Graph Convolutional Networks](https://mlsanity.com/paper/2101.12741/) (2021)
- [Visual FUDGE: Form Understanding via Dynamic Graph Editing](https://mlsanity.com/paper/2105.08194/) (2021)
- [Unified Line and Paragraph Detection by Graph Convolutional Networks](https://mlsanity.com/paper/2203.09638/) (2022)

## Built on by (most cited first, 2 of 2)

- [PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction](https://mlsanity.com/paper/2409.05125/) (2024)
- [Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysis](https://mlsanity.com/paper/2308.15517/) (2023)

## Abstract (arXiv)

Document layout analysis has a wide range of requirements across various domains, languages, and business scenarios. However, most current state-of-the-art algorithms are language-dependent, with architectures that rely on transformer encoders or language-specific text encoders, such as BERT, for feature extraction. These approaches are limited in their ability to handle very long documents due to input sequence length constraints and are closely tied to language-specific tokenizers. Additionally, training a cross-language text encoder can be challenging due to the lack of labeled multilingual document datasets that consider privacy. Furthermore, some layout tasks require a clean separation between different layout components without overlap, which can be difficult for image segmentation-based algorithms to achieve. In this paper, we present Paragraph2Graph, a language-independent graph neural network (GNN)-based model that achieves competitive results on common document layout datasets while being adaptable to business scenarios with strict separation. With only 19.95 million parameters, our model is suitable for industrial applications, particularly in multi-language scenarios.