# ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction

arXiv: https://arxiv.org/abs/2106.10786 · HTML: https://mlsanity.com/paper/2106.10786/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 21 Jun 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Are Transformers universal approximators of sequence-to-sequence functions?](https://mlsanity.com/paper/1912.10077/) (2019)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Position-aware Graph Neural Networks](https://mlsanity.com/paper/1906.04817/) (2019)
- [Chargrid: Towards Understanding 2D Documents](https://mlsanity.com/paper/1809.08799/) (2018)
- [Graph Convolution for Multimodal Information Extraction from Visually Rich Documents](https://mlsanity.com/paper/1903.11279/) (2019)
- [PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks](https://mlsanity.com/paper/2004.07464/) (2020)
- [Learning to Encode Position for Transformer with Continuous Dynamical Model](https://mlsanity.com/paper/2003.09229/) (2020)
- [Graph-based Neural Multi-Document Summarization](https://mlsanity.com/paper/1706.06681/) (2017)
- [GraphIE: A Graph-Based Framework for Information Extraction](https://mlsanity.com/paper/1810.13083/) (2018)
- [CloudScan - A configuration-free invoice analysis system using recurrent neural networks](https://mlsanity.com/paper/1708.07403/) (2017)
- [Deep Visual Template-Free Form Parsing](https://mlsanity.com/paper/1909.02576/) (2019)
- [CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor](https://mlsanity.com/paper/1903.12363/) (2019)
- [Post-OCR Paragraph Recognition by Graph Convolutional Networks](https://mlsanity.com/paper/2101.12741/) (2021)

## Built on by (most cited first, 22 of 22)

- [FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction](https://mlsanity.com/paper/2203.08411/) (2022)
- [Improving In-Context Few-Shot Learning via Self-Supervised Training](https://mlsanity.com/paper/2205.01703/) (2022)
- [LMDX: Language Model-based Document Information Extraction and Localization](https://mlsanity.com/paper/2309.10952/) (2023)
- [VRDU: A Benchmark for Visually-rich Document Understanding](https://mlsanity.com/paper/2211.15421/) (2022)
- [FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction](https://mlsanity.com/paper/2305.02549/) (2023)
- [CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues](https://mlsanity.com/paper/2404.03820/) (2024)
- [End-to-End Page-Level Assessment of Handwritten Text Recognition](https://mlsanity.com/paper/2301.05935/) (2023)
- [Unified Line and Paragraph Detection by Graph Convolutional Networks](https://mlsanity.com/paper/2203.09638/) (2022)
- [QueryForm: A Simple Zero-shot Form Entity Query Framework](https://mlsanity.com/paper/2211.07730/) (2022)
- [Enhancing Visually-Rich Document Understanding via Layout Structure Modeling](https://mlsanity.com/paper/2308.07777/) (2023)
- [DocGraphLM: Documental Graph Language Model for Information Extraction](https://mlsanity.com/paper/2401.02823/) (2024)
- [Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation](https://mlsanity.com/paper/2305.02577/) (2023)
- [Pre-Training LLMs on a budget: A comparison of three optimizers](https://mlsanity.com/paper/2507.08472/) (2025)
- [Hypergraph based Understanding for Document Semantic Entity Recognition](https://mlsanity.com/paper/2407.06904/) (2024)
- [Where is this coming from? Making groundedness count in the evaluation of Document VQA models](https://mlsanity.com/paper/2503.19120/) (2025)
- [Unsupervised Extraction of Dialogue Policies from Conversations](https://mlsanity.com/paper/2406.15214/) (2024)
- [PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis](https://mlsanity.com/paper/2304.11810/) (2023)
- [DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading](https://mlsanity.com/paper/2310.14802/) (2023)
- [RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild](https://mlsanity.com/paper/2606.23344/) (2026)
- [Towards Optimizing OCR for Accessibility](https://mlsanity.com/paper/2206.10254/) (2022)
- [GVdoc: Graph-based Visual Document Classification](https://mlsanity.com/paper/2305.17219/) (2023)
- [HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction](https://mlsanity.com/paper/2411.01139/) (2024)

## Abstract (arXiv)

Natural reading orders of words are crucial for information extraction from form-like documents. Despite recent advances in Graph Convolutional Networks (GCNs) on modeling spatial layout patterns of documents, they have limited ability to capture reading orders of given word-level node representations in a graph. We propose Reading Order Equivariant Positional Encoding (ROPE), a new positional encoding technique designed to apprehend the sequential presentation of words in documents. ROPE generates unique reading order codes for neighboring words relative to the target word given a word-level graph connectivity. We study two fundamental document entity extraction tasks including word labeling and word grouping on the public FUNSD dataset and a large-scale payment dataset. We show that ROPE consistently improves existing GCNs with a margin up to 8.4% F1-score.