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

Challenge:	Graph Convolutional Networks (GCNs) have limited ability to capture reading orders of given word-level node representations in a graph.
Approach:	They propose a new positional encoding technique to capture word-level nodes in a graph.
Outcome:	The proposed method improves existing GCNs with an 8.4% F1 score on two datasets and a large-scale payment dataset.

Similar Papers

Overview

Challenge

Approach

Outcome

Rethinking Reading Order: Toward Generalizable Document Understanding with LLM-based Relation Modeling (2026.eacl-long)

Copied to clipboard

Weishi Wang, Hengchang Hu, Daniel Dahlmeier

Challenge:	Document understanding requires modeling structural and semantic relationships between layout elements within the document without human supervision.
Approach:	They propose a cost-effective paradigm that leverages large language models to infer global RO and inter-element layout relations without human supervision.
Outcome:	Experiments on Semantic Entity Recognition, Entity Linking, and Document Question Answering show that the proposed model improves on baseline models while preserving the robustness of existing models.

Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study (2021.naacl-main)

Copied to clipboard

Chongyang Tao, Shen Gao, Juntao Li, Yansong Feng, Dongyan Zhao, Rui Yan

Challenge:	Existing approaches to encode natural languages without orders are lacking.
Approach:	They conduct a comprehensive analysis of the ability of neural models to organize sentences from a bag of words under three typical scenarios.
Outcome:	The proposed models can reorder or reconstruct sentences from a bag of words under three typical scenarios.

A Simple yet Effective Learnable Positional Encoding Method for Improving Document Transformer Model (2022.findings-aacl)

Copied to clipboard

Guoxin Wang, Yijuan Lu, Lei Cui, Tengchao Lv, Dinei Florencio, Cha Zhang

Language Models

Challenge:	Existing document Transformers lack a robust positional encoding mechanism to indicate and embed sequential order information in documents.
Approach:	They propose a positional encoding method that can be pre-trained on document datasets to improve document understanding.
Outcome:	The proposed method outperforms baselines on document understanding tasks in form, receipt, and invoice domains and is robust and stable on noisy data with incorrect order information.

Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction (2023.emnlp-main)

Copied to clipboard

Chong Zhang, Ya Guo, Yi Tu, Huan Chen, Jinyang Tang, Huijia Zhu, Qi Zhang, Tao Gui

Multimodality

Challenge:	Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs).
Approach:	They propose a method to predict token sequences within visually-rich documents by a simple prediction head.
Outcome:	The proposed method can be used to predict token mentions as token sequences within documents.

Learning to Order Graph Elements with Application to Multilingual Surface Realization (D19-63)

Copied to clipboard

Wenchao Du, Alan W Black

Multimodality

Challenge:	Recent advances in deep learning have shown promises in solving combinatorial optimization problems, such as sorting variable-sized sequences.
Approach:	They propose an encoder-decoder framework that learns the representation for each element and predicts the ordering of each local neighborhood of the graph in turn.
Outcome:	The proposed framework outperforms previous frameworks on multilingual surface realization tasks while outperforming those below by a large margin.

FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction (2022.acl-long)

Copied to clipboard

Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii, Tomas Pfister

Information Extraction & Text Mining

Challenge:	Form-like document understanding is a surging research topic due to its practical applications . form documents have unique challenges stemming from their structural characteristics .
Approach:	They propose a structure-aware sequence model that leverages spatial relationships between tokens in a form for more precise attention score calculation.
Outcome:	The proposed model outperforms existing methods with a more compact model size and less pre-training data.

GraphIE: A Graph-Based Framework for Information Extraction (N19-1)

Copied to clipboard

Yujie Qian, Enrico Santus, Zhijing Jin, Jiang Guo, Regina Barzilay

Information Extraction & Text Mining

Challenge:	Most modern Information Extraction (IE) systems are implemented as sequential taggers and model local dependencies.
Approach:	They propose a framework that operates over a graph representing a broad set of dependencies between textual units.
Outcome:	The proposed framework outperforms the state-of-the-art sequence tagging model on three different tasks.

Hierarchical Bracketing Encodings Work for Dependency Graphs (2025.emnlp-main)

Copied to clipboard

Ana Ezquerro, Carlos Gómez-Rodríguez, David Vilares

Structured Data in NLP

Challenge:	Sequence labeling (SL) is a simple yet effective paradigm for a wide range of natural language problems.
Approach:	They propose a new bracketing approach for dependency graph parsing that encodes graphs as sequences and n tagging actions.
Outcome:	The proposed approach significantly reduces label space while preserving structural information.

Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings (2021.emnlp-main)

Copied to clipboard

Shaopeng Lai, Ante Wang, Fandong Meng, Jie Zhou, Yubin Ge, Jiali Zeng, Junfeng Yao, Degen Huang, Jinsong Su

Structured Data in NLP

Challenge:	Existing sentence ordering models can be classified into pairwise ordering models and set-to-sequence models.
Approach:	They propose a novel sentence ordering framework which introduces two classifiers to make better use of pairwise orderings for graph-based sentence ordering.
Outcome:	The proposed model achieves state-of-the-art performance on five commonly-used datasets.

LayoutReader: Pre-training of Text and Layout for Reading Order Detection (2021.emnlp-main)

Copied to clipboard

Zilong Wang, Yiheng Xu, Lei Cui, Jingbo Shang, Furu Wei

Visual Data in NLP

Challenge:	Existing methods for reading order detection are too laborious to annotate large datasets.
Approach:	They propose to use a large-scale dataset to annotate reading order information for document images . they use XML metadata to capture the reading order of WORD documents .
Outcome:	The proposed model performs almost perfectly in reading order detection and improves both open-source and commercial OCR engines in ordering text lines in their results.