mlsanityData to 14 Oct 2026

HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures

arXiv 2303.13839 ↗First posted 24 Mar 2023cs.CL cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page, neglecting the reconstruction of semantic structure in multi-page documents. This paper introduces hierarchical reconstruction of document structures as a novel task suitable for NLP and CV fields. To better evaluate the system performance on the new task, we built a large-scale dataset named HRDoc, which consists of 2,500 multi-page documents with nearly 2 million semantic units. Every document in HRDoc has line-level annotations including categories and relations obtained from rule-based extractors and human annotators. Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle this problem. By adopting a multi-modal bidirectional encoder and a structure-aware GRU decoder with soft-mask operation, the DSPS model surpass the baseline method by a large margin. All scripts and datasets will be made publicly available at https://github.com/jfma-USTC/HRDoc.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

14 of 31 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2017Mask R-CNNcited by 7,277
  5. 2016Layer Normalizationcited by 5,669
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  8. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  9. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 408
  10. 2019PubLayNet: largest dataset ever for document layout analysiscited by 351
  11. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 153
  12. 2021Document AI: Benchmarks, Models and Applicationscited by 62
2 more
  1. 2020DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understandingcited by 31
  2. 2022Multimodal Pre-training Based on Graph Attention Network for Document Understandingcited by 24

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 5; 2026: 11.

23 papers.

Sort:

By area:

  1. 2024Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysiscited by 15
  2. 2024READoc: A Unified Benchmark for Realistic Document Structured Extractioncited by 15
  3. 2024DLAFormer: An End-to-End Transformer For Document Layout Analysiscited by 11
  4. 2023DSG: An End-to-End Document Structure Generatorcited by 7
  5. 2024PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answeringcited by 7
  6. 2026MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documentscited by 6
  7. 2025Document Intelligence in the Era of Large Language Models: A Surveycited by 5
  8. 2026Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligencecited by 4
  9. 2024DocMamba: Efficient Document Pre-training with State Space Modelcited by 3
  10. 2025UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysiscited by 3
  11. 2026HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answeringcited by 3
  12. 2025PubTables-v2: A new large-scale dataset for full-page and multi-page table extractioncited by 2
11 more
  1. 2026MinerU-Popo: Universal Post-Processing Model for Structured Document Parsingcited by 2
  2. 2023Count, Decode and Fetch: A New Approach to Handwritten Chinese Character Error Correctioncited by 1
  3. 2025AnnoPage Dataset: Dataset of Non-Textual Elements in Documents with Fine-Grained Categorizationcited by 1
  4. 2026MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsingcited by 1
  5. 2025TextBite: A Historical Czech Document Dataset for Logical Page Segmentationcited by 0
  6. 2026PromptDLA: A Domain-aware Prompt Document Layout Analysis Framework with Descriptive Knowledge as a Cuecited by 0
  7. 2026M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Modelscited by 0
  8. 2026DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysiscited by 0
  9. 2026LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documentscited by 0
  10. 2026Robust Hierarchical Structures for Agentic Document Analysiscited by 0
  11. 2026Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memorycited by 0