mlsanityData to 7 Oct 2026

A Comprehensive Survey of Document-level Relation Extraction (2016-2023)

arXiv 2309.16396 ↗First posted 28 Sep 2023cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Document-level relation extraction (DocRE) is an active area of research in natural language processing (NLP) concerned with identifying and extracting relationships between entities beyond sentence boundaries. Compared to the more traditional sentence-level relation extraction, DocRE provides a broader context for analysis and is more challenging because it involves identifying relationships that may span multiple sentences or paragraphs. This task has gained increased interest as a viable solution to build and populate knowledge bases automatically from unstructured large-scale documents (e.g., scientific papers, legal contracts, or news articles), in order to have a better understanding of relationships between entities. This paper aims to provide a comprehensive overview of recent advances in this field, highlighting its different applications in comparison to sentence-level relation extraction.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 58 of its 104 references that are in the map. First posted on arXiv 28 Sep 2023.

Builds on

58 of 104 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2017Graph Attention Networkscited by 8,854
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  8. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  9. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 261
  10. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  11. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  12. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
38 more
  1. 2017Cross-Sentence N-ary Relation Extraction with Graph LSTMscited by 101
  2. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  3. 2019A General Framework for Information Extraction using Dynamic Span Graphscited by 93
  4. 2020Double Graph Based Reasoning for Document-level Relation Extractioncited by 87
  5. 2022BioRED: A Rich Biomedical Relation Extraction Datasetcited by 84
  6. 2019Attention Guided Graph Convolutional Networks for Relation Extractioncited by 82
  7. 2020Coreferential Reasoning Learning for Language Representationcited by 80
  8. 2021Document-level Relation Extraction as Semantic Segmentationcited by 80
  9. 2023Semantic Segmentation using Vision Transformers: A surveycited by 73
  10. 2019Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphscited by 71
  11. 2020Domain-specific Knowledge Graphs: A surveycited by 68
  12. 2021Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extractioncited by 68
  13. 2016Distant Supervision for Relation Extraction beyond the Sentence Boundarycited by 62
  14. 2022Revisiting DocRED -- Addressing the False Negative Problem in Relation Extractioncited by 57
  15. 2019Document-Level N-ary Relation Extraction with Multiscale Representation Learningcited by 52
  16. 2019Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Networkcited by 51
  17. 2017Relation Extraction : A Surveycited by 44
  18. 2020Global-to-Local Neural Networks for Document-Level Relation Extractioncited by 43
  19. 2018Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extractioncited by 42
  20. 2019Fine-tune Bert for DocRED with Two-step Processcited by 42
  21. 2020HIN: Hierarchical Inference Network for Document-Level Relation Extractioncited by 42
  22. 2020Document-Level Relation Extraction with Reconstructioncited by 41
  23. 2022Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillationcited by 39
  24. 2023DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extractioncited by 37
  25. 2021SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extractioncited by 30
  26. 2020DWIE: an entity-centric dataset for multi-task document-level information extractioncited by 29
  27. 2021Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusioncited by 28
  28. 2018N-ary Relation Extraction using Graph State LSTMcited by 26
  29. 2021SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extractioncited by 23
  30. 2020Denoising Relation Extraction from Document-level Distant Supervisioncited by 19
  31. 2022Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocREDcited by 19
  32. 2022What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classificationcited by 17
  33. 2021Three Sentences Are All You Need: Local Path Enhanced Document Relation Extractioncited by 16
  34. 2022Document-Level Relation Extraction with Sentences Importance Estimation and Focusingcited by 16
  35. 2021Learning Logic Rules for Document-level Relation Extractioncited by 15
  36. 2018Neural Relation Extraction Within and Across Sentence Boundariescited by 13
  37. 2021BERT-GT: Cross-sentence n-ary relation extraction with BERT and Graph Transformercited by 10
  38. 2023Document-level Relation Extraction with Cross-sentence Reasoning Graphcited by 9

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2025A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trendscited by 8
  2. 2025Knowledge-augmented Pre-trained Language Models for Biomedical Relation Extractioncited by 2
  3. 2024When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Contextcited by 0
  4. 2025Multi-Relation Extraction in Entity Pairs using Global Contextcited by 0