mlsanityData to 14 Oct 2026

Document-level Relation Extraction as Semantic Segmentation

arXiv 2106.03618 ↗First posted 7 Jun 2021cs.CL cs.AI cs.CVcited by 80

Not on the map. Why?

Abstract (arXiv)

Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among relational triples. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information, parallel to the semantic segmentation task in computer vision. Herein, we propose a Document U-shaped Network for document-level relation extraction. Specifically, we leverage an encoder module to capture the context information of entities and a U-shaped segmentation module over the image-style feature map to capture global interdependency among triples. Experimental results show that our approach can obtain state-of-the-art performance on three benchmark datasets DocRED, CDR, and GDA.

Key facts. Cited by 80 papers in the map (data through 14 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

29 of 44 references.

References · 29

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
  3. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
  4. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  5. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
  6. 2017Cross-Sentence N-ary Relation Extraction with Graph LSTMscited by 101
  7. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  8. 2020Double Graph Based Reasoning for Document-level Relation Extractioncited by 87
  9. 2020Coreferential Reasoning Learning for Language Representationcited by 80
  10. 2019Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphscited by 71
  11. 2019Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networkscited by 61
  12. 2019Document-Level N-ary Relation Extraction with Multiscale Representation Learningcited by 52
17 more
  1. 2018Reinforcement Learning for Relation Classification from Noisy Datacited by 46
  2. 2020Contrastive Triple Extraction with Generative Transformercited by 44
  3. 2020Global-to-Local Neural Networks for Document-Level Relation Extractioncited by 43
  4. 2018Simultaneously Self-Attending to All Mentions for Full-Abstract Biological Relation Extractioncited by 42
  5. 2019Fine-tune Bert for DocRED with Two-step Processcited by 42
  6. 2020HIN: Hierarchical Inference Network for Document-Level Relation Extractioncited by 42
  7. 2020Document-Level Relation Extraction with Reconstructioncited by 41
  8. 2021Curriculum-Meta Learning for Order-Robust Continual Relation Extractioncited by 34
  9. 2020Incomplete Utterance Rewriting as Semantic Segmentationcited by 33
  10. 2021AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibabacited by 33
  11. 2019Relation Adversarial Network for Low Resource Knowledge Graph Completioncited by 24
  12. 2019Generalizing Natural Language Analysis through Span-relation Representationscited by 22
  13. 2020Denoising Relation Extraction from Document-level Distant Supervisioncited by 19
  14. 2020Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extractioncited by 18
  15. 2020Finding Influential Instances for Distantly Supervised Relation Extractioncited by 13
  16. 2018Attention-Based Capsule Networks with Dynamic Routing for Relation Extractioncited by 10
  17. 2020Relation of the Relations: A New Paradigm of the Relation Extraction Problemcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 29; 2023: 26; 2024: 11; 2025: 7; 2026: 2.

80 papers.

Sort:

By area:

  1. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  3. 2022Revisiting DocRED -- Addressing the False Negative Problem in Relation Extractioncited by 57
  4. 2022Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completioncited by 44
  5. 2022Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillationcited by 39
  6. 2023DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extractioncited by 37
  7. 2021Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusioncited by 28
  8. 2022Ontology-enhanced Prompt-tuning for Few-shot Learningcited by 24
  9. 2021SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extractioncited by 23
  10. 2021Uncovering Main Causalities for Long-tailed Information Extractioncited by 21
  11. 2022Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocREDcited by 19
  12. 2022KPI-BERT: A Joint Named Entity Recognition and Relation Extraction Model for Financial Reportscited by 19
38 more
  1. 2022Entity-centered Cross-document Relation Extractioncited by 18
  2. 2022DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Populationcited by 17
  3. 2022Document-Level Relation Extraction with Sentences Importance Estimation and Focusingcited by 16
  4. 2023Continual Multimodal Knowledge Graph Constructioncited by 15
  5. 2022Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuningcited by 13
  6. 2022Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddingscited by 12
  7. 2024Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extractioncited by 12
  8. 2022Few-Shot Document-Level Relation Extractioncited by 11
  9. 2022Relational Representation Learning in Visually-Rich Documentscited by 11
  10. 2022A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labelingcited by 9
  11. 2022KPI-EDGAR: A Novel Dataset and Accompanying Metric for Relation Extraction from Financial Documentscited by 9
  12. 2023Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance Rewritingcited by 9
  13. 2023RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extractioncited by 9
  14. 2023Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Modelscited by 9
  15. 2022Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extractioncited by 7
  16. 2022Relphormer: Relational Graph Transformer for Knowledge Graph Representationscited by 7
  17. 2022Towards Better Document-level Relation Extraction via Iterative Inferencecited by 7
  18. 2023Uncertainty Guided Label Denoising for Document-level Distant Relation Extractioncited by 7
  19. 2022Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extractioncited by 6
  20. 2025Knowledge Augmented Complex Problem Solving with Large Language Models: A Surveycited by 6
  21. 2022CorefDRE: Document-level Relation Extraction with coreference resolutioncited by 5
  22. 2022Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Studycited by 5
  23. 2022Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoningcited by 4
  24. 2022Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modelingcited by 4
  25. 2023Towards Integration of Discriminability and Robustness for Document-Level Relation Extractioncited by 4
  26. 2023A Frustratingly Easy Improvement for Position Embeddings via Random Paddingcited by 4
  27. 2023Rethinking Document-Level Relation Extraction: A Reality Checkcited by 4
  28. 2023A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labelingcited by 4
  29. 2023Integrating Large Pre-trained Models into Multimodal Named Entity Recognition with Evidential Fusioncited by 4
  30. 2023A Comprehensive Survey of Document-level Relation Extraction (2016-2023)cited by 4
  31. 2022Improving Long Tailed Document-Level Relation Extraction via Easy Relation Augmentation and Contrastive Learningcited by 3
  32. 2022DORE: Document Ordered Relation Extraction based on Generative Frameworkcited by 3
  33. 2023Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extractioncited by 3
  34. 2023A Survey of Document-Level Information Extractioncited by 3
  35. 2023PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibrationcited by 3
  36. 2023Anaphor Assisted Document-Level Relation Extractioncited by 3
  37. 2022Continual Contrastive Finetuning Improves Low-Resource Relation Extractioncited by 2
  38. 2023Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Datacited by 2

50 most cited of 80 All 80 (JSON)