mlsanityData to 7 Oct 2026

Double Graph Based Reasoning for Document-level Relation Extraction

arXiv 2009.13752 ↗First posted 29 Sep 2020cs.CL cs.AI cs.LGcited by 87

Not on the map. Why?

Abstract (arXiv)

Document-level relation extraction aims to extract relations among entities within a document. Different from sentence-level relation extraction, it requires reasoning over multiple sentences across a document. In this paper, we propose Graph Aggregation-and-Inference Network (GAIN) featuring double graphs. GAIN first constructs a heterogeneous mention-level graph (hMG) to model complex interaction among different mentions across the document. It also constructs an entity-level graph (EG), based on which we propose a novel path reasoning mechanism to infer relations between entities. Experiments on the public dataset, DocRED, show GAIN achieves a significant performance improvement (2.85 on F1) over the previous state-of-the-art. Our code is available at https://github.com/DreamInvoker/GAIN .

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 30; 2023: 19; 2024: 14; 2025: 5; 2026: 4.

87 papers.

Sort:

By area:

  1. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  2. 2021Document-level Relation Extraction as Semantic Segmentationcited by 80
  3. 2022Multimodal learning with graphscited by 54
  4. 2022Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillationcited by 39
  5. 2023DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extractioncited by 37
  6. 2021SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extractioncited by 30
  7. 2021Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Trackercited by 29
  8. 2021Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusioncited by 28
  9. 2021Graph Based Network with Contextualized Representations of Turns in Dialoguecited by 26
  10. 2021A Survey on Extraction of Causal Relations from Natural Language Textcited by 25
  11. 2021Discriminative Reasoning for Document-level Relation Extractioncited by 25
  12. 2021SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extractioncited by 23
38 more
  1. 2022MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoningcited by 22
  2. 2023A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontierscited by 21
  3. 2022Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocREDcited by 19
  4. 2022KPI-BERT: A Joint Named Entity Recognition and Relation Extraction Model for Financial Reportscited by 19
  5. 2022Entity-centered Cross-document Relation Extractioncited by 18
  6. 2022DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Populationcited by 17
  7. 2021Three Sentences Are All You Need: Local Path Enhanced Document Relation Extractioncited by 16
  8. 2022Document-Level Relation Extraction with Sentences Importance Estimation and Focusingcited by 16
  9. 2022A Two-Stream AMR-enhanced Model for Document-level Event Argument Extractioncited by 16
  10. 2021Learning Logic Rules for Document-level Relation Extractioncited by 15
  11. 2024Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extractioncited by 14
  12. 2022Multi-hop Evidence Retrieval for Cross-document Relation Extractioncited by 13
  13. 2021Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Surveycited by 12
  14. 2022ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Selectcited by 10
  15. 2021Discourse-level Relation Extraction via Graph Poolingcited by 9
  16. 2022A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labelingcited by 9
  17. 2022KPI-EDGAR: A Novel Dataset and Accompanying Metric for Relation Extraction from Financial Documentscited by 9
  18. 2023Document-level Relation Extraction with Cross-sentence Reasoning Graphcited by 9
  19. 2023RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extractioncited by 9
  20. 2021Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classificationcited by 8
  21. 2022None Class Ranking Loss for Document-Level Relation Extractioncited by 8
  22. 2024LLM with Relation Classifier for Document-Level Relation Extractioncited by 8
  23. 2022Towards Better Document-level Relation Extraction via Iterative Inferencecited by 7
  24. 2023Uncertainty Guided Label Denoising for Document-level Distant Relation Extractioncited by 7
  25. 2022Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extractioncited by 6
  26. 2022CorefDRE: Document-level Relation Extraction with coreference resolutioncited by 5
  27. 2024FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extractioncited by 5
  28. 2021Modular Self-Supervision for Document-Level Relation Extractioncited by 4
  29. 2022Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoningcited by 4
  30. 2022Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modelingcited by 4
  31. 2023Rethinking Document-Level Relation Extraction: A Reality Checkcited by 4
  32. 2023A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labelingcited by 4
  33. 2023A Comprehensive Survey of Document-level Relation Extraction (2016-2023)cited by 4
  34. 2023PromptRE: Weakly-Supervised Document-Level Relation Extraction via Prompting-Based Data Programmingcited by 4
  35. 2022Improving Long Tailed Document-Level Relation Extraction via Easy Relation Augmentation and Contrastive Learningcited by 3
  36. 2022Enhancing Document-level Relation Extraction by Entity Knowledge Injectioncited by 3
  37. 2022DORE: Document Ordered Relation Extraction based on Generative Frameworkcited by 3
  38. 2023Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extractioncited by 3

50 most cited of 87 All 87 (JSON)