mlsanityData to 14 Oct 2026

Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker

arXiv 2105.14924 ↗First posted 31 May 2021cs.CL cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

Document-level event extraction aims to recognize event information from a whole piece of article. Existing methods are not effective due to two challenges of this task: a) the target event arguments are scattered across sentences; b) the correlation among events in a document is non-trivial to model. In this paper, we propose Heterogeneous Graph-based Interaction Model with a Tracker (GIT) to solve the aforementioned two challenges. For the first challenge, GIT constructs a heterogeneous graph interaction network to capture global interactions among different sentences and entity mentions. For the second, GIT introduces a Tracker module to track the extracted events and hence capture the interdependency among the events. Experiments on a large-scale dataset (Zheng et al., 2019) show GIT outperforms the previous methods by 2.8 F1. Further analysis reveals GIT is effective in extracting multiple correlated events and event arguments that scatter across the document. Our code is available at https://github.com/RunxinXu/GIT.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 13 of its 39 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

13 of 39 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
  4. 2014Memory Networkscited by 363
  5. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 242
  6. 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
  7. 2020Double Graph Based Reasoning for Document-level Relation Extractioncited by 87
  8. 2018Jointly Multiple Events Extraction via Attention-based Graph Information Aggregationcited by 73
  9. 2019Doc2EDAG: An End-to-End Document-level Framework for Chinese Financial Event Extractioncited by 54
  10. 2016Joint Extraction of Events and Entities within a Document Contextcited by 48
  11. 2020Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encodingcited by 28
  12. 2017Scale Up Event Extraction Learning via Automatic Training Data Generationcited by 11
1 more
  1. 2020GRIT: Generative Role-filler Transformers for Document-level Event Entity Extractioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 6; 2023: 12; 2024: 4; 2025: 1; 2026: 1.

29 papers.

Sort:

By area:

  1. 2022Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extractioncited by 54
  2. 2021JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answeringcited by 40
  3. 2023Guideline Learning for In-context Information Extractioncited by 24
  4. 2021What is Event Knowledge Graph: A Surveycited by 19
  5. 2023The Devil is in the Details: On the Pitfalls of Event Extraction Evaluationcited by 19
  6. 2022A Two-Stream AMR-enhanced Model for Document-level Event Argument Extractioncited by 16
  7. 2021Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete Graphcited by 13
  8. 2021A Survey on Deep Learning Event Extraction: Approaches and Applicationscited by 12
  9. 2024ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinementcited by 12
  10. 2022EA2E: Improving Consistency with Event Awareness for Document-Level Argument Extractioncited by 11
  11. 2023Training Multimedia Event Extraction With Generated Images and Captionscited by 11
  12. 2023Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevancecited by 10
17 more
  1. 2021Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classificationcited by 8
  2. 2022RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extractioncited by 8
  3. 2023An AMR-based Link Prediction Approach for Document-level Event Argument Extractioncited by 8
  4. 2023LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extractioncited by 8
  5. 2025Event Extraction in Large Language Modelcited by 5
  6. 2023Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimizationcited by 4
  7. 2024A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extractioncited by 4
  8. 2022Event Extraction: A Surveycited by 3
  9. 2022DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlogcited by 3
  10. 2023A Survey of Document-Level Information Extractioncited by 3
  11. 2024Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigmcited by 2
  12. 2023Incorporating Deep Syntactic and Semantic Knowledge for Chinese Sequence Labeling with GCNcited by 1
  13. 2024Are Triggers Needed for Document-Level Event Extraction?cited by 1
  14. 2023Adaptive Ordered Information Extraction with Deep Reinforcement Learningcited by 0
  15. 2023Token-Event-Role Structure-based Multi-Channel Document-Level Event Extractioncited by 0
  16. 2023Type-aware Decoding via Explicitly Aggregating Event Information for Document-level Event Extractioncited by 0
  17. 2026Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streamscited by 0