# Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph Convolution Neural Networks

arXiv: https://arxiv.org/abs/2010.14123 · HTML: https://mlsanity.com/paper/2010.14123/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2020.

## Built on by (most cited first, 23 of 23)

- [CLEVE: Contrastive Pre-training for Event Extraction](https://mlsanity.com/paper/2105.14485/) (2021)
- [TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction](https://mlsanity.com/paper/2311.09562/) (2023)
- [Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding](https://mlsanity.com/paper/2110.07476/) (2021)
- [Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks](https://mlsanity.com/paper/2103.09330/) (2021)
- [The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation](https://mlsanity.com/paper/2306.06918/) (2023)
- [MEE: A Novel Multilingual Event Extraction Dataset](https://mlsanity.com/paper/2211.05955/) (2022)
- [MLBiNet: A Cross-Sentence Collective Event Detection Network](https://mlsanity.com/paper/2105.09458/) (2021)
- [FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction](https://mlsanity.com/paper/2202.08316/) (2022)
- [MINION: a Large-Scale and Diverse Dataset for Multilingual Event Detection](https://mlsanity.com/paper/2211.05958/) (2022)
- [TempoFormer: A Transformer for Temporally-aware Representations in Change Detection](https://mlsanity.com/paper/2408.15689/) (2024)
- [Event Extraction in Large Language Model](https://mlsanity.com/paper/2512.19537/) (2025)
- [A survey of diversity quantification in natural language processing: The why, what, where and how](https://mlsanity.com/paper/2507.20858/) (2025)
- [Event Extraction: A Survey](https://mlsanity.com/paper/2210.03419/) (2022)
- [Type Information Utilized Event Detection via Multi-Channel GNNs in Electrical Power Systems](https://mlsanity.com/paper/2211.08168/) (2022)
- [EDM3: Event Detection as Multi-task Text Generation](https://mlsanity.com/paper/2305.16357/) (2023)
- [Event Detection Explorer: An Interactive Tool for Event Detection Exploration](https://mlsanity.com/paper/2204.12456/) (2022)
- [HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold](https://mlsanity.com/paper/2210.08806/) (2022)
- [SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres](https://mlsanity.com/paper/2305.13617/) (2023)
- [Event-enhanced Retrieval in Real-time Search](https://mlsanity.com/paper/2404.05989/) (2024)
- [Token-Event-Role Structure-based Multi-Channel Document-Level Event Extraction](https://mlsanity.com/paper/2306.17733/) (2023)
- [Multi-Order Hyperbolic Graph Convolution and Aggregated Attention for Social Event Detection](https://mlsanity.com/paper/2502.00351/) (2025)
- [GraphPINE: Graph Importance Propagation for Interpretable Drug Response Prediction](https://mlsanity.com/paper/2504.05454/) (2025)
- [Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models](https://mlsanity.com/paper/2506.21294/) (2025)

## Abstract (arXiv)

Recent studies on event detection (ED) haveshown that the syntactic dependency graph canbe employed in graph convolution neural net-works (GCN) to achieve state-of-the-art per-formance. However, the computation of thehidden vectors in such graph-based models isagnostic to the trigger candidate words, po-tentially leaving irrelevant information for thetrigger candidate for event prediction. In addi-tion, the current models for ED fail to exploitthe overall contextual importance scores of thewords, which can be obtained via the depen-dency tree, to boost the performance. In thisstudy, we propose a novel gating mechanismto filter noisy information in the hidden vec-tors of the GCN models for ED based on theinformation from the trigger candidate. Wealso introduce novel mechanisms to achievethe contextual diversity for the gates and theimportance score consistency for the graphsand models in ED. The experiments show thatthe proposed model achieves state-of-the-artperformance on two ED datasets