# GTN-ED: Event Detection Using Graph Transformer Networks

arXiv: https://arxiv.org/abs/2104.15104 · HTML: https://mlsanity.com/paper/2104.15104/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 30 Apr 2021.

## Builds on (most cited first, 7 of 7)

- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation](https://mlsanity.com/paper/1809.09078/) (2018)
- [Joint Extraction of Events and Entities within a Document Context](https://mlsanity.com/paper/1609.03632/) (2016)
- [Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction](https://mlsanity.com/paper/2010.13391/) (2020)
- [Joint Event Extraction along Shortest Dependency Paths using Graph Convolutional Networks](https://mlsanity.com/paper/2003.08615/) (2020)
- [Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation](https://mlsanity.com/paper/2002.10757/) (2020)

## Built on by (most cited first, 3 of 3)

- [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)
- [Multi-Order Hyperbolic Graph Convolution and Aggregated Attention for Social Event Detection](https://mlsanity.com/paper/2502.00351/) (2025)

## Abstract (arXiv)

Recent works show that the graph structure of sentences, generated from dependency parsers, has potential for improving event detection. However, they often only leverage the edges (dependencies) between words, and discard the dependency labels (e.g., nominal-subject), treating the underlying graph edges as homogeneous. In this work, we propose a novel framework for incorporating both dependencies and their labels using a recently proposed technique called Graph Transformer Networks (GTN). We integrate GTNs to leverage dependency relations on two existing homogeneous-graph-based models, and demonstrate an improvement in the F1 score on the ACE dataset.