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.
@article{arxiv.2104.15104,
title = {GTN-ED: Event Detection Using Graph Transformer Networks},
author = {Sanghamitra Dutta and Liang Ma and Tanay Kumar Saha and Di Lu and Joel Tetreault and Alejandro Jaimes},
journal= {arXiv preprint arXiv:2104.15104},
year = {2021}
}