GTN-ED: Event Detection Using Graph Transformer Networks
This work addresses event detection in NLP, but it is incremental as it builds on existing homogeneous-graph-based models.
The paper tackled the problem of event detection by incorporating both dependency edges and their labels using Graph Transformer Networks, improving the F1 score on the ACE dataset.
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.