Attending To Syntactic Information In Biomedical Event Extraction Via Graph Neural Networks

TL;DR

This paper introduces a graph neural network approach that leverages full dependency graphs for biomedical event extraction, significantly improving accuracy over models using only shortest dependency paths.

Contribution

It proposes using the full dependency graph with GCNs for better argument classification in biomedical event extraction, outperforming existing models.

Findings

Significant performance improvement with dependency graph info

Full dependency graph outperforms shortest path methods

Model slightly surpasses state-of-the-art results

Abstract

Many models are proposed in the literature on biomedical event extraction(BEE). Some of them use the shortest dependency path(SDP) information to represent the argument classification task. There is an issue with this representation since even missing one word from the dependency parsing graph may totally change the final prediction. To this end, the full adjacency matrix of the dependency graph is used to embed individual tokens using a graph convolutional network(GCN). An ablation study is also done to show the effect of the dependency graph on the overall performance. The results show a significant improvement when dependency graph information is used. The proposed model slightly outperforms state-of-the-art models on BEE over different datasets.