Graph Neural Networks with Generated Parameters for Relation Extraction

TL;DR

This paper introduces GP-GNNs, a novel approach that generates GNN parameters from natural language sentences, enabling effective multi-hop relational reasoning for relation extraction tasks.

Contribution

The paper proposes a method to generate GNN parameters from text, enhancing multi-hop relational reasoning in relation extraction.

Findings

Significant improvement over baselines on multiple datasets

Effective multi-hop reasoning demonstrated qualitatively

Model discovers more accurate relations

Abstract

Recently, progress has been made towards improving relational reasoning in machine learning field. Among existing models, graph neural networks (GNNs) is one of the most effective approaches for multi-hop relational reasoning. In fact, multi-hop relational reasoning is indispensable in many natural language processing tasks such as relation extraction. In this paper, we propose to generate the parameters of graph neural networks (GP-GNNs) according to natural language sentences, which enables GNNs to process relational reasoning on unstructured text inputs. We verify GP-GNNs in relation extraction from text. Experimental results on a human-annotated dataset and two distantly supervised datasets show that our model achieves significant improvements compared to baselines. We also perform a qualitative analysis to demonstrate that our model could discover more accurate relations by multi-hop relational reasoning.