Graph Neural Networks with Generated Parameters for Relation Extraction
This addresses relation extraction in NLP by enabling more accurate multi-hop reasoning, though it appears incremental as it builds on existing GNN methods.
The paper tackled the problem of multi-hop relational reasoning in relation extraction by proposing Graph Neural Networks with Generated Parameters (GP-GNNs) that adapt parameters based on natural language sentences, achieving significant improvements on human-annotated and distantly supervised datasets.
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.