Graph Neural Networks with Generated Parameters for Relation Extraction

Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-seng Chua and Maosong Sun,

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 the baselines. We also perform a qualitative analysis to demonstrate that our model could discover more accurate relations by multi-hop relational reasoning.

Keywords: Graph Neural Networks, Relational Reasoning

TL;DR: A graph neural network model with parameters generated from natural languages, which can perform multi-hop reasoning.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/graph-neural-networks-with-generated/code)