English

Graph Neural Networks with Generated Parameters for Relation Extraction

Computation and Language 2019-02-05 v1

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.

Keywords

Cite

@article{arxiv.1902.00756,
  title  = {Graph Neural Networks with Generated Parameters for Relation Extraction},
  author = {Hao Zhu and Yankai Lin and Zhiyuan Liu and Jie Fu and Tat-seng Chua and Maosong Sun},
  journal= {arXiv preprint arXiv:1902.00756},
  year   = {2019}
}
R2 v1 2026-06-23T07:30:24.028Z