Graph Neural Networks with Generated Parameters for Relation Extraction

被引：0

作者：

Zhu, Hao ^{[1
]}

Lin, Yankai ^{[1
]}

Liu, Zhiyuan ^{[1
]}

Fu, Jie ^{[2
]}

Chua, Tat-seng ^{[3
]}

Sun, Maosong ^{[1
]}

机构：

[1] Tsinghua Univ, Inst Artificial Intelligence, Dept Comp Sci & Technol, State Key Lab Intelligent Technol & Syst, Beijing, Peoples R China

[2] Natl Univ Singapore, Singapore, Singapore

[3] Univ Montreal, Montreal, PQ, Canada

来源：

57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019) | 2019年

基金：

新加坡国家研究基金会;

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a novel graph neural network with generated parameters (GPGNNs). The parameters in the propagation module, i.e. the transition matrices used in message passing procedure, are produced by a generator taking natural language sentences as inputs. We verify GP-GNNs in relation extraction from text, both on bag- and instance-settings. Experimental results on a human-annotated dataset and two distantly supervised datasets show that multi-hop reasoning mechanism yields significant improvements. We also perform a qualitative analysis to demonstrate that our model could discover more accurate relations by multi-hop relational reasoning. Codes and data are released at https : //github.com/thun1p/gp -gnn.

引用

页码：1331 / 1339

页数：9