Next Article in Journal
Advances in Material Wide Range Temperature Determination by Dual-Color Emissivity Free Methodology in Long-Mid-near Infrared Ranges at Non-stationary Conditions
Next Article in Special Issue
A Sequential and Intensive Weighted Language Modeling Scheme for Multi-Task Learning-Based Natural Language Understanding
Previous Article in Journal
Effects of Differential Subgrade Settlement on Slab Track Deformation Based on a DEM-FDM Coupled Approach
Previous Article in Special Issue
Towards Improved Classification Accuracy on Highly Imbalanced Text Dataset Using Deep Neural Language Models
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 11
Issue 4
10.3390/app11041377
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Entity-Centric Fully Connected GCN for Relation Classification

by
Jun Long
1,2,
Ye Wang
1,
Xiangxiang Wei
1,
Zhen Ding
1,
Qianqian Qi
1,
Fang Xie
1,
Zheman Qian
1 and
Wenti Huang
1,*
1
School of Computer Science and Engineering, Central South University, Changsha 410083, China
2
Big Data Institute, Central South University, Changsha 410083, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2021, 11(4), 1377; https://doi.org/10.3390/app11041377
Submission received: 24 December 2020 / Revised: 25 January 2021 / Accepted: 28 January 2021 / Published: 3 February 2021
(This article belongs to the Special Issue Machine Learning and Natural Language Processing)
Browse Figures
Versions Notes

Abstract

Relation classification is an important task in the field of natural language processing, and it is one of the important steps in constructing a knowledge graph, which can greatly reduce the cost of constructing a knowledge graph. The Graph Convolutional Network (GCN) is an effective model for accurate relation classification, which models the dependency tree of textual instances to extract the semantic features of relation mentions. Previous GCN based methods treat each node equally. However, the contribution of different words to express a certain relation is different, especially the entity mentions in the sentence. In this paper, a novel GCN based relation classifier is propose, which treats the entity nodes as two global nodes in the dependency tree. These two global nodes directly connect with other nodes, which can aggregate information from the whole tree with only one convolutional layer. In this way, the method can not only simplify the complexity of the model, but also generate expressive relation representation. Experimental results on two widely used data sets, SemEval-2010 Task 8 and TACRED, show that our model outperforms all the compared baselines in this paper, which illustrates that the model can effectively utilize the dependencies between nodes and improve the performance of relation classification.
Keywords: graph convolutional network; relation classification; natural language processing graph convolutional network; relation classification; natural language processing

Share and Cite

MDPI and ACS Style

Long, J.; Wang, Y.; Wei, X.; Ding, Z.; Qi, Q.; Xie, F.; Qian, Z.; Huang, W. Entity-Centric Fully Connected GCN for Relation Classification. Appl. Sci. 2021, 11, 1377. https://doi.org/10.3390/app11041377

AMA Style

Long J, Wang Y, Wei X, Ding Z, Qi Q, Xie F, Qian Z, Huang W. Entity-Centric Fully Connected GCN for Relation Classification. Applied Sciences. 2021; 11(4):1377. https://doi.org/10.3390/app11041377

Chicago/Turabian Style

Long, Jun, Ye Wang, Xiangxiang Wei, Zhen Ding, Qianqian Qi, Fang Xie, Zheman Qian, and Wenti Huang. 2021. "Entity-Centric Fully Connected GCN for Relation Classification" Applied Sciences 11, no. 4: 1377. https://doi.org/10.3390/app11041377

APA Style

Long, J., Wang, Y., Wei, X., Ding, Z., Qi, Q., Xie, F., Qian, Z., & Huang, W. (2021). Entity-Centric Fully Connected GCN for Relation Classification. Applied Sciences, 11(4), 1377. https://doi.org/10.3390/app11041377

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop