Open Access iconOpen Access

ARTICLE

crossmark

A Graph with Adaptive Adjacency Matrix for Relation Extraction

Run Yang1,2,3, Yanping Chen1,2,3,*, Jiaxin Yan1,2,3, Yongbin Qin1,2,3

1 Engineering Research Center of Text Computing & Cognitive Intelligence, Ministry of Education, Guizhou University, Guiyang, 550025, China
2 State Key Laboratory of Public Big Data, Guizhou University, Guiyang, 550025, China
3 College of Computer Science and Technology, Guizhou University, Guiyang, 550025, China

* Corresponding Author: Yanping Chen. Email: email

Computers, Materials & Continua 2024, 80(3), 4129-4147. https://doi.org/10.32604/cmc.2024.051675

Abstract

The relation is a semantic expression relevant to two named entities in a sentence. Since a sentence usually contains several named entities, it is essential to learn a structured sentence representation that encodes dependency information specific to the two named entities. In related work, graph convolutional neural networks are widely adopted to learn semantic dependencies, where a dependency tree initializes the adjacency matrix. However, this approach has two main issues. First, parsing a sentence heavily relies on external toolkits, which can be error-prone. Second, the dependency tree only encodes the syntactical structure of a sentence, which may not align with the relational semantic expression. In this paper, we propose an automatic graph learning method to autonomously learn a sentence’s structural information. Instead of using a fixed adjacency matrix initialized by a dependency tree, we introduce an Adaptive Adjacency Matrix to encode the semantic dependency between tokens. The elements of this matrix are dynamically learned during the training process and optimized by task-relevant learning objectives, enabling the construction of task-relevant semantic dependencies within a sentence. Our model demonstrates superior performance on the TACRED and SemEval 2010 datasets, surpassing previous works by 1.3% and 0.8%, respectively. These experimental results show that our model excels in the relation extraction task, outperforming prior models.

Keywords


Cite This Article

APA Style
Yang, R., Chen, Y., Yan, J., Qin, Y. (2024). A graph with adaptive adjacency matrix for relation extraction. Computers, Materials & Continua, 80(3), 4129-4147. https://doi.org/10.32604/cmc.2024.051675
Vancouver Style
Yang R, Chen Y, Yan J, Qin Y. A graph with adaptive adjacency matrix for relation extraction. Comput Mater Contin. 2024;80(3):4129-4147 https://doi.org/10.32604/cmc.2024.051675
IEEE Style
R. Yang, Y. Chen, J. Yan, and Y. Qin "A Graph with Adaptive Adjacency Matrix for Relation Extraction," Comput. Mater. Contin., vol. 80, no. 3, pp. 4129-4147. 2024. https://doi.org/10.32604/cmc.2024.051675



cc Copyright © 2024 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 257

    View

  • 100

    Download

  • 0

    Like

Share Link