View in EDS

A discrete convolutional network for entity relation extraction.

Saved in:
Bibliographic Details
Title: A discrete convolutional network for entity relation extraction.
Authors: Yang, Weizhe1,2 (AUTHOR), Qin, Yongbin1,2,3 (AUTHOR), Wang, Kai2,3 (AUTHOR), Hu, Ying2,3 (AUTHOR), Huang, Ruizhang1,2,3 (AUTHOR), Chen, Yanping1,2,3 (AUTHOR)
Source: Neural Networks. Apr2025, Vol. 184, pN.PAG-N.PAG. 1p.
Subjects: Deep learning, Linguistics, Convolutional neural networks, Computational complexity, Public relations
Abstract: Relation extraction independently verifies all entity pairs in a sentence to identify predefined relationships between named entities. Because these entity pairs share the same contextual features of a sentence, they lead to a complicated semantic structure. To distinguish semantic expressions between relation instances, manually designed rules or elaborate deep architectures are usually applied to learn task-relevant representations. In this paper, a discrete convolutional network is proposed to incorporate discrete linguistic interactions and deep feature weighting. This network applies a discretization strategy to fix parameters of convolutional kernels into ternary values. Then, these discretized kernels are used to learn discrete semantic structures from vectorized token representations. Our approach leverages the ability of discrete CNNs to capture discrete linguistic patterns of a sentence, thereby maintaining model expressiveness and improving performance in the relation extraction task. Furthermore, our method has the advantages of reducing the overfitting problem caused by depending on prior knowledge and decreasing the computational complexity by reducing the number of trainable parameters. Our model is evaluated on five widely used benchmark datasets. It achieves state-of-the-art performance, outperforming all compared related works. Experimental results also demonstrate that, compared with traditional CNN networks, it achieves an average improvement of 14.66% in F1-score and accelerates training by an average of 17.46%, highlighting the efficiency and effectiveness of our model in the relation extraction task. • A DisCoNet model with ternary convolution is proposed for relation extraction. • Ternary convolution captures intrinsic abstract semantic structures effectively. • Achieves high F1 scores across five public relation extraction datasets. • Reduces training parameters and time while preserving classification performance. • Shows promise in NLP tasks, balancing accuracy and efficiency. [ABSTRACT FROM AUTHOR]
Copyright of Neural Networks is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Relation extraction independently verifies all entity pairs in a sentence to identify predefined relationships between named entities. Because these entity pairs share the same contextual features of a sentence, they lead to a complicated semantic structure. To distinguish semantic expressions between relation instances, manually designed rules or elaborate deep architectures are usually applied to learn task-relevant representations. In this paper, a discrete convolutional network is proposed to incorporate discrete linguistic interactions and deep feature weighting. This network applies a discretization strategy to fix parameters of convolutional kernels into ternary values. Then, these discretized kernels are used to learn discrete semantic structures from vectorized token representations. Our approach leverages the ability of discrete CNNs to capture discrete linguistic patterns of a sentence, thereby maintaining model expressiveness and improving performance in the relation extraction task. Furthermore, our method has the advantages of reducing the overfitting problem caused by depending on prior knowledge and decreasing the computational complexity by reducing the number of trainable parameters. Our model is evaluated on five widely used benchmark datasets. It achieves state-of-the-art performance, outperforming all compared related works. Experimental results also demonstrate that, compared with traditional CNN networks, it achieves an average improvement of 14.66% in F1-score and accelerates training by an average of 17.46%, highlighting the efficiency and effectiveness of our model in the relation extraction task. • A DisCoNet model with ternary convolution is proposed for relation extraction. • Ternary convolution captures intrinsic abstract semantic structures effectively. • Achieves high F1 scores across five public relation extraction datasets. • Reduces training parameters and time while preserving classification performance. • Shows promise in NLP tasks, balancing accuracy and efficiency. [ABSTRACT FROM AUTHOR]
ISSN:08936080
DOI:10.1016/j.neunet.2024.107117