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
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 182607163
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A discrete convolutional network for entity relation extraction.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yang%2C+Weizhe%22">Yang, Weizhe</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Qin%2C+Yongbin%22">Qin, Yongbin</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Kai%22">Wang, Kai</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hu%2C+Ying%22">Hu, Ying</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Huang%2C+Ruizhang%22">Huang, Ruizhang</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Yanping%22">Chen, Yanping</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Networks%22">Neural Networks</searchLink>. Apr2025, Vol. 184, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Linguistics%22">Linguistics</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Computational+complexity%22">Computational complexity</searchLink><br /><searchLink fieldCode="DE" term="%22Public+relations%22">Public relations</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>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.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=182607163
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.neunet.2024.107117
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Linguistics
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Computational complexity
        Type: general
      – SubjectFull: Public relations
        Type: general
    Titles:
      – TitleFull: A discrete convolutional network for entity relation extraction.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang, Weizhe
      – PersonEntity:
          Name:
            NameFull: Qin, Yongbin
      – PersonEntity:
          Name:
            NameFull: Wang, Kai
      – PersonEntity:
          Name:
            NameFull: Hu, Ying
      – PersonEntity:
          Name:
            NameFull: Huang, Ruizhang
      – PersonEntity:
          Name:
            NameFull: Chen, Yanping
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 08936080
          Numbering:
            – Type: volume
              Value: 184
          Titles:
            – TitleFull: Neural Networks
              Type: main
ResultId 1