View in EDS

A novel few-shot relation extraction approach based on multi-granularity semantic interaction.

Saved in:
Bibliographic Details
Title: A novel few-shot relation extraction approach based on multi-granularity semantic interaction.
Authors: He, Xinyu1,2,3 (AUTHOR), Zhao, Guangda1 (AUTHOR), Li, Shixin1 (AUTHOR), Han, Xue1 (AUTHOR), Zhuang, Qiangjian1 (AUTHOR), Ren, Yonggong1 (AUTHOR) ryg@lnnu.edu.cn
Source: Soft Computing - A Fusion of Foundations, Methodologies & Applications. Mar2026, Vol. 30 Issue 3, p1767-1778. 12p.
Subjects: Natural language processing, Semantic computing, Machine learning
Abstract: Relation extraction is an important task in natural language processing, which aims to identify the semantic relationships between entities. This task is essential for enhancing applications such as digital humanities, legal document analysis, and biomedical information extraction. Although the existing models excel with large datasets, the performance suffers when dealing with few-shot scenarios due to limited samples. Consequently, these models struggle to fully capture the semantics of the given text. To address these challenges, this paper proposes the multi-granularity semantic interaction-based relation extraction model (MGSI). Our approach, inspired by prototype networks, facilitates comprehensive semantic interaction between support instances, query instances, and relation descriptions to obtain sentence-level and word-level prototypes with varying levels of semantic granularity. These prototypes are then fused to generate the final prototype. Furthermore, our framework incorporates a target adaptative module and a semantic contrastive module. These modules enhance the model's automatic adaptation and semantic understanding by capturing class-specific differences effectively. To validate the effectiveness of our proposed model, we conducted extensive experiments on the FewRel 1.0 and FewRel 2.0 public datasets. Our model achieves an accuracy of 94.51% in 5-way-1-shot tasks and 89.97% in 10-way-1-shot tasks on the FewRel 1.0 dataset, and delivers state-of-the-art results in the same tasks on the FewRel 2.0 dataset. [ABSTRACT FROM AUTHOR]
Copyright of Soft Computing - A Fusion of Foundations, Methodologies & Applications is the property of Springer Nature 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: 192343744
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A novel few-shot relation extraction approach based on multi-granularity semantic interaction.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22He%2C+Xinyu%22">He, Xinyu</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhao%2C+Guangda%22">Zhao, Guangda</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Shixin%22">Li, Shixin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Han%2C+Xue%22">Han, Xue</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhuang%2C+Qiangjian%22">Zhuang, Qiangjian</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ren%2C+Yonggong%22">Ren, Yonggong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> ryg@lnnu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Soft+Computing+-+A+Fusion+of+Foundations%2C+Methodologies+%26+Applications%22">Soft Computing - A Fusion of Foundations, Methodologies & Applications</searchLink>. Mar2026, Vol. 30 Issue 3, p1767-1778. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Natural+language+processing%22">Natural language processing</searchLink><br /><searchLink fieldCode="DE" term="%22Semantic+computing%22">Semantic computing</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Relation extraction is an important task in natural language processing, which aims to identify the semantic relationships between entities. This task is essential for enhancing applications such as digital humanities, legal document analysis, and biomedical information extraction. Although the existing models excel with large datasets, the performance suffers when dealing with few-shot scenarios due to limited samples. Consequently, these models struggle to fully capture the semantics of the given text. To address these challenges, this paper proposes the multi-granularity semantic interaction-based relation extraction model (MGSI). Our approach, inspired by prototype networks, facilitates comprehensive semantic interaction between support instances, query instances, and relation descriptions to obtain sentence-level and word-level prototypes with varying levels of semantic granularity. These prototypes are then fused to generate the final prototype. Furthermore, our framework incorporates a target adaptative module and a semantic contrastive module. These modules enhance the model's automatic adaptation and semantic understanding by capturing class-specific differences effectively. To validate the effectiveness of our proposed model, we conducted extensive experiments on the FewRel 1.0 and FewRel 2.0 public datasets. Our model achieves an accuracy of 94.51% in 5-way-1-shot tasks and 89.97% in 10-way-1-shot tasks on the FewRel 1.0 dataset, and delivers state-of-the-art results in the same tasks on the FewRel 2.0 dataset. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Soft Computing - A Fusion of Foundations, Methodologies & Applications is the property of Springer Nature 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=192343744
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00500-025-10602-2
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 1767
    Subjects:
      – SubjectFull: Natural language processing
        Type: general
      – SubjectFull: Semantic computing
        Type: general
      – SubjectFull: Machine learning
        Type: general
    Titles:
      – TitleFull: A novel few-shot relation extraction approach based on multi-granularity semantic interaction.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: He, Xinyu
      – PersonEntity:
          Name:
            NameFull: Zhao, Guangda
      – PersonEntity:
          Name:
            NameFull: Li, Shixin
      – PersonEntity:
          Name:
            NameFull: Han, Xue
      – PersonEntity:
          Name:
            NameFull: Zhuang, Qiangjian
      – PersonEntity:
          Name:
            NameFull: Ren, Yonggong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 03
              Text: Mar2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 14327643
          Numbering:
            – Type: volume
              Value: 30
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Soft Computing - A Fusion of Foundations, Methodologies & Applications
              Type: main
ResultId 1