Conference
View in EDS

Neural Topic Modeling via Contextual and Graph Information Fusion

Bibliographic Details
Title: Neural Topic Modeling via Contextual and Graph Information Fusion
Authors: Liu, Jiyuan, Yan, Jiaxing, Zhu, Chunjiang, Liu, Xingyu, Li, Qing, Rao, Yanghui
Source: Computer Science Faculty Publications
Publisher Information: ODU Digital Commons
Publication Year: 2025
Collection: Old Dominion University: ODU Digital Commons
Subject Terms: Graph theory—Data processing, Information storage and retrieval systems—Automatic indexing, Knowledge representation (Information theory), Machine learning—Statistical methods, Natural language processing (Computer science), Semantic networks (Information theory), Text mining, Topic modeling (Information retrieval), Artificial Intelligence and Robotics, Computer Sciences, Data Science
Description: Topic modeling is a powerful unsupervised tool for knowledge discovery. However, existing work struggles with generating limited-quality topics that are uninformative and incoherent, which hindering interpretable insights from managing textual data. In this paper, we improve the original variational autoencoder framework by incorporating contextual and graph information to address the above issues. First, the encoder utilizes topic fusion techniques to combine contextual and bag-of-words information well, and meanwhile exploits the constraints of topic alignment and topic sharpening to generate informative topics. Second, we develop a simple word co-occurrence graph information fusion strategy that efficiently increases topic coherence. On three benchmark datasets, our new framework generates more coherent and diverse topics compared to various baselines, and achieves strong performance on both automatic and manual evaluations.
Document Type: conference object
File Description: application/pdf
Language: unknown
Relation: https://digitalcommons.odu.edu/computerscience_fac_pubs/413; https://digitalcommons.odu.edu/context/computerscience_fac_pubs/article/1418/viewcontent/Zhu_2025_NeuralTopicModelingviaContextualandGraphInformationOCR.pdf
DOI: 10.18653/v1/2025.emnlp-main.670
Availability: https://digitalcommons.odu.edu/computerscience_fac_pubs/413
https://doi.org/10.18653/v1/2025.emnlp-main.670
https://digitalcommons.odu.edu/context/computerscience_fac_pubs/article/1418/viewcontent/Zhu_2025_NeuralTopicModelingviaContextualandGraphInformationOCR.pdf
Rights: © 2025 Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International (CC BY 4.0) License .
Accession Number: edsbas.F57780E9
Database: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://digitalcommons.odu.edu/computerscience_fac_pubs/413#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.F57780E9
RelevancyScore: 993
AccessLevel: 3
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 992.8095703125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Neural Topic Modeling via Contextual and Graph Information Fusion
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Liu%2C+Jiyuan%22">Liu, Jiyuan</searchLink><br /><searchLink fieldCode="AR" term="%22Yan%2C+Jiaxing%22">Yan, Jiaxing</searchLink><br /><searchLink fieldCode="AR" term="%22Zhu%2C+Chunjiang%22">Zhu, Chunjiang</searchLink><br /><searchLink fieldCode="AR" term="%22Liu%2C+Xingyu%22">Liu, Xingyu</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Qing%22">Li, Qing</searchLink><br /><searchLink fieldCode="AR" term="%22Rao%2C+Yanghui%22">Rao, Yanghui</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Computer Science Faculty Publications
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: ODU Digital Commons
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Old Dominion University: ODU Digital Commons
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Graph+theory—Data+processing%22">Graph theory—Data processing</searchLink><br /><searchLink fieldCode="DE" term="%22Information+storage+and+retrieval+systems—Automatic+indexing%22">Information storage and retrieval systems—Automatic indexing</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+representation+%28Information+theory%29%22">Knowledge representation (Information theory)</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning—Statistical+methods%22">Machine learning—Statistical methods</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+processing+%28Computer+science%29%22">Natural language processing (Computer science)</searchLink><br /><searchLink fieldCode="DE" term="%22Semantic+networks+%28Information+theory%29%22">Semantic networks (Information theory)</searchLink><br /><searchLink fieldCode="DE" term="%22Text+mining%22">Text mining</searchLink><br /><searchLink fieldCode="DE" term="%22Topic+modeling+%28Information+retrieval%29%22">Topic modeling (Information retrieval)</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence+and+Robotics%22">Artificial Intelligence and Robotics</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Sciences%22">Computer Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Data+Science%22">Data Science</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Topic modeling is a powerful unsupervised tool for knowledge discovery. However, existing work struggles with generating limited-quality topics that are uninformative and incoherent, which hindering interpretable insights from managing textual data. In this paper, we improve the original variational autoencoder framework by incorporating contextual and graph information to address the above issues. First, the encoder utilizes topic fusion techniques to combine contextual and bag-of-words information well, and meanwhile exploits the constraints of topic alignment and topic sharpening to generate informative topics. Second, we develop a simple word co-occurrence graph information fusion strategy that efficiently increases topic coherence. On three benchmark datasets, our new framework generates more coherent and diverse topics compared to various baselines, and achieves strong performance on both automatic and manual evaluations.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: conference object
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: application/pdf
– Name: Language
  Label: Language
  Group: Lang
  Data: unknown
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://digitalcommons.odu.edu/computerscience_fac_pubs/413; https://digitalcommons.odu.edu/context/computerscience_fac_pubs/article/1418/viewcontent/Zhu_2025_NeuralTopicModelingviaContextualandGraphInformationOCR.pdf
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.18653/v1/2025.emnlp-main.670
– Name: URL
  Label: Availability
  Group: URL
  Data: https://digitalcommons.odu.edu/computerscience_fac_pubs/413<br />https://doi.org/10.18653/v1/2025.emnlp-main.670<br />https://digitalcommons.odu.edu/context/computerscience_fac_pubs/article/1418/viewcontent/Zhu_2025_NeuralTopicModelingviaContextualandGraphInformationOCR.pdf
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: © 2025 Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International (CC BY 4.0) License .
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.F57780E9
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.F57780E9
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.18653/v1/2025.emnlp-main.670
    Languages:
      – Text: unknown
    Subjects:
      – SubjectFull: Graph theory—Data processing
        Type: general
      – SubjectFull: Information storage and retrieval systems—Automatic indexing
        Type: general
      – SubjectFull: Knowledge representation (Information theory)
        Type: general
      – SubjectFull: Machine learning—Statistical methods
        Type: general
      – SubjectFull: Natural language processing (Computer science)
        Type: general
      – SubjectFull: Semantic networks (Information theory)
        Type: general
      – SubjectFull: Text mining
        Type: general
      – SubjectFull: Topic modeling (Information retrieval)
        Type: general
      – SubjectFull: Artificial Intelligence and Robotics
        Type: general
      – SubjectFull: Computer Sciences
        Type: general
      – SubjectFull: Data Science
        Type: general
    Titles:
      – TitleFull: Neural Topic Modeling via Contextual and Graph Information Fusion
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liu, Jiyuan
      – PersonEntity:
          Name:
            NameFull: Yan, Jiaxing
      – PersonEntity:
          Name:
            NameFull: Zhu, Chunjiang
      – PersonEntity:
          Name:
            NameFull: Liu, Xingyu
      – PersonEntity:
          Name:
            NameFull: Li, Qing
      – PersonEntity:
          Name:
            NameFull: Rao, Yanghui
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
          Titles:
            – TitleFull: Computer Science Faculty Publications
              Type: main
ResultId 1