Toxic comment classification and rationale extraction in code-mixed text leveraging co-attentive multi-task learning: Toxic comment classification...: K. B. Nelatoori and H. B. Kommanti.

Detecting toxic comments and rationale for the offensiveness of a social media post promotes moderation of social media content. For this purpose, we propose a Co-Attentive Multi-task Learning (CA-MTL) model through transfer learning for low-resource Hindi-English (commonly known as Hinglish) toxic...

Descripción completa

Detalles Bibliográficos
Publicado en:Language Resources & Evaluation Vol. 59; no. 1; pp. 161 - 191
Autores principales: Nelatoori, Kiran Babu, Kommanti, Hima Bindu
Formato: Artículo
Publicado: Springer Nature Mar2025
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=183750663&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 183750663
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Mar2025
      vid: 59
      iid: 1
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        183750663
        10.1007/s10579-023-09708-6
      ppf: 161
      ppct: 30
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 1.5MB
      tig:
        atl: Toxic comment classification and rationale extraction in code-mixed text leveraging co-attentive multi-task learning: Toxic comment classification...: K. B. Nelatoori and H. B. Kommanti.
      aug:
        au:
          Nelatoori, Kiran Babu
          Kommanti, Hima Bindu
        affil: https://ror.org/0456pcg54 Department of CSE, National Institute of Technology Andhra Pradesh, 534101, Tadepalligudem, Andhra Pradesh, India
      su:
        Internet content moderation
        Social media
        Learning modules
        Classification
      sug:
        subj:
          Internet content moderation
          Social media
          Learning modules
          Classification
      keyword:
        Annotated code-mixed corpus
        Co-attention module
        Multi-task learning
        Rationale extraction
        Toxic comments
        Toxic span
      ab: Detecting toxic comments and rationale for the offensiveness of a social media post promotes moderation of social media content. For this purpose, we propose a Co-Attentive Multi-task Learning (CA-MTL) model through transfer learning for low-resource Hindi-English (commonly known as Hinglish) toxic texts. Together, the cooperative tasks of rationale/span detection and toxic comment classification create a strong multi-task learning objective. A task collaboration module is designed to leverage the bi-directional attention between the classification and span prediction tasks. The combined loss function of the model is constructed using the individual loss functions of these two tasks. Although an English toxic span detection dataset exists, one for Hinglish code-mixed text does not exist as of today. Hence, we developed a dataset with toxic span annotations for Hinglish code-mixed text. The proposed CA-MTL model is compared against single-task and multi-task learning models that lack the co-attention mechanism, using multilingual and Hinglish BERT variants. The F1 scores of the proposed CA-MTL model with HingRoBERTa encoder for both tasks are significantly higher than the baseline models. Caution: This paper may contain words disturbing to some readers.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Language Resources & Evaluation is a copyright of Springer, 2025. All Rights Reserved.
      item: Language Resources & Evaluation
      holder: Springer Nature
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N