Cantonese natural language processing in the transformers era: a survey and current challenges.

Despite being spoken by a large population of speakers worldwide, Cantonese is under-resourced in terms of the data scale and diversity compared to other major languages. This limitation has excluded it from the current "pre-training and fine-tuning" paradigm that is dominated by Transformer archite...

Full description

Bibliographic Details
Published in:Language Resources & Evaluation Vol. 59; no. 2; pp. 1747 - 1774
Main Authors: Xiang, Rong, Chersoni, Emmanuele, Li, Yixia, Li, Jing, Huang, Chu-Ren, Pan, Yushan, Li, Yushi
Format: Literature Review
Published: Springer Nature Jun2025
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=185240039&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 185240039
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Jun2025
      vid: 59
      iid: 2
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        185240039
        10.1007/s10579-024-09744-w
      ppf: 1747
      ppct: 27
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 1.4MB
      tig:
        atl: Cantonese natural language processing in the transformers era: a survey and current challenges.
      aug:
        au:
          Xiang, Rong
          Chersoni, Emmanuele
          Li, Yixia
          Li, Jing
          Huang, Chu-Ren
          Pan, Yushan
          Li, Yushi
        affil:
          https://ror.org/0030zas98 Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China
          https://ror.org/0030zas98 Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Hong Kong, China
          https://ror.org/0030zas98 Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China
          https://ror.org/03zmrmn05 Department of Computing, Xi-an Jiaotong-Liverpool University, Suzhou, China
          https://ror.org/03zmrmn05 Department of Intelligent Science, Xi-an Jiaotong-Liverpool University, Suzhou, China
      su:
        Natural language processing
        Language models
        Cantonese dialects
        Language acquisition
        Transformer models
      sug:
        subj:
          Natural language processing
          Language models
          Cantonese dialects
          Language acquisition
          Transformer models
      keyword:
        Cantonese
        Code-switching
        Communication and Culture Linguistics
        Evaluation resources
        Language
        Multilingualism
        NLP for social media
      ab: Despite being spoken by a large population of speakers worldwide, Cantonese is under-resourced in terms of the data scale and diversity compared to other major languages. This limitation has excluded it from the current "pre-training and fine-tuning" paradigm that is dominated by Transformer architectures. In this paper, we provide a comprehensive review on the existing resources and methodologies for Cantonese Natural Language Processing, covering the recent progress in language understanding, text generation and development of language models. We finally discuss two aspects of the Cantonese language that could make it potentially challenging even for state-of-the-art architectures: colloquialism and multilinguality
      pubtype: Academic Journal
      doctype: Literature Review
      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