Findings of the WILDRE Shared Task on Code-mixed Less-resourced Sentiment Analysis for Indo-Aryan Languages

    Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

    2 Citations (Scopus)

    Abstract

    This paper describes the structure and findings of the WILDRE 2024 shared task on code-mixed less-resourced sentiment analysis for Indo-Aryan Languages. The participants were asked to submit the test data’s final prediction on CodaLab. A total of fourteen teams registered for the shared task. Only five participants submitted the system for evaluation on CodaLab, with only two teams submitting the system description paper. All the submitted systems exceed baseline scores, with the best F1 Scores of 0.97, 0.54, 0.45, 0.60 and 0.49 for Bangla-Hindi-English, Hindi-English, Magahi-Hindi-English, Combined, and Maithili-Hindi-English, respectively. This significant improvement from the baseline score highlights notable progress in the performance of the systems. This underscores the advancement and refinement of methodologies, highlighting the potential for further innovation for code-mixed tasks.

    Original languageEnglish
    Title of host publication7th Workshop on Indian Language Data Resource and Evaluation at LREC-COLING-2024, WILDRE 2024 - Workshop Proceedings
    EditorsGirish Nath Jha, Sobha Lalitha Devi, Kalika Bali, Atul Kr. Ojha, Atul Kr. Ojha
    PublisherAssociation for Computational Linguistics (ACL)
    Pages17-23
    Number of pages7
    ISBN (Electronic)9782493814371
    Publication statusPublished - 2024
    Event7th Workshop on Indian Language Data: Resource and Evaluation, WILDRE 2024 - Torino, Italy
    Duration: 25 May 2024 → …

    Publication series

    NameProceedings - International Conference on Computational Linguistics, COLING
    ISSN (Print)2951-2093

    Conference

    Conference7th Workshop on Indian Language Data: Resource and Evaluation, WILDRE 2024
    Country/TerritoryItaly
    CityTorino
    Period25/05/24 → …

    Keywords

    • Closely-related languages
    • Codemixing
    • Indian languages
    • Less-resourced languages
    • Sentiment

    Fingerprint

    Dive into the research topics of 'Findings of the WILDRE Shared Task on Code-mixed Less-resourced Sentiment Analysis for Indo-Aryan Languages'. Together they form a unique fingerprint.

    Cite this