@inproceedings{nguyen-etal-2024-vihealthnli,
    title = "{V}i{H}ealth{NLI}: A Dataset for {V}ietnamese Natural Language Inference in Healthcare",
    author = "Nguyen, Huyen  and
      Ngo, Quyen The  and
      Do, Thanh-Ha  and
      Hoang, Tuan-Anh",
    editor = "Melero, Maite  and
      Sakti, Sakriani  and
      Soria, Claudia",
    booktitle = "Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.sigul-1.48/",
    pages = "404--409",
    abstract = "This paper introduces ViHealthNLI, a large dataset for the natural language inference problem for Vietnamese. Unlike the similar Vietnamese datasets, ours is specific to the healthcare domain. We conducted an exploratory analysis to characterize the dataset and evaluated the state-of-the-art methods on the dataset. Our findings indicate that the dataset poses significant challenges while also holding promise for further advanced research and the creation of practical applications."
}