@inproceedings{pires-etal-2026-formalizing,
    title = "Formalizing the {DATASUS} {RTS}: An Ontological Model for a Resource Description Framework Knowledge Graph",
    author = "Pires, Vitor  and
      Griebler, Dalvan  and
      Meneguzzi, Felipe",
    editor = "Souza, Marlo  and
      de-Dios-Flores, Iria  and
      Santos, Diana  and
      Freitas, Larissa  and
      Souza, Jackson Wilke da Cruz  and
      Ribeiro, Eug{\'e}nio",
    booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
    month = apr,
    year = "2026",
    address = "Salvador, Brazil",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-dnd/2026.propor-1.90/",
    pages = "908--916",
    ISBN = "979-8-89176-387-6",
    abstract = "The Brazilian DataSUS platform provides vast health databases in relational formats that, while operationally efficient, lack the robust representation needed for advanced scientific data management, restricting interoperability. In this paper, we develop a knowledge engineering pipeline using Scenario 2 of the NeOn methodology to extract, process, and transform knowledge from the DataSUS Health Terminology Repository into a formal knowledge graph that adheres to World Wide Web Consortium standards.We illustrate the potential of this formalization by showing how the graph captures the domain{'}s complex relationships.The resulting graph comprises over 1.4 million triples, with approximately 700,000 associations generated solely through logical inference. Our pipeline provides a foundational resource that enables advanced structural and semantic querying in Portuguese."
}