Institutional documents, such as meeting minutes, contain valuable organizational knowledge, but their unstructured nature hinders systematic analysis. This work presents LLM-Text2KG, an ontology-guided pipeline for constructing knowledge graphs from institutional documents. The pipeline was evaluated on ten meeting mi...
G. Veríssimo, J. Marinho, M. Duarte et al.· Brazilian Symposium on Multi...· 0 citations
Relational database queries depend on SQL and prior knowledge of the schema. This work proposes SABRE, a plain-text search architecture for relational databases based on the vectorization of tuples and queries and on retrieval by semantic similarity. The evaluation used a pilot study for selecting the embedding model a...
Mikael Sales, M. Duarte, Wellington Franco et al.· Brazilian Symposium on Datab...· 0 citations
Workload analysis is fundamental to database performance management, as heterogeneous and complex workloads require automated identification of similar query patterns. In this context, this work investigates whether SQL query clustering based on structural embeddings extracted from the workload can support more efficie...
M. Duarte, Júlio César de Lira Marinho, Angelo Brayner et al.· Brazilian Symposium on Datab...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.