SPARQL Query
SPARQL is a query language for retrieving information from knowledge graphs, structured datasets representing knowledge as interconnected entities and relationships. Current research focuses on improving the automatic translation of natural language questions into SPARQL queries, employing techniques like neural machine translation (using architectures such as transformers and convolutional sequence-to-sequence models) and integrating large language models to enhance accuracy and handle complex queries. This work is significant because it aims to make knowledge graphs more accessible to non-experts, enabling broader use in diverse applications ranging from scholarly question answering to healthcare decision support systems.
Papers
LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphs
Vincent Emonet, Jerven Bolleman, Severine Duvaud, Tarcisio Mendes de Farias, Ana Claudia Sima
A large collection of bioinformatics question-query pairs over federated knowledge graphs: methodology and applications
Jerven Bolleman, Vincent Emonet, Adrian Altenhoff, Amos Bairoch, Marie-Claude Blatter, Alan Bridge, Severine Duvaud, Elisabeth Gasteiger, Dmitry Kuznetsov, Sebastien Moretti, Pierre-Andre Michel, Anne Morgat, Marco Pagni, Nicole Redaschi, Monique Zahn-Zabal, Tarcisio Mendes de Farias, Ana Claudia Sima
Bottom-up Anytime Discovery of Generalised Multimodal Graph Patterns for Knowledge Graphs
Xander Wilcke, Rick Mourits, Auke Rijpma, Richard Zijdeman