About KGPrune

KGPrune is an application realized as part of the AT2TA project by

  • Miguel Couceiro (Université de Lorraine, CNRS, LORIA, Nancy, France)
  • Lucas Jarnac (Université de Lorraine, CNRS, LORIA, Nancy, France & Orange, Belfort, France)
  • Pierre Monnin (Université Côte d’Azur, Inria, CNRS, I3S, Sophia Antipolis, France)
  • Ndeye-Emilie Mbengue (Université de Lorraine, CNRS, LORIA, Nancy, France)
  • Cherif Hassan Nousradine (Université de Lorraine, CNRS, LORIA, Nancy, France)

Contact the team

You can contact us using the email address: kgprune@inria.fr



Algorithmic Framework of this Project

The KGPrune Web application is described in:

Pierre Monnin, Cherif-Hassan Nousradine, Lucas Jarnac, Laurel Zuckerman, Miguel Couceiro: KGPrune: a Web Application to Extract Subgraphs of Interest from Wikidata with Analogical Pruning. ECAI 2024 [paper]

The source code of our backend analogical model is open-source and available on GitHub.

Note that the first version of KGPrune analogical pruning algorithm was described in:

Lucas Jarnac, Miguel Couceiro, Pierre Monnin: Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruning. CIKM 2023: 934-944 [paper]

The code was already open-source and available on GitHub.

Please cite both articles when referring to KGPrune.








Contact us

kgprune@inria.fr