KGPrune
Contact us
kgprune@inria.fr
Knowledge Graph Pruning
KGPrune aims at extracting a subgraph of Wikidata related to input entities of interest to you. In particular, our approach starts from such seed entities, and keeps or prunes their neighboring entities. This process allows you to extract a subgraph of Wikidata related to your domains of interest. Such a subgraph can then be used, e.g., as a high-quality nucleus to bootstrap the construction of a new knowledge graph, or as a supporting structure for knowledge extraction or mining approaches.
The KGPrune website and API offer an easy introduction to knowledge graph pruning through concrete examples, allowing users to visualize the model's decision-making process effectively. The deployment relies on Loria’s computing resources. To ensure fair use, we impose a time limit of 10 minutes per query. To avoid such limitations, we recommend that you deploy your own instance of KGPrune. Please contact kgprune@inria.fr for assistance in finding a customized solution.
More Information and Citation
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]
Lucas Jarnac, Miguel Couceiro, Pierre Monnin: Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruning. CIKM 2023 [paper]