Detecting Synonymous Properties by Shared Data-driven Definitions

Aus International Center for Computational Logic
Wechseln zu:Navigation, Suche

Toggle side column

Detecting Synonymous Properties by Shared Data-driven Definitions

Jan-Christoph KaloJan-Christoph Kalo,  Stephan MennickeStephan Mennicke,  Philipp EhlerPhilipp Ehler,  Wolf-Tilo BalkeWolf-Tilo Balke
Jan-Christoph Kalo, Stephan Mennicke, Philipp Ehler, Wolf-Tilo Balke
Detecting Synonymous Properties by Shared Data-driven Definitions
The Semantic Web - 17th International Conference, ESWC 2020, Virtual, June 2-4, 2020, Proceedings., 360-375, June 2020. Springer
  • KurzfassungAbstract
    Knowledge graphs have become an essential source of entitycentric

    information for modern applications. Today’s KGs have reached a size of billions of RDF triples extracted from a variety of sources, including structured sources and text. While this definitely improves completeness, the inherent variety of sources leads to severe heterogeneity, negatively affecting data quality by introducing duplicate information. We present a novel technique for detecting synonymous properties in large knowledge graphs by mining interpretable definitions of properties using association rule mining. Relying on such shared definitions, our technique is able to mine even synonym rules that have only little support in the data. In particular, our extensive experiments on DBpedia and Wikidata show that our rule-based approach can outperform stateof- the-art knowledge graph embedding techniques, while offering good

    interpretability through shared logical rules.
  • Forschungsgruppe:Research Group: Wissensbasierte SystemeKnowledge-Based Systems
The final publication is available at Springer.
@inproceedings{KMEB2020,
  author    = {Jan-Christoph Kalo and Stephan Mennicke and Philipp Ehler and
               Wolf-Tilo Balke},
  title     = {Detecting Synonymous Properties by Shared Data-driven Definitions},
  booktitle = {The Semantic Web - 17th International Conference, {ESWC} 2020,
               Virtual, June 2-4, 2020, Proceedings.},
  publisher = {Springer},
  year      = {2020},
  month     = {June},
  pages     = {360-375}
}