Ralf Krestel

• About Me
• Publications
  • Book Chapters
  • Journal Articles
  • Conference Papers
  • Workshop Papers
  • Posters & Demos
    • ISWC 20
    • IUI 20
    • CIKM 18
    • WWW 17
    • SMBM 16
    • WWW 15
    • WWW 12
    • DASFAA 12
    • JCDL 11
    • SIGIR 10
    • AAAI 07
  • Proceedings
  • Others
• Travels

ISWC 20

Learning Fine-Grained Semantics for Multi-Relational Data

Abstract

The semantics of relations play a central role in the understanding and analysis of multi-relational data. Real-world relational datasets represented by knowledge graphs often contain polysemous relations between different types of entities, that represent multiple semantics. In this work, we present a data-driven method that can automatically discover the distinct semantics associated with high-level relations and derive an optimal number of sub-relations having fine-grained meaning. To this end, we perform clustering over vector representations of entities and relations obtained from knowledge graph embedding models.

Demo Paper

ISWC20.pdf

Conference Homepage

ISWC-20

BibTex Entry

@inproceedings{krestel-iswc20, author = {Jain, Nitisha and Krestel, Ralf}, booktitle = {Proceedings of the International Semantic Web Conference}, month = {November 2--6} pages = {1--5}, publisher = {ACM}, title = {Learning Fine-Grained Semantics for Multi-Relational Data}, location = {Athens, Greece}, year = {2020} }