Nitisha Jain, Ralf Krestel
We are happy to announce that our poster submission for the International Semantic Web Conference 2020 has been accepted for presentation. The conference will be held virtually from November 2-6.
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.