Abstract
This work introduces Distributional Relational Net- works (DRNs), a Knowledge Representation (KR) framework which focuses on allowing semantic approx- imations over large-scale and heterogeneous knowledge bases. The proposed model uses the distributional se- mantics information embedded in large text data cor- pora to provide a comprehensive and principled solu- tion for semantic approximation. DRNs can be applied to open domain knowledge bases and can be used as a KR model for commonsense reasoning. Experimental results show the suitability of DRNs as a semantically flexible KR framework.
| Original language | English (Ireland) |
|---|---|
| Title of host publication | AAAI 2013 Fall Symposium on Semantics for Big Data |
| Publication status | Published - 1 Jan 2013 |
Authors (Note for portal: view the doc link for the full list of authors)
- Authors
- Freitas, Andre;Silva, Joao C. P. da;O'Riain, Sean;Curry, Edward