An Open-World Extension to Knowledge Graph Completion Models
Shah, Haseeb, Villmow, Johannes, Ulges, Adrian, Schwanecke, Ulrich, Shafait, Faisal
–arXiv.org Artificial Intelligence
We present a novel extension to embedding-based knowledge graph completion models which enables them to perform open-world link prediction, i.e. to predict facts for entities unseen in training based on their textual description. Our model combines a regular link prediction model learned from a knowledge graph with word embeddings learned from a textual corpus. After training both independently, we learn a transformation to map the embeddings of an entity's name and description to the graph-based embedding space. In experiments on several datasets including FB20k, DBPedia50k and our new dataset FB15k-237-OWE, we demonstrate competitive results. Particularly, our approach exploits the full knowledge graph structure even when textual descriptions are scarce, does not require a joint training on graph and text, and can be applied to any embedding-based link prediction model, such as TransE, ComplEx and DistMult.
arXiv.org Artificial Intelligence
Jun-19-2019
- Country:
- North America > United States (0.68)
- Genre:
- Research Report (0.64)
- Overview (0.46)
- Industry:
- Education (0.47)
- Technology: