Name
Abstract | ||
|---|---|---|
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, DBPe-dia50k 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. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1609/AAAI.V33I01.33013044 | THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE |
Field | DocType | Volume |
Graph,Knowledge graph,Embedding,Computer science,Open world,Theoretical computer science,Exploit,Artificial intelligence,Machine learning | Journal | 33 |
Issue | Citations | PageRank |
01 | 1 | 0.36 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Haseeb Shah | 1 | 1 | 0.36 |
| Johannes Villmow | 2 | 1 | 0.36 |
| Adrian Ulges | 3 | 328 | 26.61 |
| Ulrich Schwanecke | 4 | 269 | 22.77 |
| Faisal Shafait | 5 | 1324 | 88.97 |