BoxE: A box embedding model for knowledge base completion
Knowledge base completion (KBC) aims to automatically infer missing facts by exploiting information already present in a knowledge base (KB). A promising approach for KBC is to embed knowledge into latent spaces and make predictions from learned embeddings. However, existing embedding models are sub...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Jezik: | English |
| Izdano: |
NeurIPS
2020
|