Papers with embedings
Embedding Multimodal Relational Data for Knowledge Base Completion (D18-1)
Copied to clipboard
| Challenge: | Existing approaches focus on a finite set of entities, ignoring the variety of data types used in knowledge bases. |
| Approach: | They propose multimodal knowledge base embeddings that use different neural encoders for observed data and different neural decoders to learn embedded entities and multimodal data. |
| Outcome: | The proposed models outperform existing methods with 5-7% accuracy over existing methods. |