# An Open-World Extension to Knowledge Graph Completion Models

## TL;DR

This paper introduces an extension to knowledge graph completion models that allows them to predict links involving unseen entities by leveraging textual descriptions and a learned transformation, enhancing open-world reasoning capabilities.

## Contribution

The authors propose a method to incorporate textual descriptions into existing embedding models for open-world link prediction without joint training, applicable to various models like TransE, ComplEx, and DistMult.

## Key findings

- Competitive results on multiple datasets including FB20k, DBPedia50k, and FB15k-237-OWE.
- Effective use of textual descriptions even with scarce data.
- Model flexibility to integrate with different embedding-based link prediction models.

## 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, 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.