English

An Open-World Extension to Knowledge Graph Completion Models

Artificial Intelligence 2020-01-10 v1 Computation and Language

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.

Keywords

Cite

@article{arxiv.1906.08382,
  title  = {An Open-World Extension to Knowledge Graph Completion Models},
  author = {Haseeb Shah and Johannes Villmow and Adrian Ulges and Ulrich Schwanecke and Faisal Shafait},
  journal= {arXiv preprint arXiv:1906.08382},
  year   = {2020}
}

Comments

8 pages, accepted to AAAI-2019

R2 v1 2026-06-23T09:58:33.165Z