An Open-World Extension to Knowledge Graph Completion Models

Authors

  • Haseeb Shah National University of Sciences and Technology
  • Johannes Villmow RheinMain University of Applied Sciences
  • Adrian Ulges RheinMain University of Applied Sciences
  • Ulrich Schwanecke RheinMain University of Applied Sciences
  • Faisal Shafait National University of Sciences and Technology

DOI:

https://doi.org/10.1609/aaai.v33i01.33013044

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.

Downloads

Published

2019-07-17

How to Cite

Shah, H., Villmow, J., Ulges, A., Schwanecke, U., & Shafait, F. (2019). An Open-World Extension to Knowledge Graph Completion Models. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 3044-3051. https://doi.org/10.1609/aaai.v33i01.33013044

Issue

Section

AAAI Technical Track: Knowledge Representation and Reasoning