Why a Naive Way to Combine Symbolic and Latent Knowledge Base Completion Works Surprisingly Well
doi:10.24432/C5PK5V
TL;DR
We compare a rule-based approach for knowledge graph completion against current state-of-the-art, which is based on embbedings. Instead of focusing on aggregated metrics, we look at several examples that illustrate essential differences between symbolic and latent approaches. Based on our insights, we construct a simple method to combine the outcome of rule-based and latent approaches in a post-processing step. Our method improves the results constantly for each model and dataset used in our experiments.
Citation
@inproceedings{
meilicke2021why,
title={Why a Naive Way to Combine Symbolic and Latent Knowledge Base Completion Works Surprisingly Well},
author={Christian Meilicke and Patrick Betz and Heiner Stuckenschmidt},
booktitle={3rd Conference on Automated Knowledge Base Construction},
year={2021},
url={https://openreview.net/forum?id=JQHqeGx6qFw},
doi={10.24432/C5PK5V}
}