A shallow neural model for relation prediction
Abstract
Knowledge graph completion refers to predicting missing triples. Most approaches achieve this goal by predicting entities, given an entity and a relation. We predict missing triples via the relation prediction. To this end, we frame the relation prediction problem as a multi-label classification problem and propose a shallow neural model (SHALLOM) that accurately infers missing relations from entities. SHALLOM is analogous to C-BOW as both approaches predict a central token (p) given surrounding tokens ((s,o)). Our experiments indicate that SHALLOM outperforms state-of-the-art approaches on the FB15K-237 and WN18RR with margins of up to and (absolute), respectively, while requiring a maximum training time of 8 minutes on these datasets. We ensure the reproducibility of our results by providing an open-source implementation including training and evaluation scripts at {\url{https://github.com/dice-group/Shallom}.}
Cite
@article{arxiv.2101.09090,
title = {A shallow neural model for relation prediction},
author = {Caglar Demir and Diego Moussallem and Axel-Cyrille Ngonga Ngomo},
journal= {arXiv preprint arXiv:2101.09090},
year = {2021}
}
Comments
15th IEEE International Conference on Semantic Computing, ICSC-2021