English

A shallow neural model for relation prediction

Machine Learning 2021-01-25 v1 Computation and Language

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 3%3\% and 8%8\% (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}.}

Keywords

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

R2 v1 2026-06-23T22:25:20.782Z