A shallow neural model for relation prediction

2021/01/22 by Demir, Caglar, Moussallem, Diego, Ngomo, Axel-Cyrille Ngonga
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2101.09090

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% and 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 \urlhttps://github.com/dice-group/Shallom.

Related

• Learning Attention-based Embeddings for Relation Prediction in Knowledge\n Graphs
• MUSE: Multi-Knowledge Passing on the Edges, Boosting Knowledge Graph Completion
• Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations
• Investigations on Knowledge Base Embedding for Relation Prediction and Extraction
• Relations Prediction for Knowledge Graph Completion using Large Language Models