ProtoE: Enhancing Knowledge Graph Completion Models with Unsupervised Type Representation Learning

Knowledge graph completion (KGC) models are a feasible approach for manipulating facts in knowledge graphs. However, the lack of entity types in current KGC models results in inaccurate link prediction results. Most existing type-aware KGC models require entity type annotations, which are not always available and expensive to obtain. We propose ProtoE, an unsupervised method for learning implicit type and type constraint representations. ProtoE enhances type-agnostic KGC models by relation-specific prototype embeddings. Our method does not rely on entity type annotations to capture the type and type constraints of entities. Unlike existing unsupervised type representation learning methods, which have only a single representation for entity-type and relation-type constraints, our method can capture multiple type constraints in relations. Experimental results show that our method can improve the performance of both bilinear and translational KGC models in the link prediction task.