Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations

2018/11/02 by Lalisse, Matthias, Smolensky, Paul
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1811.01062

Abstract

Neural models of Knowledge Base data have typically employed compositional representations of graph objects: entity and relation embeddings are systematically combined to evaluate the truth of a candidate Knowedge Base entry. Using a model inspired by Harmonic Grammar, we propose to tokenize triplet embeddings by subjecting them to a process of optimization with respect to learned well-formedness conditions on Knowledge Base triplets. The resulting model, known as Gradient Graphs, leads to sizable improvements when implemented as a companion to compositional models. Also, we show that the "supracompositional" triplet token embeddings it produces have interpretable properties that prove helpful in performing inference on the resulting triplet representations.

Related

• Improved Knowledge Graph Embedding using Background Taxonomic\n Information
• Neural Compositional Rule Learning for Knowledge Graph Reasoning
• Compositional Vector Space Models for Knowledge Base Completion
• LogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical\n Rules
• Rule-Guided Compositional Representation Learning on Knowledge Graphs