Augmentic Compositional Models for Knowledge Base Completion Using Gradient Representations

Matthias R. Lalisse, Paul Smolensky
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 wellformedness conditions on Knowledge Base triplets. The resulting model, known as Gradient Graphs, leads to
more » ... e 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.
doi:10.7275/8et8-qd83 fatcat:fobjxseewvbs3pvf25gkbw4pra