Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations
This work addresses knowledge base completion for AI systems, presenting an incremental enhancement to existing neural models.
The paper tackled the problem of knowledge base completion by augmenting compositional models with gradient-based tokenization of triplet embeddings, resulting in sizable improvements in performance.
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.