Faithful Embeddings for Knowledge Base Queries

Abstract

The deductive closure of an ideal knowledge base (KB) contains exactly the logical queries that the KB can answer. However, in practice KBs are both incomplete and over-specified, failing to answer some queries that have real-world answers. \emph{Query embedding} (QE) techniques have been recently proposed where KB entities and KB queries are represented jointly in an embedding space, supporting relaxation and generalization in KB inference. However, experiments in this paper show that QE systems may disagree with deductive reasoning on answers that do not require generalization or relaxation. We address this problem with a novel QE method that is more faithful to deductive reasoning, and show that this leads to better performance on complex queries to incomplete KBs. Finally we show that inserting this new QE module into a neural question-answering system leads to substantial improvements over the state-of-the-art.

arXiv commentPublished at 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada

References in corpus (10)

• Analogical Inference for Multi-Relational Embeddings
• Variational Reasoning for Question Answering with Knowledge Graph
• Word Representations via Gaussian Embedding
• Traversing Knowledge Graphs in Vector Space
• Modeling Relation Paths for Representation Learning of Knowledge Bases
• Embedding Logical Queries on Knowledge Graphs
• PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
• TensorLog: Deep Learning Meets Probabilistic DBs
• Neural Query Language: A Knowledge Base Query Language for Tensorflow
• Sketching and Neural Networks

Cited by in corpus (7)

• Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs
• Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge
• A Survey of Knowledge Enhanced Pre-trained Models
• SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs
• Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs
• Query Embedding on Hyper-relational Knowledge Graphs
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs