Faithful Embeddings for Knowledge Base Queries

TL;DR

This paper introduces a new query embedding method that aligns more closely with deductive reasoning, improving complex query answering on incomplete knowledge bases and enhancing neural question-answering systems.

Contribution

A novel query embedding technique that increases faithfulness to deductive reasoning, leading to improved performance on complex queries and integration into neural QA systems.

Findings

Better accuracy on complex KB queries

Improved neural question-answering performance

Enhanced faithfulness to logical deduction

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.