Knowledge Base Question Answering by Case-based Reasoning over Subgraphs

TL;DR

This paper introduces a novel case-based reasoning model for knowledge base question answering that leverages local subgraph similarities to improve reasoning and scalability over large KBs.

Contribution

The paper proposes CBR-SUBG, a semiparametric model that dynamically retrieves similar subgraphs and learns reasoning patterns, enabling scalable and accurate KBQA.

Findings

Achieves competitive performance on KBQA benchmarks.

Reduces subgraph size by 55% while increasing answer recall.

Demonstrates effective reasoning over large knowledge bases.

Abstract

Question answering (QA) over knowledge bases (KBs) is challenging because of the diverse, essentially unbounded, types of reasoning patterns needed. However, we hypothesize in a large KB, reasoning patterns required to answer a query type reoccur for various entities in their respective subgraph neighborhoods. Leveraging this structural similarity between local neighborhoods of different subgraphs, we introduce a semiparametric model (CBR-SUBG) with (i) a nonparametric component that for each query, dynamically retrieves other similar $k$-nearest neighbor (KNN) training queries along with query-specific subgraphs and (ii) a parametric component that is trained to identify the (latent) reasoning patterns from the subgraphs of KNN queries and then apply them to the subgraph of the target query. We also propose an adaptive subgraph collection strategy to select a query-specific compact subgraph, allowing us to scale to full Freebase KB containing billions of facts. We show that CBR-SUBG can answer queries requiring subgraph reasoning patterns and performs competitively with the best models on several KBQA benchmarks. Our subgraph collection strategy also produces more compact subgraphs (e.g. 55\% reduction in size for WebQSP while increasing answer recall by 4.85\%)\footnote{Code, model, and subgraphs are available at \url{https://github.com/rajarshd/CBR-SUBG}}.