A Two-Stage Approach towards Generalization in Knowledge Base Question Answering

TL;DR

This paper proposes a two-stage KBQA framework that separates semantic parsing from knowledge base interaction, enabling transfer learning across different datasets and knowledge graphs, and achieving state-of-the-art results.

Contribution

It introduces a novel two-stage architecture for KBQA that enhances generalization and transfer learning across multiple knowledge bases.

Findings

Pretraining on different knowledge bases improves performance.

The approach achieves state-of-the-art results on multiple datasets.

Explicit separation of parsing and KB interaction facilitates transfer learning.

Abstract

Most existing approaches for Knowledge Base Question Answering (KBQA) focus on a specific underlying knowledge base either because of inherent assumptions in the approach, or because evaluating it on a different knowledge base requires non-trivial changes. However, many popular knowledge bases share similarities in their underlying schemas that can be leveraged to facilitate generalization across knowledge bases. To achieve this generalization, we introduce a KBQA framework based on a 2-stage architecture that explicitly separates semantic parsing from the knowledge base interaction, facilitating transfer learning across datasets and knowledge graphs. We show that pretraining on datasets with a different underlying knowledge base can nevertheless provide significant performance gains and reduce sample complexity. Our approach achieves comparable or state-of-the-art performance for LC-QuAD (DBpedia), WebQSP (Freebase), SimpleQuestions (Wikidata) and MetaQA (Wikimovies-KG).