A Two-Stage Approach towards Generalization in Knowledge Base Question Answering
This addresses the challenge of KBQA systems being tied to specific knowledge bases, enabling more flexible and efficient applications in question answering.
The paper tackles the problem of generalizing Knowledge Base Question Answering (KBQA) across different knowledge bases by introducing a two-stage framework that separates semantic parsing from knowledge base interaction, achieving comparable or state-of-the-art performance on multiple datasets like LC-QuAD, WebQSP, SimpleQuestions, and MetaQA.
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).