Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
This addresses generalization issues in knowledge base question answering, which is crucial for real-world applications, though it appears incremental as it builds on existing methods with schema enhancements.
The paper tackles the problem of KBQA models struggling with unseen knowledge base elements at test time by introducing SG-KBQA, which uses schema contexts to improve generalization, achieving state-of-the-art performance on two benchmark datasets.
Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with unseen knowledge base elements at test time,we introduce SG-KBQA: a novel model that injects schema contexts into entity retrieval and logical form generation to tackle this issue. It uses the richer semantics and awareness of the knowledge base structure provided by schema contexts to enhance generalizability. We show that SG-KBQA achieves strong generalizability, outperforming state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. Our source code is available at https://github.com/gaosx2000/SG_KBQA.