FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering

2023/06/26 by Lingxi Zhang, Jing Zhang, Zhang, Lingxi +13 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Semantic Web and Ontologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2306.14722

openalex publication_date 2023/06/26 · openalex created_date 2023/06/28 · openalex updated_date 2026/07/28

Abstract

The generalization problem on KBQA has drawn considerable attention. Existing research suffers from the generalization issue brought by the entanglement in the coarse-grained modeling of the logical expression, or inexecutability issues due to the fine-grained modeling of disconnected classes and relations in real KBs. We propose a Fine-to-Coarse Composition framework for KBQA (FC-KBQA) to both ensure the generalization ability and executability of the logical expression. The main idea of FC-KBQA is to extract relevant fine-grained knowledge components from KB and reformulate them into middle-grained knowledge pairs for generating the final logical expressions. FC-KBQA derives new state-of-the-art performance on GrailQA and WebQSP, and runs 4 times faster than the baseline.

Cited by

• KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
• RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
• KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering

Related

• Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
• KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base
• A Learn-Then-Reason Model Towards Generalization in Knowledge Base Question Answering
• A Two-Stage Approach towards Generalization in Knowledge Base Question Answering
• KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering