Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering

Abstract

Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning. A desired subgraph is crucial as a small one may exclude the answer but a large one might introduce more noises. However, the existing retrieval is either heuristic or interwoven with the reasoning, causing reasoning on the partial subgraphs, which increases the reasoning bias when the intermediate supervision is missing. This paper proposes a trainable subgraph retriever (SR) decoupled from the subsequent reasoning process, which enables a plug-and-play framework to enhance any subgraph-oriented KBQA model. Extensive experiments demonstrate SR achieves significantly better retrieval and QA performance than existing retrieval methods. Via weakly supervised pre-training as well as the end-to-end fine-tuning, SRl achieves new state-of-the-art performance when combined with NSM, a subgraph-oriented reasoner, for embedding-based KBQA methods.

The experimental results are updated by fixing the data leakage issue in the code

References in corpus (3)

• Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals
• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering

Cited by in corpus (3)

• Leveraging Medical Knowledge Graphs Into Large Language Models for Diagnosis Prediction: Design and Application Study
• In-Context Learning for Knowledge Base Question Answering for Unmanned Systems based on Large Language Models
• Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach