Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
This addresses the challenge of noisy or incomplete subgraphs in KBQA, offering a plug-and-play solution to enhance existing models, though it is incremental as it builds on prior subgraph-oriented methods.
The paper tackles the problem of retrieving optimal subgraphs for multi-hop knowledge base question answering by proposing a trainable subgraph retriever decoupled from reasoning, which significantly improves retrieval and QA performance, achieving new state-of-the-art results when combined with NSM.
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.