通过结构化模式增强实体检索与逻辑生成，提升知识库问答模型泛化能力
Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
- 利用知识库模式上下文增强实体检索和逻辑形式生成
- 在两个基准数据集上超越现有模型，测试场景下表现更稳定
- 适合关注知识库问答泛化性能的研究者与工程师
知识库问答（KBQA）旨在利用大型知识库中的丰富人类知识回答自然语言问题。当前的KBQA方法在测试时面对未见过的知识库元素时表现不佳。为此，我们提出SG-KBQA：一种将知识库模式上下文注入实体检索和逻辑形式生成的新模型。通过利用模式上下文提供的更丰富语义和结构意识，显著提升模型泛化能力。实验表明，SG-KBQA在两个常用基准数据集上，多种测试设置下均优于现有最先进模型。源代码已公开于https://github.com/gaosx2000/SG_KBQA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。