论文标题
利用抽象含义表示知识基础问题回答
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
论文作者
论文摘要
知识基础问题回答（KBQA）是自然语言处理中的重要任务。现有方法面临重大挑战，包括复杂的问题理解，推理的必要性以及缺乏大型端到端培训数据集。在这项工作中，我们提出了一个模块化KBQA系统的神经符号问题回答（NSQA），该系统利用（1）抽象含义表示（AMR）解析了与任务无关的问题理解； （2）一种简单而有效的图形转换方法，将AMR解析转换为与KB一致的候选逻辑查询； （3）一种基于管道的方法，该方法集成了多个可重复使用的模块，这些模块是专门针对其单个任务的培训（语义解析器，实体andriations andRiatiationhip Linkers和neuro-Symbolic推理器），并且不需要端到端训练数据。 NSQA基于DBPEDIA（QALD-9和LC-QUAD1.0），在两个突出的KBQA数据集上实现了最先进的性能。此外，我们的分析强调，AMR是KBQA系统的强大工具。
Knowledge base question answering (KBQA)is an important task in Natural Language Processing. Existing approaches face significant challenges including complex question understanding, necessity for reasoning, and lack of large end-to-end training datasets. In this work, we propose Neuro-Symbolic Question Answering (NSQA), a modular KBQA system, that leverages (1) Abstract Meaning Representation (AMR) parses for task-independent question understanding; (2) a simple yet effective graph transformation approach to convert AMR parses into candidate logical queries that are aligned to the KB; (3) a pipeline-based approach which integrates multiple, reusable modules that are trained specifically for their individual tasks (semantic parser, entity andrelationship linkers, and neuro-symbolic reasoner) and do not require end-to-end training data. NSQA achieves state-of-the-art performance on two prominent KBQA datasets based on DBpedia (QALD-9 and LC-QuAD1.0). Furthermore, our analysis emphasizes that AMR is a powerful tool for KBQA systems.
