Complex question answering over knowledge base (Complex KBQA) is challenging because it requires various compositional reasoning capabilities, such as multi-hop inference, attribute comparison, set operation. Existing benchmarks have some shortcomings that limit the development of Complex KBQA: 1) they only provide QA pairs without explicit reasoning processes; 2) questions are poor in diversity or scale. To this end, we introduce KQA Pro, a dataset for Complex KBQA including ~120K diverse natural language questions. We introduce a compositional and interpretable programming language KoPL to represent the reasoning process of complex questions. For each question, we provide the corresponding KoPL program and SPARQL query, so that KQA Pro serves for both KBQA and semantic parsing tasks. Experimental results show that SOTA KBQA methods cannot achieve promising results on KQA Pro as on current datasets, which suggests that KQA Pro is challenging and Complex KBQA requires further research efforts. We also treat KQA Pro as a diagnostic dataset for testing multiple reasoning skills, conduct a thorough evaluation of existing models and discuss further directions for Complex KBQA. Our codes and datasets can be obtained from https://github.com/shijx12/KQAPro_Baselines.
翻译:回答知识基础(Complex KBQA)的复杂问题具有挑战性,因为它需要多种构成推理能力,例如多点推理、属性比较、设定操作等。现有的基准有一些缺点,限制了复杂的 KBQA的发展:(1) 它们只提供质量A配对,而没有明确的推理程序;(2) 问题在多样性或规模上都很差。 为此,我们为复杂的 KBQAA 引入了KQA Pro 数据集, 包括~120K多样化的自然语言问题。 我们引入了一种组成和可解释的编程语言 KOPL, 以代表复杂问题的推理过程。 对于每一个问题,我们提供相应的 KPL 程序和 SPARQL 查询, 以便 KQA ProQA ProQA 服务于 KBQA 和 语义分析任务; 实验结果表明, SOTA KBA 方法无法在目前数据集上取得有希望的结果。 这表明 KQA Pro Pro Proqa Prochal KBA 和 Complas KBA 进一步的指南。