With the development of pre-trained language models, many prompt-based approaches to data-efficient knowledge graph construction have been proposed and achieved impressive performance. However, existing prompt-based learning methods for knowledge graph construction are still susceptible to several potential limitations: (i) semantic gap between natural language and output structured knowledge with pre-defined schema, which means model cannot fully exploit semantic knowledge with the constrained templates; (ii) representation learning with locally individual instances limits the performance given the insufficient features, which are unable to unleash the potential analogical capability of pre-trained language models. Motivated by these observations, we propose a retrieval-augmented approach, which retrieves schema-aware Reference As Prompt (RAP), for data-efficient knowledge graph construction. It can dynamically leverage schema and knowledge inherited from human-annotated and weak-supervised data as a prompt for each sample, which is model-agnostic and can be plugged into widespread existing approaches. Experimental results demonstrate that previous methods integrated with RAP can achieve impressive performance gains in low-resource settings on five datasets of relational triple extraction and event extraction for knowledge graph construction. Code is available in https://github.com/zjunlp/RAP.

翻译：随着预训练语言模型的发展，许多基于提示的数据高效知识图谱构建方法被提出并取得了显著性能。然而，现有基于提示学习的知识图谱构建方法仍存在若干潜在局限：（i）自然语言与预定义模式下的输出结构化知识之间存在语义鸿沟，导致模型无法充分利用约束模板中的语义知识；（ii）基于局部个体实例的表示学习在特征不足时限制性能，未能释放预训练语言模型的潜在类比能力。受这些观察启发，我们提出一种检索增强方法——模式感知的参考提示（RAP），用于数据高效知识图谱构建。该方法可动态利用人工标注与弱监督数据中继承的模式与知识作为每个样本的提示，其具有模型无关性，可嵌入现有广泛方法中。实验结果表明，在关系三元组抽取与事件抽取两类知识图谱构建任务的五个数据集上的低资源场景中，集成RAP的现有方法均能取得显著性能提升。代码已开源至https://github.com/zjunlp/RAP。