Knowledge Extraction (KE), aiming to extract structural information from unstructured texts, often suffers from data scarcity and emerging unseen types, i.e., low-resource scenarios. Many neural approaches to low-resource KE have been widely investigated and achieved impressive performance. In this paper, we present a literature review towards KE in low-resource scenarios, and systematically categorize existing works into three paradigms: (1) exploiting higher-resource data, (2) exploiting stronger models, and (3) exploiting data and models together. In addition, we highlight promising applications and outline some potential directions for future research. We hope that our survey can help both the academic and industrial communities to better understand this field, inspire more ideas, and boost broader applications.

翻译：知识抽取（KE）旨在从非结构化文本中提取结构化信息，但常面临数据稀缺和新兴未见类型（即低资源场景）的挑战。针对低资源知识抽取的多种神经方法已被广泛研究并取得了显著性能。本文对低资源场景下的知识抽取进行了文献综述，系统性地将现有工作归纳为三种范式：(1) 利用高资源数据、(2) 利用更强的模型，以及(3) 同时利用数据与模型。此外，我们重点介绍了有前景的应用，并展望了一些未来研究方向。希望本综述能帮助学术界与工业界更好地理解该领域，激发更多思路，并推动更广泛的应用。