Knowledge Extraction (KE) which aims to extract structural information from unstructured texts often suffers from data scarcity and emerging unseen types, i.e., low-resource scenarios. Many neural approaches on 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 describe promising applications and outline some potential directions for future research. We hope that our survey can help both the academic and industrial community to better understand this field, inspire more ideas and boost broader applications.
翻译:旨在从非结构化文本中提取结构性信息的《知识提取》(KE)往往缺乏数据,而且出现了新的不可见类型,即低资源情景。许多关于低资源 KE的神经方法已经受到广泛调查并取得了令人印象深刻的业绩。在本文中,我们介绍了在低资源情景下对KE的文献审查,并将现有作品系统地分为三种模式:(1) 利用高资源数据,(2) 利用更强大的模型,(3) 共同利用数据和模型。此外,我们描述了有希望的应用,并概述了未来研究的一些潜在方向。我们希望我们的调查能够帮助学术界和产业界更好地了解这一领域,激发更多想法,促进更广泛的应用。