论文标题
了解概念网中常识关系中的子结构
Understanding Substructures in Commonsense Relations in ConceptNet
论文作者
论文摘要
获得常识性知识和推理是现代NLP研究的重要目标。尽管取得了很多进展，但仍然缺乏对常识性知识本质本质的理解（尤其是在大规模上）。概念网是一种可以用来获取见解的结构常识知识的潜在来源。特别是，概念网包含几种粗粒关系，包括hascontext，formof和符号，这些关系在理解广泛但至关重要的常识性概念（例如“上下文””中是无价的。在本文中，我们提出了一种基于无监督的知识图表示学习和聚类的方法，以揭示和研究ConceptNet中三个大使用的常识关系中的子结构。我们的结果表明，尽管在ConceptNet上具有“官方”定义，但其中许多常识关系表现出相当大的子结构。因此，将来，这种关系可以细分为其他关系，并具有更精致的定义。我们还通过可视化和定性分析来补充我们的核心研究。
Acquiring commonsense knowledge and reasoning is an important goal in modern NLP research. Despite much progress, there is still a lack of understanding (especially at scale) of the nature of commonsense knowledge itself. A potential source of structured commonsense knowledge that could be used to derive insights is ConceptNet. In particular, ConceptNet contains several coarse-grained relations, including HasContext, FormOf and SymbolOf, which can prove invaluable in understanding broad, but critically important, commonsense notions such as 'context'. In this article, we present a methodology based on unsupervised knowledge graph representation learning and clustering to reveal and study substructures in three heavily used commonsense relations in ConceptNet. Our results show that, despite having an 'official' definition in ConceptNet, many of these commonsense relations exhibit considerable sub-structure. In the future, therefore, such relations could be sub-divided into other relations with more refined definitions. We also supplement our core study with visualizations and qualitative analyses.
