论文标题
具有多层元图神经网络的规范化开放知识基础
Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network
论文作者
论文摘要
开放知识基础中的名词短语和关系短语通常不是规范性的，导致了多余和模棱两可的事实。在这项工作中，我们整合了结构信息（从哪个元素，哪个句子）和语义信息（语义相似性）来进行规范化。我们将两种类型的信息表示为多层图：结构信息形成了整个句子的链接，关系短语和名词短语层；语义信息为每一层形成加权内部链路。我们提出了一个图形神经网络模型，以通过多层元图结构来汇总名词短语和关系短语的表示。实验表明，我们的模型在一般域中的公共数据集上优于现有方法。
Noun phrases and relational phrases in Open Knowledge Bases are often not canonical, leading to redundant and ambiguous facts. In this work, we integrate structural information (from which tuple, which sentence) and semantic information (semantic similarity) to do the canonicalization. We represent the two types of information as a multi-layered graph: the structural information forms the links across the sentence, relational phrase, and noun phrase layers; the semantic information forms weighted intra-layer links for each layer. We propose a graph neural network model to aggregate the representations of noun phrases and relational phrases through the multi-layered meta-graph structure. Experiments show that our model outperforms existing approaches on a public datasets in general domain.
