论文标题
通过弱监督重新利用知识图嵌入三重表示
Repurposing Knowledge Graph Embeddings for Triple Representation via Weak Supervision
论文作者
论文摘要
大多数知识图嵌入技术将实体和谓词视为单独的嵌入矩阵，使用聚合函数来构建输入三重的表示。但是，这些聚集是有损的，即它们没有捕获原始三元组的语义，例如谓词中包含的信息。为了消除这些缺点，当前方法从头开始学习三重嵌入，而无需利用预训练模型的实体和谓词嵌入。在本文中，我们通过从预训练的知识图嵌入中创建弱监督信号来设计一种新型的微调方法，以学习三重嵌入。我们开发了一种从知识图中自动采样三联的方法，并从预训练的嵌入模型中估算了它们的成对相似性。然后将这些成对的相似性得分馈送到类似暹罗的神经结构中，以微调三重表示。我们在两个广泛研究的知识图上评估了提出的方法，并在三重分类和三重聚类任务上显示出比其他最先进的三重嵌入方法的一致改进。
The majority of knowledge graph embedding techniques treat entities and predicates as separate embedding matrices, using aggregation functions to build a representation of the input triple. However, these aggregations are lossy, i.e. they do not capture the semantics of the original triples, such as information contained in the predicates. To combat these shortcomings, current methods learn triple embeddings from scratch without utilizing entity and predicate embeddings from pre-trained models. In this paper, we design a novel fine-tuning approach for learning triple embeddings by creating weak supervision signals from pre-trained knowledge graph embeddings. We develop a method for automatically sampling triples from a knowledge graph and estimating their pairwise similarities from pre-trained embedding models. These pairwise similarity scores are then fed to a Siamese-like neural architecture to fine-tune triple representations. We evaluate the proposed method on two widely studied knowledge graphs and show consistent improvement over other state-of-the-art triple embedding methods on triple classification and triple clustering tasks.
