We address the problem of learning vector representations for entities and relations in Knowledge Graphs (KGs) for Knowledge Base Completion (KBC). This problem has received significant attention in the past few years and multiple methods have been proposed. Most of the existing methods in the literature use a predefined characteristic scoring function for evaluating the correctness of KG triples. These scoring functions distinguish correct triples (high score) from incorrect ones (low score). However, their performance vary across different datasets. In this work, we demonstrate that a simple neural network based score function can consistently achieve near start-of-the-art performance on multiple datasets. We also quantitatively demonstrate biases in standard benchmark datasets, and highlight the need to perform evaluation spanning various datasets.
翻译:我们处理在知识图(KGs)中各实体的学习矢量表现和知识库完成(KBC)关系中的学习矢量表现问题。这个问题在过去几年中受到极大关注,并提出了多种方法。文献中的大多数现有方法都使用预先界定的特征评分功能来评价KG三重的正确性。这些评分功能区分正确的三重(高分)和不正确的三重(低分),但是它们在不同数据集中的表现不尽相同。在这项工作中,我们证明基于神经网络的评分功能可以始终在多个数据集方面实现近于最先进的性能。我们还从数量上表明标准基准数据集中的偏差,并强调需要对各种数据集进行评价。