In this paper, we propose a new method for knowledge base completion (KBC): instance-based learning (IBL). For example, to answer (Jill Biden, lived city,? ), instead of going directly to Washington D.C., our goal is to find Joe Biden, who has the same lived city as Jill Biden. Through prototype entities, IBL provides interpretability. We develop theories for modeling prototypes and combining IBL with translational models. Experiments on various tasks confirmed the IBL model's effectiveness and interpretability.
In addition, IBL shed light on the mechanism of rule-based KBC models. Previous research has generally agreed that rule-based models provide rules with semantically compatible premises and hypotheses. We challenge this view. We begin by demonstrating that some logical rules represent {\it instance-based equivalence} (i.e. prototypes) rather than semantic compatibility. These are denoted as {\it IBL rules}. Surprisingly, despite occupying only a small portion of the rule space, IBL rules outperform non-IBL rules in all four benchmarks. We use a variety of experiments to demonstrate that rule-based models work because they have the ability to represent instance-based equivalence via IBL rules. The findings provide new insights of how rule-based models work and how to interpret their rules.
Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Institute of Artificial Intelligence, Beihang University(北京航空航天大学人工智能研究院);School of Computer Science, Beihang University(北京航空航天大学计算机学院);University of Notre Dame(圣母大学)
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
Peking University(北京大学);Washington University in St. Louis(圣路易斯华盛顿大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);UC Berkeley(加州大学伯克利分校)