arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.06807cs.AIcs.LG
收藏

基于实例学习的知识库补全

Instance-based Learning for Knowledge Base Completion

University of Michigan(密歇根大学)

Wanyun Cui, Xingran Chen

摘要:

在本文中,我们提出了一种新的方法,知识库完成(KBC):基于实例的学习(IBL)。例如,回答(吉尔拜登,生活的城市,?),而不是直接前往华盛顿特区,我们的目标是找到乔·拜登,他和吉尔·拜登有着同样的生活城市。通过原型实体,IBL提供了可解释性。我们开发的理论建模原型和IBL与翻译模型相结合。在不同任务上的实验证实了IBL模型的有效性和可解释性。此外,IBL揭示了基于规则的KBC模型的机制。以往的研究普遍认为,基于规则的模型提供的规则与语义兼容的前提和假设。我们对这一观点提出质疑。我们首先证明,一些逻辑规则表示{ \it基于实例的等价}(即原型),而不是语义兼容性。这些规则表示为{ \it IBL规则}。令人惊讶的是,尽管只占用了一小部分规则空间,但IBL规则在所有四个基准测试中都优于非IBL规则。我们使用各种实验来证明,基于规则的模型的工作,因为他们有能力通过IBL规则表示基于实例的等价。这些发现为基于规则的模型如何工作以及如何解释其规则提供了新的见解。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑