An ontology-based deep learning approach for triple classification with out-of-knowledge-base entities
An ontology-based deep learning approach for triple classification with out-of-knowledge-base entities
复制标题
DOI：
10.1016/j.ins.2021.02.018
复制
发表时间：
2021-02
期刊：
影响因子：
--
通讯作者：
Elvira Amador-Domínguez;E. Serrano;Daniel Manrique;Patrick Hohenecker;Thomas Lukasiewicz
中科院分区：
文献类型：
--
作者：
Elvira Amador-Domínguez;E. Serrano;Daniel Manrique;Patrick Hohenecker;Thomas Lukasiewicz
知识图(KGs)是最常用的知识表示框架之一。然而，它们面临着严重的可伸缩性问题，阻碍了它们的使用。KG嵌入旨在为这一问题提供解决方案。尽管如此，一般的方法不能表示和推理先前未包含在图中的信息。本文提出利用语义和本体信息来实现知识图补全的显著好处，重点是三重分类。这项任务的目标是确定给定的事实是否成立。此外，本文还考虑了包括在训练过程中未见的实体在内的事实的分类，称为知识库外实体或OOKB实体。提出了一种增量方法，该方法由六个阶段组成。虽然该方案可以应用于任何KG嵌入模型，但本文的工作主要集中在它在语义匹配模型上的应用，如Complex和DistMult。与其他方法相比，我们的建议是模型不可知的，计算成本低，并且不需要重新培训。结果表明，该方法的三重分类精度可达15%，并加快了模型收敛到最优解的速度。此外，包含OOKB实体的事实可以合理准确地分类。
Knowledge graphs (KGs) are one of the most common frameworks for knowledge representation. However, they suffer from a severe scalability problem that hinders their usage. KG embedding aims to provide a solution to this issue. Nonetheless, general approaches are incapable of representing and reasoning about information not previously contained in the graph. This paper proposes to leverage semantic and ontological information for a significant benefit of knowledge graph completion, focusing on triple classification. The goal of this task is to determine whether a given fact holds. Furthermore, this paper also considers the classification of facts that include entities that have not been seen during training, denoted out-of-knowledge-base orOOKBentities. An incremental method is presented, composed of six stages. Although the proposal can be applied to any KG embedding model, this work focuses on its application for semantic matching models, such as ComplEx and DistMult. Compared to other approaches, our proposal is model-agnostic, computationally inexpensive, and does not require retraining. The results show that triple classification accuracy scales up to 15% with the proposed approach, as well as accelerating the convergence of the model to its optimal solution. Furthermore, facts containing OOKB entities can be classified with a reasonable accuracy.