arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.14843cs.AIcs.CL
收藏

知识图谱嵌入与可解释的AI

Knowledge Graph Embeddings and Explainable AI

Bocconi University(博科尼大学);IBM Research AI(IBM研究AI);Accenture Labs(埃森哲实验室);University of Milan-Bicocca(米兰比可卡大学);University College London(伦敦大学学院)

Federico Bianchi, Gaetano Rossiello, Luca Costabello, Matteo Palmonari, Pasquale Minervini

摘要:

知识图谱嵌入是一种广泛采用的知识表示方法,其中实体和关系嵌入在向量空间中。在本章中,我们通过解释知识图谱嵌入的概念、如何生成它们以及如何评估它们来向读者介绍它们。我们总结了国家的最先进的在这一领域中描述的方法,已被引入到表示知识的向量空间。在知识表示方面,我们考虑了可解释性问题,并讨论了解释通过知识图谱嵌入获得的预测的模型和方法。

英文摘要:

Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces. In this chapter, we introduce the reader to the concept of knowledge graph embeddings by explaining what they are, how they can be generated and how they can be evaluated. We summarize the state-of-the-art in this field by describing the approaches that have been introduced to represent knowledge in the vector space. In relation to knowledge representation, we consider the problem of explainability, and discuss models and methods for explaining predictions obtained via knowledge graph embeddings.

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。

↑