arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.01389cs.DBcs.IR
收藏

知识图谱验证

Knowledge Graph Validation

Elwin Huaman, Elias Kärle, Dieter Fensel

摘要:

知识图谱(KG)已被证明是谷歌和微软等大公司的重要资产。知识库在提供结构化和语义丰富的信息,使它们可用于人和机器,并提供准确,正确和可靠的知识方面发挥着重要作用。要做到这一点,一个关键的任务是知识验证,它衡量是否从KG语句是语义正确的,并对应于所谓的“真实”世界。在本文中,我们提供了一个概述和审查的国家的最先进的方法,方法和工具知识验证的幼儿园,以及他们的评价。因此,我们证明了工具结果缺乏可重复性,给出了见解,并说明了我们未来的研究方向。

英文摘要:

Knowledge graphs (KGs) have shown to be an important asset of large companies like Google and Microsoft. KGs play an important role in providing structured and semantically rich information, making them available to people and machines, and supplying accurate, correct and reliable knowledge. To do so a critical task is knowledge validation, which measures whether statements from KGs are semantically correct and correspond to the so-called "real" world. In this paper, we provide an overview and review of the state-of-the-art approaches, methods and tools on knowledge validation for KGs, as well as an evaluation of them. As a result, we demonstrate a lack of reproducibility of tools results, give insights, and state our future research direction.

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。

↑