arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.03514cs.AI
收藏

可解释的深度RDFS推理

Explainable Deep RDFS Reasoner

IBM Research(IBM研究院);IBM T.J. Watson Research Center(IBM托马斯·J·沃森研究中心);Rensselaer Polytechnic Institute(伦斯勒理工学院)

Bassem Makni, Ibrahim Abdelaziz, James Hendler

摘要:

最近的研究工作旨在弥合RDFS推理的神经符号差距,经验证明深度学习技术可以用于学习RDFS推理规则。然而,与基于规则的推理机相比,它们的主要缺陷之一是缺乏对推断三元组的推导(即AI术语的可解释性)。在本文中,我们建立在这些方法,不仅提供推断图,但也解释了如何推断这些三元组。在图词方法中,RDF图被表示为一系列图词,其中可以通过神经机器翻译来实现推理。为了实现RDFS推理的可解释性,我们重新审视这种方法,并引入一个新的神经网络模型,该模型获得输入图-作为一个序列的图形字-以及推断三元组的编码,并输出推断三元组的推导。我们在两个数据集上评估了我们的合理性模型:一个合成数据集- LUBM基准-和一个真实世界的数据集-关于会议的学术数据-其中最低的验证准确率接近96%。

英文摘要:

Recent research efforts aiming to bridge the Neural-Symbolic gap for RDFS reasoning proved empirically that deep learning techniques can be used to learn RDFS inference rules. However, one of their main deficiencies compared to rule-based reasoners is the lack of derivations for the inferred triples (i.e. explainability in AI terms). In this paper, we build on these approaches to provide not only the inferred graph but also explain how these triples were inferred. In the graph words approach, RDF graphs are represented as a sequence of graph words where inference can be achieved through neural machine translation. To achieve explainability in RDFS reasoning, we revisit this approach and introduce a new neural network model that gets the input graph--as a sequence of graph words-- as well as the encoding of the inferred triple and outputs the derivation for the inferred triple. We evaluated our justification model on two datasets: a synthetic dataset-- LUBM benchmark-- and a real-world dataset --ScholarlyData about conferences-- where the lowest validation accuracy approached 96%.

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。

↑