Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph
Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph
复制标题
DOI：
10.1007/978-3-319-63703-7_11
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
D. Summers-Stay
中科院分区：
文献类型：
--
作者：
D. Summers-Stay
将知识表示为连续语义向量空间中的高维向量，有助于克服传统知识库的脆性和不完备性。我们提出了一种在这样的向量空间中直接执行演绎推理的方法，利用来自不同来源和本体的知识，在推理链的每一步以直接的方式结合类比、联想和演绎。
Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases. We present a method for performing deductive reasoning directly in such a vector space, combining analogy, association, and deduction in a straightforward way at each step in a chain of reasoning, drawing on knowledge from diverse sources and ontologies.