Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph

07/11/2017
by   Douglas Summers-Stay, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/13/2016

Using a Distributional Semantic Vector Space with a Knowledge Base for Reasoning in Uncertain Conditions

The inherent inflexibility and incompleteness of commonsense knowledge b...
research
05/26/2018

From Knowledge Graph Embedding to Ontology Embedding: Region Based Representations of Relational Structures

Recent years have witnessed the enormous success of low-dimensional vect...
research
08/10/2017

Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs

Knowledge graphs and vector space models are robust knowledge representa...
research
04/21/2018

Extrofitting: Enriching Word Representation and its Vector Space with Semantic Lexicons

We propose post-processing method for enriching not only word representa...
research
01/15/2023

On the graph of non-degenerate linear [n,2]_2 codes

Consider the Grassmann graph of k-dimensional subspaces of an n-dimensio...
research
01/31/2020

A comparison of Vector Symbolic Architectures

Vector Symbolic Architectures (VSAs) combine a high-dimensional vector s...
research
09/24/2018

Representing Sets as Summed Semantic Vectors

Representing meaning in the form of high dimensional vectors is a common...

Please sign up or login with your details

Forgot password? Click here to reset