Published on Mon Jun 13 2016

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

Douglas Summers-Stay, Clare Voss, Taylor Cassidy

The inherent inflexibility and incompleteness of commonsense knowledge bases (KB) has limited their usefulness. We describe a system called Displacer for performing KB queries extended with the analogical capabilities of the word2vecal semantic vector space (DSVS)

0
0
0
Abstract

The inherent inflexibility and incompleteness of commonsense knowledge bases (KB) has limited their usefulness. We describe a system called Displacer for performing KB queries extended with the analogical capabilities of the word2vec distributional semantic vector space (DSVS). This allows the system to answer queries with information which was not contained in the original KB in any form. By performing analogous queries on semantically related terms and mapping their answers back into the context of the original query using displacement vectors, we are able to give approximate answers to many questions which, if posed to the KB alone, would return no results. We also show how the hand-curated knowledge in a KB can be used to increase the accuracy of a DSVS in solving analogy problems. In these ways, a KB and a DSVS can make up for each other's weaknesses.

Fri Feb 23 2018
Artificial Intelligence
Semantic Vector Spaces for Broadening Consideration of Consequences
Hand-encoding the enormous and subtle body of facts into a knowledge base has proved too difficult despite decades of work. Distributed semantic vector spaces learned from large text corpora, on the other hand, can learn representations that capture shades of meaning of common-sense concepts.
0
0
0
Tue Jul 11 2017
Artificial Intelligence
Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph
We present a method for performing deductive reasoning directly in such a vector space. We combine analogy, association, and Deduction in a straightforward way at each step in a chain of reasoning. We draw on knowledge from diverse sources and ontologies.
0
0
0
Wed Jul 13 2016
Machine Learning
A Vector Space for Distributional Semantics for Entailment
Distributional semantics creates vector-space representations that capture many forms of semantic similarity. Their relation to semantic entailment has been less clear. We propose a model which provides a formal foundation for the distributional semantics of entailment.
0
0
0
Fri Aug 08 2008
Artificial Intelligence
Commonsense Knowledge, Ontology and Ordinary Language
In this paper we hope to demonstrate that both trends are partly misguided. The time has come to replace logical semantics with an ontological structure that reflects our Commonsense view of the world.
0
0
0
Wed Oct 11 2006
Artificial Intelligence
Language, logic and ontology: uncovering the structure of commonsense knowledge
0
0
0
Mon Jan 24 2011
Artificial Intelligence
A Context-theoretic Framework for Compositionality in Distributional Semantics
There is currently no general semantic formalism for representing meaning in terms of vectors. We show that the vector representations of words can be considered as elements of an algebra over a field. We relate the framework to existing methods of composing vector-based representations of meaning.
0
0
0