High-Dimensional Vector Semantics
Computation and Language
2018-02-28 v1 Artificial Intelligence
Machine Learning
Machine Learning
Abstract
In this paper we explore the "vector semantics" problem from the perspective of "almost orthogonal" property of high-dimensional random vectors. We show that this intriguing property can be used to "memorize" random vectors by simply adding them, and we provide an efficient probabilistic solution to the set membership problem. Also, we discuss several applications to word context vector embeddings, document sentences similarity, and spam filtering.
Keywords
Cite
@article{arxiv.1802.09914,
title = {High-Dimensional Vector Semantics},
author = {M. Andrecut},
journal= {arXiv preprint arXiv:1802.09914},
year = {2018}
}
Comments
12 pages, 5 figures, Int. J. Mod. Phys. C, 2018