Semantics in High-Dimensional Space

Geometric models are used for modelling meaning in various semantic-space models. They are seductive in their simplicity and their imaginative qualities, and for that reason, their metaphorical power risks leading our intuitions astray: human intuition works well in a three-dimensional world but is...

Descripción completa

Detalles Bibliográficos
Autores principales: Karlgren, Jussi, Kanerva, Pentti
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Artificial Intelligence
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8439276/
https://www.ncbi.nlm.nih.gov/pubmed/34532704
http://dx.doi.org/10.3389/frai.2021.698809
_version_ 1783752506038288384
author Karlgren, Jussi
Kanerva, Pentti
author_facet Karlgren, Jussi
Kanerva, Pentti
author_sort Karlgren, Jussi
collection PubMed
description Geometric models are used for modelling meaning in various semantic-space models. They are seductive in their simplicity and their imaginative qualities, and for that reason, their metaphorical power risks leading our intuitions astray: human intuition works well in a three-dimensional world but is overwhelmed by higher dimensionalities. This note is intended to warn about some practical pitfalls of using high-dimensional geometric representation as a knowledge representation and a memory model—challenges that can be met by informed design of the representation and its application.
format Online
Article
Text
id pubmed-8439276
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-84392762021-09-15 Semantics in High-Dimensional Space Karlgren, Jussi Kanerva, Pentti Front Artif Intell Artificial Intelligence Geometric models are used for modelling meaning in various semantic-space models. They are seductive in their simplicity and their imaginative qualities, and for that reason, their metaphorical power risks leading our intuitions astray: human intuition works well in a three-dimensional world but is overwhelmed by higher dimensionalities. This note is intended to warn about some practical pitfalls of using high-dimensional geometric representation as a knowledge representation and a memory model—challenges that can be met by informed design of the representation and its application. Frontiers Media S.A. 2021-08-31 /pmc/articles/PMC8439276/ /pubmed/34532704 http://dx.doi.org/10.3389/frai.2021.698809 Text en Copyright © 2021 Karlgren and Kanerva. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Artificial Intelligence
Karlgren, Jussi
Kanerva, Pentti
Semantics in High-Dimensional Space
title Semantics in High-Dimensional Space
title_full Semantics in High-Dimensional Space
title_fullStr Semantics in High-Dimensional Space
title_full_unstemmed Semantics in High-Dimensional Space
title_short Semantics in High-Dimensional Space
title_sort semantics in high-dimensional space
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8439276/
https://www.ncbi.nlm.nih.gov/pubmed/34532704
http://dx.doi.org/10.3389/frai.2021.698809
work_keys_str_mv AT karlgrenjussi semanticsinhighdimensionalspace
AT kanervapentti semanticsinhighdimensionalspace

Ejemplares similares