Publication Details

Obtaining word embedding from existing classification model

ŠŮSTEK, M.; ZBOŘIL, F. Obtaining word embedding from existing classification model. In Intelligent Systems Design and Applications. Advances in Intelligent Systems and Computing. ISDA 2017 Intelligent Systems Design and Applications. Cham: Springer International Publishing, 2018. p. 540-547. ISBN: 978-3-319-76347-7. ISSN: 2194-5357.
Czech title
Reprezentace tříd v klasifikačním modelu pomocí word embedding
Type
conference paper
Language
English
Authors
Šůstek Martin, Ing. (DCGM)
Zbořil František, doc. Ing., CSc. (DITS)
Keywords

unsupervised learning, artificial intelligence, word embedding, word2vec, CNN

Abstract

This paper introduces a new technique to inspect relations between classes in classification model. The method is built on the assumption that it is easier to distinguish some classes than others. The harder the distinction is, the more similar the objects are. Simple application demonstrating this approach was implemented and obtained class representations in a vector space are discussed. Created representation can be treated as word embedding where the words are represented by the classes. As an addition, potential usages and characteristics are discussed including a knowledge base.

Published
2018
Pages
540–547
Journal
Advances in Intelligent Systems and Computing, vol. 2018, no. 736, ISSN 2194-5357
Proceedings
Intelligent Systems Design and Applications
Series
ISDA 2017 Intelligent Systems Design and Applications
ISBN
978-3-319-76347-7
Publisher
Springer International Publishing
Place
Cham
DOI
10.1007/978-3-319-76348-4_52
EID Scopus
2-s2.0-85044468383
BibTeX 
@inproceedings{BUT147178,
  author="Martin {Šůstek} and František {Zbořil}",
  title="Obtaining word embedding from existing classification model",
  booktitle="Intelligent Systems Design and Applications",
  year="2018",
  series="ISDA 2017 Intelligent Systems Design and Applications",
  journal="Advances in Intelligent Systems and Computing",
  volume="2018",
  number="736",
  pages="540--547",
  publisher="Springer International Publishing",
  address="Cham",
  doi="10.1007/978-3-319-76348-4\{_}52",
  isbn="978-3-319-76347-7",
  issn="2194-5357",
  url="https://www.fit.vut.cz/research/publication/11546/"
}
Files
Back to top