Detail publikace

Obtaining word embedding from existing classification model

ŠŮSTEK, M. ZBOŘIL, F.

Originální název

Obtaining word embedding from existing classification model

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

ŠŮSTEK, M.; ZBOŘIL, F.

Vydáno

22. 3. 2018

Nakladatel

Springer International Publishing

Místo

Cham

ISBN

978-3-319-76347-7

Kniha

Intelligent Systems Design and Applications

Edice

ISDA 2017 Intelligent Systems Design and Applications

ISSN

2194-5357

Periodikum

Advances in Intelligent Systems and Computing

Ročník

2018

Číslo

736

Stát

Švýcarská konfederace

Strany od

540

Strany do

547

Strany počet

8

URL

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/"
}