Obtaining word embedding from existing classification model
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU127781" target="_blank" >RIV/00216305:26230/18:PU127781 - isvavai.cz</a>
Result on the web
<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11546" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11546</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-76348-4_52" target="_blank" >10.1007/978-3-319-76348-4_52</a>
Alternative languages
Result language
angličtina
Original language name
Obtaining word embedding from existing classification model
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Intelligent Systems Design and Applications
ISBN
978-3-319-76347-7
ISSN
2194-5357
e-ISSN
—
Number of pages
8
Pages from-to
540-547
Publisher name
Springer International Publishing
Place of publication
Cham
Event location
Delhi
Event date
Dec 14, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—