Conference paper

ŠŮSTEK Martin and ZBOŘIL František V.. Obtaining word embedding from existing classification model. In: Intelligent Systems Design and Applications. Cham: Springer International Publishing, 2018, pp. 540-547. ISBN 978-3-319-76347-7. ISSN 2194-5357.
Publication language:english
Original title:Obtaining word embedding from existing classification model
Title (cs):Reprezentace tříd v klasifikačním modelu pomocí word embedding
Proceedings:Intelligent Systems Design and Applications
Conference:17th International Conference on Intelligent Systems Design and Applications
Series:ISDA 2017 Intelligent Systems Design and Applications
Place:Cham, CH
Journal:Advances in Intelligent Systems and Computing, Vol. 2018, No. 736, CZ
Publisher:Springer International Publishing
unsupervised learning, artificial intelligence, word embedding, word2vec, CNN
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.
   author = {Martin {\v{S}}{\r{u}}stek and V. Franti{\v{s}}ek
   title = {Obtaining word embedding from existing
	classification model},
   pages = {540--547},
   booktitle = {Intelligent Systems Design and Applications},
   series = {ISDA 2017 Intelligent Systems Design and Applications},
   journal = {Advances in Intelligent Systems and Computing},
   volume = 2018,
 number = 736,
   year = 2018,
   location = {Cham, CH},
   publisher = {Springer International Publishing},
   ISBN = {978-3-319-76347-7},
   ISSN = {2194-5357},
   doi = {10.1007/978-3-319-76348-4_52},
   language = {english},
   url = {}

Your IPv4 address: