Ensemble of Neural Networks for Multi-label Document Classification
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F17%3A43932759" target="_blank" >RIV/49777513:23520/17:43932759 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Ensemble of Neural Networks for Multi-label Document Classification
Original language description
This paper deals with multi-label document classification using an ensemble of neural networks. The assumption is that different network types can keep complementary information and that the combination of more neural classifiers will bring higher accuracy. We verify this hypothesis by an error analysis of the individual networks. One contribution of this work is thus evaluation of several network combinations that improve performance over one single network. Another contribution is a detailed analysis of the achieved results and a proposition of possible directions of further improvement. We evaluate the approaches on a Czech ČTK corpus and also compare the results with state-of-the-art approaches on the English Reuters-21578 dataset. We show that the ensemble of neural classifiers achieves competitive results using only very simple features.
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/LO1506" target="_blank" >LO1506: Sustainability support of the centre NTIS - New Technologies for the Information Society</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ITAT 2017: Information Technologies—Applications and Theory Proceedings of the 17th conference ITAT 2017
ISBN
978-1-974274-74-1
ISSN
1613-0073
e-ISSN
—
Number of pages
7
Pages from-to
186-192
Publisher name
CreateSpace Independent Publishing Platform, 2017
Place of publication
—
Event location
Martinské hole, Slovakia
Event date
Sep 22, 2017
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—