Deep Neural Networks for Czech Multi-label Document Classification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F18%3A43952035" target="_blank" >RIV/49777513:23520/18:43952035 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-75487-1_36" target="_blank" >http://dx.doi.org/10.1007/978-3-319-75487-1_36</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-75487-1_36" target="_blank" >10.1007/978-3-319-75487-1_36</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep Neural Networks for Czech Multi-label Document Classification

Popis výsledku v původním jazyce

This paper is focused on automatic multi-label document classification of Czech text documents. The current approaches usually use some preprocessing which can have negative impact. Therefore, we would like to omit it and use deep neural networks that learn from simple features. This choice was motivated by their successful usage in many other machine learning fields. Two different networks are compared: the first one is a standard multi-layer perceptron, while the second one is a popular convolutional network. The experiments on a Czech newspaper corpus show that both networks significantly outperform baseline method which uses a rich set of features with maximum entropy classifier. We have also shown that convolutional network gives the best results.

Název v anglickém jazyce

Deep Neural Networks for Czech Multi-label Document Classification

Popis výsledku anglicky

This paper is focused on automatic multi-label document classification of Czech text documents. The current approaches usually use some preprocessing which can have negative impact. Therefore, we would like to omit it and use deep neural networks that learn from simple features. This choice was motivated by their successful usage in many other machine learning fields. Two different networks are compared: the first one is a standard multi-layer perceptron, while the second one is a popular convolutional network. The experiments on a Czech newspaper corpus show that both networks significantly outperform baseline method which uses a rich set of features with maximum entropy classifier. We have also shown that convolutional network gives the best results.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LO1506" target="_blank" >LO1506: Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnost</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computational Linguistics and Intelligent Text Processing

ISBN

978-3-319-75486-4

ISSN

0302-9743

e-ISSN

neuvedeno

Počet stran výsledku

12

Strana od-do

460-471

Název nakladatele

Springer International Publishing AG,

Místo vydání

Switzerland, Cham

Místo konání akce

Konya, Turkey

Datum konání akce

3. 4. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—