Word Embeddings 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%3A43949732" target="_blank" >RIV/49777513:23520/17:43949732 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.26615/978-954-452-049-6_057" target="_blank" >http://dx.doi.org/10.26615/978-954-452-049-6_057</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.26615/978-954-452-049-6_057" target="_blank" >10.26615/978-954-452-049-6_057</a>
Alternative languages
Result language
angličtina
Original language name
Word Embeddings for Multi-label Document Classification
Original language description
In this paper, we analyze and evaluate word embeddings for representation of longer texts in the multi-label document classification scenario. The embeddings are used in three convolutional neural network topologies. The experiments are realized on the Czech ČTK and English Reuters-21578 standard corpora. We compare the results of word2vec static and trainable embeddings with randomly initialized word vectors. We conclude that initialization does not play an important role for classification. However, learning of word vectors is crucial to obtain good results.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20204 - Robotics and automatic control
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
Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
ISBN
978-954-452-048-9
ISSN
1313-8502
e-ISSN
neuvedeno
Number of pages
7
Pages from-to
431-437
Publisher name
INCOMA Ltd.
Place of publication
Shoumen, BULGARIA
Event location
Varna, Bulgaria
Event date
Sep 2, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—