SubGram: Extending Skip-gram Word Representation with Substrings
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F16%3A10335477" target="_blank" >RIV/00216208:11320/16:10335477 - isvavai.cz</a>
Result on the web
<a href="http://link.springer.com/chapter/10.1007/978-3-319-45510-5_21" target="_blank" >http://link.springer.com/chapter/10.1007/978-3-319-45510-5_21</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
SubGram: Extending Skip-gram Word Representation with Substrings
Original language description
Skip-gram (word2vec) is a recent method for creating vector representations of words ("distributed word representations") using a neural network. The representation gained popularity in various areas of natural language processing, because it seems to capture syntactic and semantic information about words without any explicit supervision in this respect. We propose SubGram, a refinement of the Skip-gram model to consider also the word structure during the training process, achieving large gains on the Skip-gram original test set.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/LM2015071" target="_blank" >LM2015071: Language Research Infrastructure in the Czech Republic</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Text, Speech, and Dialogue: 19th International Conference, TSD 2016
ISBN
978-3-319-45509-9
ISSN
0302-9743
e-ISSN
—
Number of pages
8
Pages from-to
182-189
Publisher name
Springer International Publishing
Place of publication
New York, London
Event location
Brno, Czechia
Event date
Sep 12, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—