Continuous Distributed Representations of Words as Input of LSTM Network Language Model
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F14%3A43922923" target="_blank" >RIV/49777513:23520/14:43922923 - isvavai.cz</a>
Result on the web
<a href="http://link.springer.com/chapter/10.1007/978-3-319-10816-2_19" target="_blank" >http://link.springer.com/chapter/10.1007/978-3-319-10816-2_19</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-10816-2_19" target="_blank" >10.1007/978-3-319-10816-2_19</a>
Alternative languages
Result language
angličtina
Original language name
Continuous Distributed Representations of Words as Input of LSTM Network Language Model
Original language description
he continuous skip-gram model is an efficient algorithm for learning quality distributed vector representations that are able to capture a large number of syntactic and semantic word relationships. Artificial neural networks have become the state-of-the-art in the task of language modelling whereas Long-Short Term Memory (LSTM) networks seem to be efficient training algorithm. In this paper, we carry out experiments with a combination of these powerful models: the continuous distributed representationsof words are trained with skip-gram method on a big corpora and are used as the input of LSTM language model instead of traditional 1-of-N coding. The possibilities of this approach are shown in experiments on perplexity with Wikipedia and Penn Treebankcorpus.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/DF12P01OVV022" target="_blank" >DF12P01OVV022: ASR- and MT-based Access to a Large Archive of Cultural Heritage (AMALACH)</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2014
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, 17th International Conference, TSD 2014, Brno, Czech Republic, September 8-12, 2014. Proceedings
ISBN
978-3-319-10815-5
ISSN
0302-9743
e-ISSN
—
Number of pages
8
Pages from-to
150-157
Publisher name
Springer
Place of publication
Heidelberg
Event location
Brno, Czech Republic
Event date
Sep 8, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—