[ Skip to the content ]

Institute of Formal and Applied Linguistics

at Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic


[ Back to the navigation ]

Publication


Year 2016
Type in proceedings
Status published
Language English
Author(s) Kocmi, Tom Bojar, Ondřej
Date 15.9.2016
Title SubGram: Extending Skip-gram Word Representation with Substrings
Czech title SubGram: Rozšíření Skip-gramové slovní reprezentace o podřetězce
Proceedings 2016: Cham / Heidelberg / New York / Dordrecht / London: TSD 2016: Text, Speech, and Dialogue: 19th International Conference, TSD 2016
Pages range 182-189
How published print
URL http://link.springer.com/chapter/10.1007/978-3-319-45510-5_21
Supported by 2015-2018 H2020-ICT-2014-1-645452 (QT21: Quality Translation 21) 2016 SVV 260 333 (Teoretické základy informatiky a výpočetní lingvistiky) 2016-2019 LM2015071 (LINDAT-CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat) 2016-2018 GAUK 8502/2016 (Využití umělých neuronových sítí pro počítačový překlad) 2012-2016 PRVOUK P46 (Informatika)
Czech abstract Představujeme SubGram, rozšíření Skip-gram modelu, které používá podřetězce slov během trénování reprezentace slov.
English abstract 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.
Specialization linguistics ("jazykověda")
Confidentiality default – not confidential
Open access no
Editor(s)* Petr Sojka; Aleš Horák; Ivan Kopeček; Karel Pala
ISBN* 978-3-319-45509-9
ISSN* 0302-9743
Address* Cham / Heidelberg / New York / Dordrecht / London
Month* September
Venue* Hotel Continental
Publisher* Springer International Publishing
Institution* Masaryk University
Journal* Lecture Notes in Computer Science
Creator: Common Account
Created: 9/6/16 4:00 PM
Modifier: Almighty Admin
Modified: 2/25/17 10:07 PM
***

Content, Design & Functionality: ÚFAL, 2006–2016. Page generated: Thu Nov 23 08:39:21 CET 2017

[ Back to the navigation ] [ Back to the content ]

100% OpenAIRE compliant