Prikaži enostavni zapis vnosa

 
dc.contributor.author Terčon, Luka
dc.contributor.author Ljubešić, Nikola
dc.date.accessioned 2023-02-03T16:55:59Z
dc.date.available 2023-02-03T16:55:59Z
dc.date.issued 2023-01-31
dc.identifier.uri http://hdl.handle.net/11356/1769
dc.description This model for UD dependency parsing of standard Slovenian was built with the CLASSLA-Stanza tool (https://github.com/clarinsi/classla) by training on the SUK training corpus (http://hdl.handle.net/11356/1747) and using the CLARIN.SI-embed.sl word embeddings (http://hdl.handle.net/11356/1204) expanded with the MaCoCu-sl Slovene web corpus (http://hdl.handle.net/11356/1517). The estimated LAS of the parser is ~91.11. The difference to the previous version of the model is that the model was trained using the SUK training corpus and uses the updated embeddings.
dc.language.iso slv
dc.publisher Jožef Stefan Institute
dc.relation.isreferencedby https://aclanthology.org/W19-3704/
dc.relation.replaces http://hdl.handle.net/11356/1258
dc.rights Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
dc.rights.uri https://creativecommons.org/licenses/by-sa/4.0/
dc.rights.label PUB
dc.source.uri https://github.com/clarinsi/classla
dc.subject parsing
dc.subject language model
dc.title The CLASSLA-Stanza model for UD dependency parsing of standard Slovenian 2.0
dc.type toolService
metashare.ResourceInfo#ContentInfo.detailedType tool
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent true
has.files yes
branding CLARIN.SI data & tools
contact.person Nikola Ljubešić nikola.ljubesic@ijs.si Jožef Stefan Institute
contact.person Luka Terčon luka.tercon@gmail.com Faculty of Computer and Information Science, University of Ljubljana
sponsor ARRS (Slovenian Research Agency) P6-0411 Language Resources and Technologies for Slovene nationalFunds
sponsor Ministry of Culture C3340-20-278001 Development of Slovene in a Digital Environment Other
files.count 2
files.size 200379389


 Datoteke v tem vnosu

 Prenesi vse datoteke v vnosu (191.1 MB)
Icon
Ime
suk_udsyn.zip
Velikost
86.38 MB
Format
application/zip
Opis
Language model
MD5
5d012af715ee7c6b3e6e2c1a11b261cb
 Prenesi datoteko  Predogled
 Predogled datoteke  
    • suk_udsyn95 MB
Icon
Ime
sl_ssj.pretrain.pt.zip
Velikost
104.71 MB
Format
application/zip
Opis
Pretrained word embeddings
MD5
503d53e78362e1d78d4f6b037d5fe94d
 Prenesi datoteko  Predogled
 Predogled datoteke  
    • sl_ssj.pretrain.pt149 MB

Prikaži enostavni zapis vnosa