Show simple item record

 
dc.contributor.author Ljubešić, Nikola
dc.contributor.author Osenova, Petya
dc.contributor.author Simov, Kiril
dc.contributor.author Krsnik, Luka
dc.date.accessioned 2021-02-02T08:07:21Z
dc.date.available 2021-02-02T08:07:21Z
dc.date.issued 2021-02-02
dc.identifier.uri http://hdl.handle.net/11356/1394
dc.description This model for morphosyntactic annotation of standard Bulgarian was built with the CLASSLA-StanfordNLP tool (https://github.com/clarinsi/classla-stanfordnlp) by training on the BulTreeBank training corpus (http://hdl.handle.net/11495/D93F-C6E9-65D9-2) and using the CoNLL2017 word embeddings (http://hdl.handle.net/11234/1-1989). The model produces simultaneously UPOS, FEATS and XPOS (MULTEXT-East) labels. The estimated F1 of the XPOS annotations is ~96.8. The difference to the previous version of the model is that the pre-trained embeddings are limited to 250 thousand entries and adapted to the new code base.
dc.language.iso bul
dc.publisher Jožef Stefan Institute
dc.publisher IICT-BAS
dc.relation.isreferencedby http://dx.doi.org/10.18653/v1/W19-3704
dc.relation.replaces http://hdl.handle.net/11356/1326
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-stanfordnlp
dc.subject part-of-speech tagging
dc.subject language model
dc.title The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Bulgarian 1.1
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
sponsor ARRS (Slovenian Research Agency) P6-0411 Language Resources and Technologies for Slovene nationalFunds
sponsor Ministry of Education and Science Republic of Bulgaria DO01-272/16.12.2019 Bulgarian National Interdisciplinary Research e-Infrastructure for Resources and Technologies CLaDA-BG nationalFunds
files.count 2
files.size 175133875


 Files in this item

 Download all files in item (167.02 MB)
This item is
Publicly Available
and licensed under:
Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Distributed under Creative Commons Attribution Required Share Alike
Icon
Name
BTB.zip
Size
57.87 MB
Format
application/zip
Description
Language model
MD5
d4b08b8233a34658448ccadaa8f27175
 Download file  Preview
 File Preview  
    • BTB-1 B
Icon
Name
BTB.pretrain.pt.zip
Size
109.15 MB
Format
application/zip
Description
Pretrained word embeddings
MD5
9a6ad9c2a01e9129a108c3bc53db86ad
 Download file  Preview
 File Preview  
    • BTB.pretrain.pt-1 B

Show simple item record