Zobrazit minimální záznam

 
dc.contributor.author Vysušilová, Petra
dc.contributor.author Straka, Milan
dc.date.accessioned 2021-11-18T15:58:05Z
dc.date.available 2021-11-18T15:58:05Z
dc.date.issued 2021
dc.identifier.uri http://hdl.handle.net/11234/1-4613
dc.description Model trained for Czech POS Tagging and Lemmatization using Czech version of BERT model, RobeCzech. Model is trained on data from Prague Dependency Treebank 3.5. Model is a part of Czech NLP with Contextualized Embeddings master thesis and presented a state-of-the-art performance on the date of submission of the work. Demo jupyter notebook is available on the project GitHub.
dc.language.iso ces
dc.publisher Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
dc.relation.isreferencedby https://dspace.cuni.cz/handle/20.500.11956/147648
dc.rights Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/4.0/
dc.subject BERT
dc.subject PoS tagging
dc.subject lemmatization
dc.title POS Tagging and Lemmatization (Czech model)
dc.type languageDescription
metashare.ResourceInfo#ContentInfo.mediaType text
metashare.ResourceInfo#ContentInfo.detailedType mlmodel
dc.rights.label PUB
has.files yes
branding LINDAT / CLARIAH-CZ
demo.uri https://github.com/flower-go/DiplomaThesis
contact.person Petra Vysušilová vysusilova@ktiml.mff.cuni.cz Charles University, Faculty of Mathematics and Physics
files.size 1823072785
files.count 4


 Soubory tohoto záznamu

Icon
Název
ch18.index
Velikost
16.79 KB
Formát
Neznámý
Popis
TensorFlow checkpoint data index
MD5
99a09ee9ba3531fdba323db57a4554c8
 Stáhnout soubor
Icon
Název
mappings.pickle
Velikost
40.81 MB
Formát
Neznámý
Popis
Mappings
MD5
363f9a3b8d82610fcb99773c2eb5e856
 Stáhnout soubor
Icon
Název
ch18.data-00000-of-00001
Velikost
847.49 MB
Formát
Neznámý
Popis
TensorFlow checkpoint data
MD5
273672b0bb2f180a6ad6e223f696d58d
 Stáhnout soubor
Icon
Název
forms.vectors-w5-d300-ns5.16b.npz
Velikost
850.3 MB
Formát
Neznámý
Popis
Pretrained embeddings needed for the model construction
MD5
1691478ca44620a734dff58c8bd6b7fd
 Stáhnout soubor

Zobrazit minimální záznam