dc.contributor.author | Kondratyuk, Dan |
dc.contributor.author | Straka, Milan |
dc.date.accessioned | 2019-08-27T09:15:07Z |
dc.date.available | 2019-08-27T09:15:07Z |
dc.date.issued | 2019-08-26 |
dc.identifier.uri | http://hdl.handle.net/11234/1-3042 |
dc.description | Pretrained model weights for the UDify model, and extracted BERT weights in pytorch-transformers format. Note that these weights slightly differ from those used in the paper. |
dc.language.iso | grc |
dc.language.iso | ara |
dc.language.iso | eus |
dc.language.iso | bul |
dc.language.iso | hrv |
dc.language.iso | ces |
dc.language.iso | dan |
dc.language.iso | nld |
dc.language.iso | eng |
dc.language.iso | est |
dc.language.iso | fin |
dc.language.iso | fra |
dc.language.iso | deu |
dc.language.iso | got |
dc.language.iso | ell |
dc.language.iso | heb |
dc.language.iso | hin |
dc.language.iso | hun |
dc.language.iso | ind |
dc.language.iso | gle |
dc.language.iso | ita |
dc.language.iso | jpn |
dc.language.iso | lat |
dc.language.iso | nor |
dc.language.iso | chu |
dc.language.iso | fas |
dc.language.iso | pol |
dc.language.iso | por |
dc.language.iso | ron |
dc.language.iso | slv |
dc.language.iso | spa |
dc.language.iso | swe |
dc.language.iso | tam |
dc.language.iso | cat |
dc.language.iso | zho |
dc.language.iso | glg |
dc.language.iso | kaz |
dc.language.iso | lav |
dc.language.iso | rus |
dc.language.iso | tur |
dc.language.iso | cop |
dc.language.iso | san |
dc.language.iso | slk |
dc.language.iso | ukr |
dc.language.iso | uig |
dc.language.iso | vie |
dc.language.iso | bel |
dc.language.iso | kor |
dc.language.iso | lit |
dc.language.iso | urd |
dc.language.iso | bxr |
dc.language.iso | kmr |
dc.language.iso | sme |
dc.language.iso | hsb |
dc.language.iso | afr |
dc.language.iso | yue |
dc.language.iso | mar |
dc.language.iso | srp |
dc.language.iso | swl |
dc.language.iso | tel |
dc.language.iso | amh |
dc.language.iso | hye |
dc.language.iso | bre |
dc.language.iso | fao |
dc.language.iso | kpv |
dc.language.iso | pcm |
dc.language.iso | fro |
dc.language.iso | tgl |
dc.language.iso | tha |
dc.language.iso | wbp |
dc.language.iso | yor |
dc.language.iso | akk |
dc.language.iso | bam |
dc.language.iso | myv |
dc.language.iso | mlt |
dc.publisher | Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL) |
dc.relation.isreferencedby | https://arxiv.org/abs/1904.02099 |
dc.rights | Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) |
dc.rights.uri | http://creativecommons.org/licenses/by-sa/4.0/ |
dc.source.uri | https://github.com/Hyperparticle/udify |
dc.subject | syntax |
dc.subject | dependency parser |
dc.subject | universal dependencies |
dc.title | UDify Pretrained Model |
dc.type | toolService |
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent | true |
metashare.ResourceInfo#ContentInfo.detailedType | tool |
dc.rights.label | PUB |
has.files | yes |
branding | LINDAT / CLARIAH-CZ |
contact.person | Dan Kondratyuk dankondratyuk@u.boisestate.edu Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL) |
contact.person | Milan Straka straka@ufal.mff.cuni.cz Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL) |
sponsor | Education, Audiovisual and Culture Executive Agency EMJMD Erasmus Mundus, Language and Communication Technologies euFunds |
sponsor | Ministerstvo školství, mládeže a tělovýchovy České republiky LM2015071 LINDAT/CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat nationalFunds |
files.size | 1456088999 |
files.count | 2 |
Files in this item
This item is
Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Publicly Available
and licensed under:Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
- Name
- udify-model.tar.gz
- Size
- 759.07 MB
- Format
- application/x-gzip
- Description
- The UDify model weights
- MD5
- 42aacc00e0ed6272b31ca7329055c108
- vocabulary
- upos.txt79 B
- xpos.txt245 kB
- non_padded_namespaces.txt37 B
- head_tags.txt2 kB
- lemmas.txt2 MB
- tokens.txt18 MB
- token_characters.txt32 kB
- feats.txt1 MB
- config.json5 kB
- weights.th809 MB
- Name
- udify-bert.tar.gz
- Size
- 629.56 MB
- Format
- application/x-gzip
- Description
- The BERT weights extracted from the UDify model
- MD5
- facd2798e9786636ced131804ac67398