UDify Pretrained Model

 
LINDAT / CLARIAH-CZ
  Authors
Kondratyuk, Dan and Straka, Milan
  Item identifier
http://hdl.handle.net/11234/1-3042
 Project URL
https://github.com/Hyperparticle/udify
 Referenced by
https://arxiv.org/abs/1904.02099
 Date issued
2019-08-26
 Type
toolService
 Language(s)
Afrikaans , Akkadian , Amharic , AncientGreek (to 1453) , Arabic , Armenian , Bambara , Basque , Belarusian , Breton , Bulgarian , Catalan , Chinese , ChurchSlavic , Coptic , Croatian , Czech , Danish , Dutch , English , Erzya , Estonian , Faroese , Finnish , French , Galician , German , Gothic , Hebrew , Hindi , Hungarian , Indonesian , Irish , Italian , Japanese , Kazakh , Komi-Zyrian , Korean , Latin , Latvian , Lithuanian , Maltese , Marathi , Modern Greek (1453-) , Nigerian Pidgin , NorthernKurdish , Northern Sami , Norwegian , OldFrench (842-ca. 1400) , Persian , Polish , Portuguese , Romanian , Russia Buriat , Russian , Sanskrit , Serbian , Slovak , Slovenian , Spanish , Swedish , SwedishSign Language , Tagalog , Tamil , Telugu , Thai , Turkish , Uighur , Ukrainian , UpperSorbian , Urdu , Vietnamese , Warlpiri , Yoruba , YueChinese
 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.
 Publisher
Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
 Acknowledgement

Education, Audiovisual and Culture Executive Agency

Project code: EMJMD

Project name: Erasmus Mundus, Language and Communication Technologies

 

Ministerstvo školství, mládeže a tělovýchovy České republiky

Project code: LM2015071

Project name: LINDAT/CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat

 Subject(s)
syntax dependency parser universal dependencies
 Collection(s)
LINDAT / CLARIAH-CZ Data & Tools
Show full item record
 

 Files in this item

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
udify-model.tar.gz
Size
759.07 MB
Format
application/x-gzip
Description
The UDify model weights
MD5
42aacc00e0ed6272b31ca7329055c108
 Download file  Preview
 File Preview  
  • 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
Icon
Name
udify-bert.tar.gz
Size
629.56 MB
Format
application/x-gzip
Description
The BERT weights extracted from the UDify model
MD5
facd2798e9786636ced131804ac67398
 Download file  Preview
 File Preview  
    • pytorch_model.bin678 MB
    • bert_config.json521 B