KoichiYasuoka's picture
initial release
0a15e28
|
raw
history blame
No virus
1.06 kB
metadata
language:
  - de
tags:
  - german
  - token-classification
  - pos
  - dependency-parsing
datasets:
  - universal_dependencies
license: mit
pipeline_tag: token-classification

bert-base-german-upos

Model Description

This is a RoBERTa model pre-trained with UD_German-HDT for POS-tagging and dependency-parsing, derived from bert-base-german-cased. Every word is tagged by UPOS (Universal Part-Of-Speech).

How to Use

from transformers import AutoTokenizer,AutoModelForTokenClassification
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/bert-base-german-upos")
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/bert-base-german-upos")

or

import esupar
nlp=esupar.load("KoichiYasuoka/bert-base-german-upos")

See Also

esupar: Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa models