German BERT for Legal NER
Use:
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("PaDaS-Lab/gbert-legal-ner", use_auth_token="AUTH_TOKEN")
model = AutoModelForTokenClassification.from_pretrained("PaDaS-Lab/gbert-legal-ner", use_auth_token="AUTH_TOKEN")
ner = pipeline("ner", model=model, tokenizer=tokenizer)
example = "1. Das Bundesarbeitsgericht ist gemäß § 9 Abs. 2 Satz 2 ArbGG iVm. § 201 Abs. 1 Satz 2 GVG für die beabsichtigte Klage gegen den Bund zuständig ."
results = ner(example)
print(results)
Classes:
Abbreviation | Class |
---|---|
PER | Person |
RR | Judge |
AN | Lawyer |
LD | Country |
ST | City |
STR | Street |
LDS | Landscape |
ORG | Organization |
UN | Company |
INN | Institution |
GRT | Court |
MRK | Brand |
GS | Law |
VO | Ordinance |
EUN | European legal norm |
VS | Regulation |
VT | Contract |
RS | Court decision |
LIT | Legal literature |
Please reference our work when using the model.
@conference{icaart23,
author={Harshil Darji. and Jelena Mitrović. and Michael Granitzer.},
title={German BERT Model for Legal Named Entity Recognition},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={723-728},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011749400003393},
isbn={978-989-758-623-1},
issn={2184-433X},
}
- Downloads last month
- 237
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.