PaDaS-Lab/gbert-legal-ner

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},
}