German NER in Flair (default model)

This is the standard 4-class NER model for German that ships with Flair.

F1-Score: 87,94 (CoNLL-03 German revised)

Predicts 4 tags:

tag meaning
PER person name
LOC location name
ORG organization name
MISC other name

Based on Flair embeddings and LSTM-CRF.


Demo: How to use in Flair

Requires: Flair (pip install flair)

from flair.data import Sentence
from flair.models import SequenceTagger

# load tagger
tagger = SequenceTagger.load("flair/ner-german")

# make example sentence
sentence = Sentence("George Washington ging nach Washington")

# predict NER tags
tagger.predict(sentence)

# print sentence
print(sentence)

# print predicted NER spans
print('The following NER tags are found:')
# iterate over entities and print
for entity in sentence.get_spans('ner'):
    print(entity)

This yields the following output:

Span [1,2]: "George Washington"   [βˆ’ Labels: PER (0.9977)]
Span [5]: "Washington"   [βˆ’ Labels: LOC (0.9895)]

So, the entities "George Washington" (labeled as a person) and "Washington" (labeled as a location) are found in the sentence "George Washington ging nach Washington".


Training: Script to train this model

The following Flair script was used to train this model:

from flair.data import Corpus
from flair.datasets import CONLL_03_GERMAN
from flair.embeddings import WordEmbeddings, StackedEmbeddings, FlairEmbeddings

# 1. get the corpus
corpus: Corpus = CONLL_03_GERMAN()

# 2. what tag do we want to predict?
tag_type = 'ner'

# 3. make the tag dictionary from the corpus
tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)

# 4. initialize each embedding we use
embedding_types = [

    # GloVe embeddings
    WordEmbeddings('de'),

    # contextual string embeddings, forward
    FlairEmbeddings('de-forward'),

    # contextual string embeddings, backward
    FlairEmbeddings('de-backward'),
]

# embedding stack consists of Flair and GloVe embeddings
embeddings = StackedEmbeddings(embeddings=embedding_types)

# 5. initialize sequence tagger
from flair.models import SequenceTagger

tagger = SequenceTagger(hidden_size=256,
                        embeddings=embeddings,
                        tag_dictionary=tag_dictionary,
                        tag_type=tag_type)

# 6. initialize trainer
from flair.trainers import ModelTrainer

trainer = ModelTrainer(tagger, corpus)

# 7. run training
trainer.train('resources/taggers/ner-german',
              train_with_dev=True,
              max_epochs=150)

Cite

Please cite the following paper when using this model.

@inproceedings{akbik2018coling,
  title={Contextual String Embeddings for Sequence Labeling},
  author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
  booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
  pages     = {1638--1649},
  year      = {2018}
}

Issues?

The Flair issue tracker is available here.

Downloads last month
34,691
Inference Examples
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.

Dataset used to train flair/ner-german

Spaces using flair/ner-german 3