| --- |
| library_name: flair |
| tags: |
| - flair |
| - token-classification |
| - sequence-tagger-model |
| language: de |
| license: other |
| license_name: flukes-nc-1.0 |
| license_link: https://github.com/flairNLP/flukes/blob/main/MODEL_LICENSE.md |
| widget: |
| - text: "Die Deutsche Nationalmannschaft, trainiert von Helmut Schön, gewann in München bei der Weltmeisterschaft 1974 das Endspiel gegen die Niederlande." |
| --- |
| |
|
|
| ## German NER in Flair (8-class) |
|
|
| This is the 8-class NER model for German for [Flair](https://github.com/flairNLP/flair/). |
|
|
| F1-Score: **95.6** |
|
|
| Predicts 8 tags: |
|
|
| | **tag** | **meaning** | |
| |---------------------------------|-----------| |
| | PER | person name | |
| | LOC | location name | |
| | ORG | organization name | |
| | PRODUCT | product name ("Oura Ring 5")| |
| | WORK_OF_ART | film/song/album/book name | |
| | EVENT | named event ("1970 World Cup") | |
| | IDENT | nationality, ethnicity or adherence | |
| | MISC | other name | |
|
|
| > ⚠️ **Default license: noncommercial use only.** This model is released under the |
| > [Flukes NC 1.0 License](https://github.com/flairNLP/flukes/blob/main/MODEL_LICENSE.md). |
| > Commercial use — including using this model's predictions in a commercial |
| > product or service — requires a separate license. Contact |
| > `alan.akbik@gmail.com`. |
| > |
| |
| --- |
|
|
| ### Demo: How to use in Flair |
|
|
| Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`) |
|
|
| ```python |
| from flair.data import Sentence |
| from flair.models import SequenceTagger |
| |
| # load tagger |
| tagger = SequenceTagger.load("flair/entity-german-4class") |
| |
| # make example sentence |
| sentence = Sentence("Die Deutsche Nationalmannschaft, trainiert von Helmut Schön, gewann in München bei der Weltmeisterschaft 1974 das Endspiel gegen die Niederlande.") |
| |
| # 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[1:3]: "Deutsche Nationalmannschaft" → ORG (1.0000) |
| Span[6:8]: "Helmut Schön" → PER (1.0000) |
| Span[11:12]: "München" → LOC (1.0000) |
| Span[14:16]: "Weltmeisterschaft 1974" → EVENT (1.0000) |
| Span[20:21]: "Niederlande" → ORG (1.0000) |
| ``` |
|
|
| So, the entities "*Deutsche Nationalmannschaft*" and "*Niederlande*" are tagged as **organization** (soccer teams), "*Helmut Schön*" is tagged as a **person**, |
| "*Mexico*" as a **location** and "*, together with |
| the entity "*Weltmeisterschaft 1974*", labeled as **event**. |
| |
| --- |
| |
| ### Cite |
| |
| Please cite the following paper when using this model. |
| |
| ``` |
| @inproceedings{akbik2019flair, |
| title={{FLAIR}: An easy-to-use framework for state-of-the-art {NLP}}, |
| author={Akbik, Alan and Bergmann, Tanja and Blythe, Duncan and Rasul, Kashif and Schweter, Stefan and Vollgraf, Roland}, |
| booktitle={{NAACL} 2019, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)}, |
| pages={54--59}, |
| year={2019} |
| } |
| ``` |
| |
| --- |
| |
| ## License |
| |
| **Model weights**: [Flukes Noncommercial License 1.0](https://github.com/flairNLP/flukes/blob/main/MODEL_LICENSE.md). |
| Personal, academic, and other noncommercial use permitted. Commercial use |
| requires a separate license — contact `alan.akbik@gmail.com`. |
