https://github.com/zamgi/lingvo--ner--german
Named-entity recognition in German language using combined of deep neural network and ruled-based approach in C# for .NET
https://github.com/zamgi/lingvo--ner--german
csharp deep-learning german linguistics lingvo machine-learning morphology named-entity-recognition natural-language-processing ner net neural-network nlp nlp-machine-learning
Last synced: 11 months ago
JSON representation
Named-entity recognition in German language using combined of deep neural network and ruled-based approach in C# for .NET
- Host: GitHub
- URL: https://github.com/zamgi/lingvo--ner--german
- Owner: zamgi
- License: bsd-3-clause
- Created: 2023-03-28T18:52:56.000Z (about 3 years ago)
- Default Branch: master
- Last Pushed: 2025-06-04T22:28:07.000Z (about 1 year ago)
- Last Synced: 2025-06-05T03:22:31.693Z (about 1 year ago)
- Topics: csharp, deep-learning, german, linguistics, lingvo, machine-learning, morphology, named-entity-recognition, natural-language-processing, ner, net, neural-network, nlp, nlp-machine-learning
- Language: C#
- Homepage:
- Size: 17.7 MB
- Stars: 5
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://github.com/zamgi/lingvo--NER--German/actions/workflows/dotnet.yml)
# NER
Named-entity recognition in German language using combined of deep neural network and ruled-based approach in C# for .NET
#
Metrics for includes models:
ner_de__em128__e6xm8_[union]:
```
Common-Score: '95.42'
B-PER: F-score = '97.98' Precision = '98.34' Recall = '97.62'
I-PER: F-score = '98.39' Precision = '98.70' Recall = '98.09'
B-LOC: F-score = '95.70' Precision = '95.81' Recall = '95.58'
I-LOC: F-score = '94.55' Precision = '93.61' Recall = '95.50'
B-ORG: F-score = '92.62' Precision = '92.84' Recall = '92.41'
I-ORG: F-score = '93.29' Precision = '93.73' Recall = '92.86'
The number of categories = '6' of '6'
```
ner_de__em128__e6xm8_[union]_(upper):
```
Common-Score: '95.47'
B-PER: F-score = '98.04' Precision = '98.54' Recall = '97.54'
I-PER: F-score = '98.34' Precision = '98.74' Recall = '97.95'
B-LOC: F-score = '95.58' Precision = '95.79' Recall = '95.38'
I-LOC: F-score = '94.99' Precision = '94.96' Recall = '95.01'
B-ORG: F-score = '92.35' Precision = '92.62' Recall = '92.08'
I-ORG: F-score = '93.55' Precision = '94.46' Recall = '92.64'
The number of categories = '6' of '6'
```
#
Included NER UI sample:
