Downloads · 30 days
11
28% of all-time downloads
parl-german-ner
schlenker/parl-german-ner
parl-german-ner is a token classification model from schlenker. Use it when you need labels on individual words, such as names. It is set up for transformers.
This model is part of GePaDeU, which equips parliamentary debates of the German Bundestag with rich semantic and pragmatic information across multiple annotation layers.
All-time downloads
40
Public
Parameters
335M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Nov 13, 2025
- Updated
- Nov 13, 2025
- SHA
- 1159c0ad
Base models
Model card
From the Hugging Face model README
Annotation Layer: NER
This model is part of GePaDeU, which equips parliamentary debates of the German Bundestag with rich semantic and pragmatic information across multiple annotation layers.
parl-german-ner is trained on a mix of news headlines and parliamentary speeches to tag a sequence with fine-grained named entities (e.g., geo-political entities, persons, organizations). The NER tag inventory is adapted from the OntoNotes NER inventory.
🔍 Model Overview
- Task Type: Token classification
- Base Model: GBERT large
- Fine-tuning method: full fine-tuning
- Language: German
📚 Dataset
Models were trained and evaluated on a mix of Twitter news headlines data (Ruppenhofer et al., 2020) and 40 manually annotated parliamentary speeches. The latter results in 1,639 annotated entities.
🏋️ Model Training
📊 Evaluation
🚀 How to Use
Please, refer to our GitHub repo for detailed instructions on the required input format and how to run the model.
⚠️ Limitations
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Languages
- de
- Created
- Nov 13, 2025
- Updated
- Nov 13, 2025