stefan-it's picture
readme: fix base model key name
69283b4
---
license: cc-by-4.0
library_name: span-marker
base_model: gwlms/teams-base-dewiki-v1-discriminator
tags:
- span-marker
- token-classification
- ner
- named-entity-recognition
pipeline_tag: token-classification
widget:
- text: "Jürgen Schmidhuber studierte ab 1983 Informatik und Mathematik an der TU München ."
example_title: "Wikipedia"
datasets:
- gwlms/germeval2014
language:
- de
model-index:
- name: SpanMarker with GWLMS TEAMS on GermEval 2014 NER Dataset by Stefan Schweter (@stefan-it)
results:
- task:
type: token-classification
name: Named Entity Recognition
dataset:
type: gwlms/germeval2014
name: GermEval 2014
split: test
revision: f3647c56803ce67c08ee8d15f4611054c377b226
metrics:
- type: f1
value: 0.8781
name: F1
metrics:
- f1
---
# SpanMarker for GermEval 2014 NER
This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that
was fine-tuned on the [GermEval 2014 NER Dataset](https://sites.google.com/site/germeval2014ner/home).
The GermEval 2014 NER Shared Task builds on a new dataset with German Named Entity annotation with the following
properties: The data was sampled from German Wikipedia and News Corpora as a collection of citations. The dataset
covers over 31,000 sentences corresponding to over 590,000 tokens. The NER annotation uses the NoSta-D guidelines,
which extend the Tübingen Treebank guidelines, using four main NER categories with sub-structure, and annotating
embeddings among NEs such as `[ORG FC Kickers [LOC Darmstadt]]`.
12 classes of Named Entites are annotated and must be recognized: four main classes `PER`son, `LOC`ation, `ORG`anisation,
and `OTH`er and their subclasses by introducing two fine-grained labels: `-deriv` marks derivations from NEs such as
"englisch" (“English”), and `-part` marks compounds including a NE as a subsequence deutschlandweit (“Germany-wide”).
# Fine-Tuning
We use the same hyper-parameters as used in the
["German's Next Language Model"](https://aclanthology.org/2020.coling-main.598/) paper using the
[GWLMS TEAMS](https://huggingface.co/gwlms/teams-base-dewiki-v1-discriminator) model as backbone.
Evaluation is performed with SpanMarkers internal evaluation code that uses `seqeval`.
We fine-tune 5 models and upload the model with best F1-Score on development set. Results on development set are
in brackets:
| Model | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg.
| ----------- | --------------- | --------------- | --------------- | ------------------- | ----------------| ---------------
| GWLMS TEAMS | (88.76) / 87.85 | (88.54) / 87.77 | (88.41) / 87.98 | (**88.86**) / 87.81 | (88.83) / 88.50 | (88.68) / 87.98
The best model achieves a final test score of 87.81%.
Scripts for [training](trainer.py) and [evaluation](evaluator.py) are also available.
# Usage
The fine-tuned model can be used like:
```python
from span_marker import SpanMarkerModel
# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("gwlms/span-marker-teams-germeval14")
# Run inference
entities = model.predict("Jürgen Schmidhuber studierte ab 1983 Informatik und Mathematik an der TU München .")
```