Hugging Face's logo

clarin-pl
/
FastPDN-distiluse

Token Classification
Transformers
PyTorch
Safetensors
Polish
distilbert
ner
Inference Endpoints
Model card Files Community
1
FastPDN-distiluse / README.md
NorbertRop's picture
NorbertRop
Upload README.md with huggingface_hub
7099e73
preview code
|
raw
history blame
2.57 kB
metadata
language: pl
license: cc-by-4.0
tags:
  - ner
datasets:
  - clarin-pl/kpwr-ner
metrics:
  - f1
  - accuracy
  - precision
  - recall
widget:
  - text: Nazywam się Jan Kowalski i mieszkam we Wrocławiu.
    example_title: Example

FastPDN

FastPolDeepNer is model for Named Entity Recognition, designed for easy use, training and configuration. The forerunner of this project is PolDeepNer2. The model implements a pipeline consisting of data processing and training using: hydra, pytorch, pytorch-lightning, transformers.

Source code: https://gitlab.clarin-pl.eu/grupa-wieszcz/ner/fast-pdn

How to use

Here is how to use this model to get Named Entities in text:

from transformers import pipeline
ner = pipeline('ner', model='clarin-pl/FastPDN', aggregation_strategy='simple')

text = "Nazywam się Jan Kowalski i mieszkam we Wrocławiu."
ner_results = ner(text)
for output in ner_results:
    print(output)

{'entity_group': 'nam_liv_person', 'score': 0.9996054, 'word': 'Jan Kowalski', 'start': 12, 'end': 24}
{'entity_group': 'nam_loc_gpe_city', 'score': 0.998931, 'word': 'Wrocławiu', 'start': 39, 'end': 48}

Here is how to use this model to get the logits for every token in text:

from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("clarin-pl/FastPDN")
model = AutoModelForTokenClassification.from_pretrained("clarin-pl/FastPDN")

text = "Nazywam się Jan Kowalski i mieszkam we Wrocławiu."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)

Training data

The FastPDN model was trained on datasets (with 82 class versions) of kpwr and cen. Annotation guidelines are specified here.

Pretraining

FastPDN models have been fine-tuned, thanks to pretrained models:

Evaluation

Runs trained on cen_n82 and kpwr_n82:

name test/f1 test/pdn2_f1 test/acc test/precision test/recall
distiluse 0.53 0.61 0.95 0.55 0.54
herbert 0.68 0.78 0.97 0.7 0.69

Authors

  • Grupa Wieszcze CLARIN-PL
  • Wiktor Walentynowicz

Contact