metadata
language: fr
datasets:
- nlpso/m0_fine_tuning_ocr_cmbert_io
tag: token-classification
widget:
- text: "Duflot, loueur de carrosses, r. de Paradis-\P 505\P Poissonnière, 22."
example_title: 'Noisy entry #1'
- text: "Duſour el Besnard, march, de bois à bruler,\P quai de la Tournelle, 17. etr. des Fossés-\P SBernard. 11.\P Dí"
example_title: 'Noisy entry #2'
- text: "Dufour (Charles), épicier, r. St-Denis\P ☞\P 332"
example_title: 'Ground-truth entry #1'
m0_flat_ner_ocr_cmbert_io
Introduction
This model is a fine-tuned verion from Jean-Baptiste/camembert-ner for nested NER task on a nested NER Paris trade directories dataset.
Dataset
| Abbreviation | Description |
|---|---|
| O | Outside of a named entity |
| PER | Person or company name |
| ACT | Person or company professional activity |
| TITRE | Distinction |
| LOC | Street name |
| CARDINAL | Street number |
| FT | Geographical feature |
Experiment parameter
- Pretrained-model : Jean-Baptiste/camembert-ner
- Dataset : noisy (Pero OCR)
- Tagging format : IO
- Recognised entities : All (flat entities)
Load model from the HuggingFace
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("nlpso/m0_flat_ner_ocr_cmbert_io")
model = AutoModelForTokenClassification.from_pretrained("nlpso/m0_flat_ner_ocr_cmbert_io")