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")