Modelpublic

nlpso/m1_ind_layers_ocr_cmbert_io_level_2

sourceHugging Faceupdated 4y agoView on Hugging Face

0likes14downloads

Model Card

m1indlayersocrcmbertiolevel_2

Introduction

This model is a model that was fine-tuned from Jean-Baptiste/camembert-ner for nested NER task on a nested NER Paris trade directories dataset.

Dataset

Abbreviation	Entity group (level)	Description
O	1 & 2	Outside of a named entity
PER	1	Person or company name
ACT	1 & 2	Person or company professional activity
TITREH	2	Military or civil distinction
DESC	1	Entry full description
TITREP	2	Professionnal reward
SPAT	1	Address
LOC	2	Street name
CARDINAL	2	Street number
FT	2	Geographical feature

Experiment parameter

—Pretrained-model : Jean-Baptiste/camembert-ner
—Dataset : noisy (Pero OCR)
—Tagging format : IO
—Recognised entities : level 2

Load model from the Hugging Face

Warning 1 : this model only recognises level-2 entities of dataset. It has to be used with m1_ind_layers_ocr_cmbert_io_level_1 to recognise nested entities level-1.

python

from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("nlpso/m1_ind_layers_ocr_cmbert_io_level_2")
model = AutoModelForTokenClassification.from_pretrained("nlpso/m1_ind_layers_ocr_cmbert_io_level_2")