🚀 DistilCamemBERT-NER
We present DistilCamemBERT-NER, a model based on DistilCamemBERT that has been fine - tuned for Named Entity Recognition (NER) in French. This work is inspired by Jean - Baptiste/camembert-ner, which is built on the CamemBERT model. The issue with CamemBERT - based models is scalability, especially during the production phase. Inference cost can be a significant technological hurdle. To address this, we introduce this model that cuts the inference time in half while maintaining the same power consumption, thanks to DistilCamemBERT.
✨ Features
- Fine - tuned DistilCamemBERT for French NER.
- Reduces inference time by half compared to CamemBERT - based models with the same power consumption.
📦 Installation
No installation steps are provided in the original document, so this section is skipped.
💻 Usage Examples
Basic Usage
from transformers import pipeline
ner = pipeline(
task='ner',
model="cmarkea/distilcamembert-base-ner",
tokenizer="cmarkea/distilcamembert-base-ner",
aggregation_strategy="simple"
)
result = ner(
"Le Crédit Mutuel Arkéa est une banque Française, elle comprend le CMB "
"qui est une banque située en Bretagne et le CMSO qui est une banque "
"qui se situe principalement en Aquitaine. C'est sous la présidence de "
"Louis Lichou, dans les années 1980 que différentes filiales sont créées "
"au sein du CMB et forment les principales filiales du groupe qui "
"existent encore aujourd'hui (Federal Finance, Suravenir, Financo, etc.)."
)
result
[{'entity_group': 'ORG',
'score': 0.9974479,
'word': 'Crédit Mutuel Arkéa',
'start': 3,
'end': 22},
{'entity_group': 'LOC',
'score': 0.9000358,
'word': 'Française',
'start': 38,
'end': 47},
{'entity_group': 'ORG',
'score': 0.9788757,
'word': 'CMB',
'start': 66,
'end': 69},
{'entity_group': 'LOC',
'score': 0.99919766,
'word': 'Bretagne',
'start': 99,
'end': 107},
{'entity_group': 'ORG',
'score': 0.9594884,
'word': 'CMSO',
'start': 114,
'end': 118},
{'entity_group': 'LOC',
'score': 0.99935514,
'word': 'Aquitaine',
'start': 169,
'end': 178},
{'entity_group': 'PER',
'score': 0.99911094,
'word': 'Louis Lichou',
'start': 208,
'end': 220},
{'entity_group': 'ORG',
'score': 0.96226394,
'word': 'CMB',
'start': 291,
'end': 294},
{'entity_group': 'ORG',
'score': 0.9983959,
'word': 'Federal Finance',
'start': 374,
'end': 389},
{'entity_group': 'ORG',
'score': 0.9984454,
'word': 'Suravenir',
'start': 391,
'end': 400},
{'entity_group': 'ORG',
'score': 0.9985084,
'word': 'Financo',
'start': 402,
'end': 409}]
Advanced Usage
from optimum.onnxruntime import ORTModelForTokenClassification
from transformers import AutoTokenizer, pipeline
HUB_MODEL = "cmarkea/distilcamembert-base-nli"
tokenizer = AutoTokenizer.from_pretrained(HUB_MODEL)
model = ORTModelForTokenClassification.from_pretrained(HUB_MODEL)
onnx_qa = pipeline("token-classification", model=model, tokenizer=tokenizer)
quantized_model = ORTModelForTokenClassification.from_pretrained(
HUB_MODEL, file_name="model_quantized.onnx"
)
📚 Documentation
Dataset
The dataset used is wikiner_fr, which contains approximately 170,000 sentences labeled in 5 categories:
- PER: Personality
- LOC: Location
- ORG: Organization
- MISC: Miscellaneous entities (e.g., movie titles, books)
- O: Background (Outside entity)
Evaluation Results
class |
precision (%) |
recall (%) |
f1 (%) |
support (#sub - word) |
global |
98.17 |
98.19 |
98.18 |
378,776 |
PER |
96.78 |
96.87 |
96.82 |
23,754 |
LOC |
94.05 |
93.59 |
93.82 |
27,196 |
ORG |
86.05 |
85.92 |
85.98 |
6,526 |
MISC |
88.78 |
84.69 |
86.69 |
11,891 |
O |
99.26 |
99.47 |
99.37 |
309,409 |
Benchmark
This model's performance is compared to 2 reference models using the f1 score metric. For the mean inference time measurement, an AMD Ryzen 5 4500U @ 2.3GHz with 6 cores was used:
🔧 Technical Details
The model is based on DistilCamemBERT and is fine - tuned for the NER task in French. It addresses the scalability issue of CamemBERT - based models by reducing the inference time by half while maintaining the same power consumption.
📄 License
The model is released under the MIT license.
📖 Citation
@inproceedings{delestre:hal-03674695,
TITLE = {{DistilCamemBERT : une distillation du mod{\`e}le fran{\c c}ais CamemBERT}},
AUTHOR = {Delestre, Cyrile and Amar, Abibatou},
URL = {https://hal.archives-ouvertes.fr/hal-03674695},
BOOKTITLE = {{CAp (Conf{\'e}rence sur l'Apprentissage automatique)}},
ADDRESS = {Vannes, France},
YEAR = {2022},
MONTH = Jul,
KEYWORDS = {NLP ; Transformers ; CamemBERT ; Distillation},
PDF = {https://hal.archives-ouvertes.fr/hal-03674695/file/cap2022.pdf},
HAL_ID = {hal-03674695},
HAL_VERSION = {v1},
}