Multilingual BERT finetunned on an artificially annotated multilingual subset of Oscar dataset. This model provides domain & language independent embedding for Entity Recognition Task. We fine-tunned it only on 9 languages but the model can generalize over other languages that are supported by the Multilingual BERT.

Metrics:

Read more about evaluation protocol & datasets in our blog post

Model	F1 macro
bert-base-multilingual-cased	0.5206
ours	0.5892
ours + two emb	0.6231

Usage

Embeddings can be used out of the box or fine-tuned on specific datasets.

Get embeddings:

python

import torch
import transformers


model = transformers.AutoModel.from_pretrained(
    'numind/NuNER-multilingual-v0.1',
    output_hidden_states=True,
)
tokenizer = transformers.AutoTokenizer.from_pretrained(
    'numind/NuNER-multilingual-v0.1',
)

text = [
    "NuMind is an AI company based in Paris and USA.",
    "NuMind est une entreprise d'IA basée à Paris et aux États-Unis.",
    "See other models from us on https://huggingface.co/numind"
]
encoded_input = tokenizer(
    text,
    return_tensors='pt',
    padding=True,
    truncation=True
)
output = model(**encoded_input)

# two emb trick: for better quality
emb = torch.cat(
    (output.hidden_states[-1], output.hidden_states[-7]),
    dim=2
)

# single emb: for better speed
# emb = output.hidden_states[-1]

Citation

@misc{bogdanov2024nuner,
      title={NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data}, 
      author={Sergei Bogdanov and Alexandre Constantin and Timothée Bernard and Benoit Crabbé and Etienne Bernard},
      year={2024},
      eprint={2402.15343},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}