NuNER_Zero / README.md
Serega6678's picture
Update README.md
e59884a verified
|
raw
history blame
2.22 kB
metadata
license: mit
datasets:
  - numind/NuNER
library_name: gliner
language:
  - en
pipeline_tag: token-classification
tags:
  - entity recognition
  - NER
  - named entity recognition
  - zero shot
  - zero-shot

NuNerZero - is the family of Zero-Shot Entity Recognition models inspired by GLiNER and built with insights we gathered throughout our work on NuNER.

The key differences between NuNerZero Long in comparison to GLiNER are:

  • The possibility to detect entities that are longer than 12 tokens, as NuZero Token operates on the token level rather than on the span level.
  • a more powerful version of GLiNER-large-v2.1, surpassing it by +3.1% on average
  • NuNerZero family is trained on the diverse dataset tailored for real-life use cases - NuNER v2.0 dataset

Installation & Usage

!pip install gliner

NuZero requires labels to be lower-cased

from gliner import GLiNER

model = GLiNER.from_pretrained("numind/NuNerZero")

# NuZero requires labels to be lower-cased!
labels = ["person", "award", "date", "competitions", "teams"]
labels [l.lower() for l in labels]

text = """

"""

entities = model.predict_entities(text, labels)

for entity in entities:
    print(entity["text"], "=>", entity["label"])

Fine-tuning

Citation

This work

@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}
}

Previous work

@misc{zaratiana2023gliner,
      title={GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer}, 
      author={Urchade Zaratiana and Nadi Tomeh and Pierre Holat and Thierry Charnois},
      year={2023},
      eprint={2311.08526},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}