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
NuZero - 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 difference between NuZero Token in comparison to GLiNER is 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. Also, NuZero token is trained on the diverse internal dataset tailored for real-life use cases.
Installation & Usage
!pip install gliner
NuZero requires labels to be lower-cased
from gliner import GLiNER
model = GLiNER.from_pretrained("numind/NuZero_span")
# 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}
}