metadata

language:
  - en
license: apache-2.0
library_name: span-marker
tags:
  - span-marker
  - token-classification
  - ner
  - named-entity-recognition
datasets:
  - conll2003
metrics:
  - f1
  - recall
  - precision
pipeline_tag: token-classification
widget:
  - text: >-
      Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic
      to Paris.
    example_title: Amelia Earhart
base_model: prajjwal1/bert-tiny
model-index:
  - name: SpanMarker w. bert-tiny on CoNLL03 by Tom Aarsen
    results:
      - task:
          type: token-classification
          name: Named Entity Recognition
        dataset:
          name: CoNLL03
          type: conll2003
          split: test
          revision: 01ad4ad271976c5258b9ed9b910469a806ff3288
        metrics:
          - type: f1
            value: 0.8093994778067886
            name: F1
          - type: precision
            value: 0.8546048601184398
            name: Precision
          - type: recall
            value: 0.7687362233651727
            name: Recall

SpanMarker for Named Entity Recognition

This is a SpanMarker model that can be used for Named Entity Recognition. In particular, this SpanMarker model uses prajjwal1/bert-tiny as the underlying encoder.

Note

This model is primarily used for efficient tests on the SpanMarker GitHub repository.

Usage

To use this model for inference, first install the span_marker library:

pip install span_marker

You can then run inference with this model like so:

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-tiny-conll03")
# Run inference
entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")

See the SpanMarker repository for documentation and additional information on this library.