README.md

metadata

license: apache-2.0
library_name: span-marker
tags:
  - span-marker
  - token-classification
  - ner
  - named-entity-recognition
pipeline_tag: token-classification
widget:
  - text: >-
      Amelia Earthart voló su Lockheed Vega 5B monomotor a través del Océano
      Atlántico hasta París .
    example_title: Spanish
  - text: >-
      Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic
      to Paris .
    example_title: English
  - text: >-
      Amelia Earthart a fait voler son monomoteur Lockheed Vega 5B à travers
      l'ocean Atlantique jusqu'à Paris .
    example_title: French
  - text: >-
      Amelia Earthart flog mit ihrer einmotorigen Lockheed Vega 5B über den
      Atlantik nach Paris .
    example_title: German
  - text: >-
      Амелия Эртхарт перелетела на своем одномоторном самолете Lockheed Vega 5B
      через Атлантический океан в Париж .
    example_title: Russian
  - text: >-
      Amelia Earthart vloog met haar één-motorige Lockheed Vega 5B over de
      Atlantische Oceaan naar Parijs .
    example_title: Dutch
  - text: >-
      Amelia Earthart przeleciała swoim jednosilnikowym samolotem Lockheed Vega
      5B przez Ocean Atlantycki do Paryża .
    example_title: Polish
  - text: >-
      Amelia Earthart flaug eins hreyfils Lockheed Vega 5B yfir Atlantshafið til
      Parísar .
    example_title: Icelandic
  - text: >-
      Η Amelia Earthart πέταξε το μονοκινητήριο Lockheed Vega 5B της πέρα ​​από
      τον Ατλαντικό Ωκεανό στο Παρίσι .
    example_title: Greek
model-index:
  - name: SpanMarker w. xlm-roberta-base on MultiNERD by Tom Aarsen
    results:
      - task:
          type: token-classification
          name: Named Entity Recognition
        dataset:
          type: Babelscape/multinerd
          name: MultiNERD
          split: test
          revision: 2814b78e7af4b5a1f1886fe7ad49632de4d9dd25
        metrics:
          - type: f1
            value: 0.91314
            name: F1
          - type: precision
            value: 0.91994
            name: Precision
          - type: recall
            value: 0.90643
            name: Recall
datasets:
  - Babelscape/multinerd
language:
  - multilingual
metrics:
  - f1
  - recall
  - precision

SpanMarker for Named Entity Recognition

This is a SpanMarker model that can be used for Named Entity Recognition. In particular, this SpanMarker model uses xlm-roberta-base as the underlying encoder. See train.py for the training script.

Metrics

Language	F1	Precision	Recall
all	91.31	91.99	90.64
de	93.77	93.56	93.87
en	94.55	94.01	95.10
es	90.82	92.58	89.13
fr	90.90	93.23	88.68
it	93.40	90.23	92.60
nl	92.47	93.61	91.36
pl	91.66	92.51	90.81
pt	91.73	93.29	90.22
ru	92.64	92.37	92.91
zh	82.38	83.23	81.55

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-xlm-roberta-base-multinerd")
# 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.