README.md

---
license: apache-2.0
library_name: span-marker
tags:
- span-marker
- token-classification
- ner
- named-entity-recognition
pipeline_tag: token-classification
widget:
  - text: >-
      Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic
      to Paris.
    example_title: Amelia Earhart
  - text: >-
      Leonardo di ser Piero da Vinci painted the Mona Lisa based on Italian noblewoman
      Lisa del Giocondo.
    example_title: Leonardo da Vinci
  - text: >-
      On June 13th, 2014, at 4:44 pm during the 2014 World Cup held in Salvador, Brazil,
      the legendary soccer player, Robin van Persie, representing the Dutch national team,
      scored a remarkable goal in the 44th minute.
    example_title: Robin van Persie
model-index:
  - name: >-
      SpanMarker w. roberta-large on OntoNotes v5.0 by Tom Aarsen
    results:
      - task:
          type: token-classification
          name: Named Entity Recognition
        dataset:
          type: tner/ontonotes5
          name: OntoNotes v5.0
          split: test
          revision: cf9ef57ad260810be1298ba795d83c09a915e959
        metrics:
          - type: f1
            value: 0.9153
            name: F1
          - type: precision
            value: 0.9116
            name: Precision
          - type: recall
            value: 0.9191
            name: Recall
datasets:
  - tner/ontonotes5
language:
  - en
metrics:
  - f1
  - recall
  - precision
---

# SpanMarker for Named Entity Recognition

This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model that can be used for Named Entity Recognition. In particular, this SpanMarker model uses [roberta-large](https://huggingface.co/roberta-large) as the underlying encoder. See [train.py](train.py) for the training script.

## Usage

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

```bash
pip install span_marker
```

You can then run inference with this model like so:

```python
from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-roberta-large-ontonotes5")
# Run inference
entities = model.predict("Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.")
```

### Limitations

**Warning**: This model works best when punctuation is separated from the prior words, so 
```python
# ✅
model.predict("He plays J. Robert Oppenheimer , an American theoretical physicist .")
# ❌
model.predict("He plays J. Robert Oppenheimer, an American theoretical physicist.")

# You can also supply a list of words directly: ✅
model.predict(["He", "plays", "J.", "Robert", "Oppenheimer", ",", "an", "American", "theoretical", "physicist", "."])
```
The same may be beneficial for some languages, such as splitting `"l'ocean Atlantique"` into `"l' ocean Atlantique"`.

See the [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) repository for documentation and additional information on this library.