---
language:
- es
license: cc-by-4.0
library_name: span-marker
tags:
- span-marker
- token-classification
- ner
- named-entity-recognition
- generated_from_span_marker_trainer
datasets:
- xtreme
metrics:
- precision
- recall
- f1
widget:
- text: Me llamo Álvaro y vivo en Barcelona (España).
- text: Marie Curie fue profesora en la Universidad de Paris.
- text: La Universidad de Salamanca es la universidad en activo más antigua de España.
pipeline_tag: token-classification
base_model: bert-base-multilingual-cased
model-index:
- name: SpanMarker with bert-base-multilingual-cased on xtreme/PAN-X.es
  results:
  - task:
      type: token-classification
      name: Named Entity Recognition
    dataset:
      name: xtreme/PAN-X.es
      type: xtreme
      split: eval
    metrics:
    - type: f1
      value: 0.9186626746506986
      name: F1
    - type: precision
      value: 0.9231154938993816
      name: Precision
    - type: recall
      value: 0.9142526071842411
      name: Recall
---

# SpanMarker with bert-base-multilingual-cased on xtreme/PAN-X.es

This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model trained on the [xtreme/PAN-X.es](https://huggingface.co/datasets/xtreme) dataset that can be used for Named Entity Recognition. This SpanMarker model uses [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) as the underlying encoder.

## Model Details

### Model Description
- **Model Type:** SpanMarker
- **Encoder:** [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased)
- **Maximum Sequence Length:** 512 tokens
- **Maximum Entity Length:** 8 words
- **Training Dataset:** [xtreme/PAN-X.es](https://huggingface.co/datasets/xtreme)
- **Languages:** es
- **License:** cc-by-4.0

### Model Sources

- **Repository:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER)
- **Thesis:** [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf)

### Model Labels
| Label | Examples                                                                            |
|:------|:------------------------------------------------------------------------------------|
| LOC   | "Salamanca", "Paris", "Barcelona (España)"                                |
| ORG   | "ONU", "Fútbol Club Barcelona", "Museo Nacional del Prado" |
| PER   | "Fray Luis de León", "Leo Messi", "Álvaro Bartolomé"                                  |

## Uses

### Direct Use for Inference

```python
from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("alvarobartt/bert-base-multilingual-cased-ner-spanish")
# Run inference
entities = model.predict("Marie Curie fue profesora en la Universidad de Paris.")
```

<!--
### Out-of-Scope Use

*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->

<!--
## Bias, Risks and Limitations

*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->

<!--
### Recommendations

*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->

## Training Details

### Training Set Metrics

| Training set          | Min | Median | Max |
|:----------------------|:----|:-------|:----|
| Sentence length       | 3   | 6.4642 | 64  |
| Entities per sentence | 1   | 1.2375 | 24  |

### Training Hyperparameters

- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2

### Training Results
| Epoch  | Step | Validation Loss | Validation Precision | Validation Recall | Validation F1 | Validation Accuracy |
|:------:|:----:|:---------------:|:--------------------:|:-----------------:|:-------------:|:-------------------:|
| 0.3998 | 1000 | 0.0388          | 0.8761               | 0.8641            | 0.8701        | 0.9223              |
| 0.7997 | 2000 | 0.0326          | 0.8995               | 0.8740            | 0.8866        | 0.9341              |
| 1.1995 | 3000 | 0.0277          | 0.9076               | 0.9019            | 0.9047        | 0.9424              |
| 1.5994 | 4000 | 0.0261          | 0.9143               | 0.9113            | 0.9128        | 0.9473              |
| 1.9992 | 5000 | 0.0234          | 0.9231               | 0.9143            | 0.9187        | 0.9502              |

### Framework Versions
- Python: 3.10.12
- SpanMarker: 1.3.1.dev
- Transformers: 4.33.3
- PyTorch: 2.0.1+cu118
- Datasets: 2.14.5
- Tokenizers: 0.13.3

## Citation

### BibTeX
```
@software{Aarsen_SpanMarker,
    author = {Aarsen, Tom},
    license = {Apache-2.0},
    title = {{SpanMarker for Named Entity Recognition}},
    url = {https://github.com/tomaarsen/SpanMarkerNER}
}
```

<!--
## Glossary

*Clearly define terms in order to be accessible across audiences.*
-->

<!--
## Model Card Authors

*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->

<!--
## Model Card Contact

*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->