|
--- |
|
license: gpl-3.0 |
|
language: |
|
- es |
|
library_name: spacy |
|
pipeline_tag: token-classification |
|
tags: |
|
- spacy |
|
- token-classification |
|
widget: |
|
- text: "Fue antes de llegar a Sigüeiro, en el Camino de Santiago." |
|
- text: "Si te metes en el Franco desde la Alameda, vas hacia la Catedral." |
|
- text: "Y allí precisamente es Santiago el patrón del pueblo." |
|
model-index: |
|
- name: bne-spacy-corgale-ner-es |
|
results: |
|
- task: |
|
name: NER |
|
type: token-classification |
|
metrics: |
|
- name: NER Precision |
|
type: precision |
|
value: 0.9721311475 |
|
- name: NER Recall |
|
type: recall |
|
value: 0.9732708089 |
|
- name: NER F Score |
|
type: f_score |
|
value: 0.9727006444 |
|
--- |
|
|
|
# Introduction |
|
|
|
spaCy NER model for Spanish trained with interviews in the domain of tourism related to the Way of Saint Jacques. It recognizes four types of entities: location (LOC), organizations (ORG), person (PER) and miscellaneous (MISC). It was fine-tuned using `PlanTL-GOB-ES/roberta-base-bne`. |
|
|
|
| Feature | Description | |
|
| --- | --- | |
|
| **Name** | `bne-spacy-corgale-ner-es` | |
|
| **Version** | `0.0.2` | |
|
| **spaCy** | `>=3.5.2,<3.6.0` | |
|
| **Default Pipeline** | `transformer`, `ner` | |
|
| **Components** | `transformer`, `ner` | |
|
|
|
### Label Scheme |
|
|
|
<details> |
|
|
|
<summary>View label scheme (4 labels for 1 components)</summary> |
|
|
|
| Component | Labels | |
|
| --- | --- | |
|
| **`ner`** | `LOC`, `MISC`, `ORG`, `PER` | |
|
|
|
</details> |
|
|
|
## Usage |
|
|
|
You can use this model with the spaCy *pipeline* for NER. |
|
|
|
```python |
|
import spacy |
|
from spacy.pipeline import merge_entities |
|
|
|
|
|
nlp = spacy.load("bne-spacy-corgale-ner-es") |
|
nlp.add_pipe('sentencizer') |
|
|
|
example = "Fue antes de llegar a Sigüeiro, en el Camino de Santiago. Si te metes en el Franco desde la Alameda, vas hacia la Catedral. Y allí precisamente es Santiago el patrón del pueblo." |
|
ner_pipe = nlp(example) |
|
|
|
print(ner_pipe.ents) |
|
for token in merge_entities(ner_pipe): |
|
print(token.text, token.ent_type_) |
|
``` |
|
|
|
## Dataset |
|
|
|
ToDo |
|
|
|
## Model performance |
|
|
|
entity|precision|recall|f1 |
|
-|-|-|- |
|
LOC|0.985|0.987|0.986 |
|
MISC|0.862|0.865|0.863 |
|
ORG|0.938|0.779|0.851 |
|
PER|0.921|0.941|0.931 |
|
micro avg|0.971|0.972|0.971 |
|
macro avg|0.926|0.893|0.908 |
|
weighted avg|0.971|0.972|0.971 |
