README.md

---
language:
- es
license: apache-2.0
library_name: transformers
base_model: dccuchile/bert-base-spanish-wwm-cased
pipeline_tag: token-classification
tags:
- ner
- token-classification
- spanish
- bert
- emergencies
- ecu-911
datasets:
- custom-ecu911
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: ner_model_bert_base
  results:
  - task:
      type: token-classification
      name: Named Entity Recognition
    dataset:
      name: custom-ecu911
      type: custom
      split: test
    metrics:
    - type: accuracy
      value: 0.9739766081871345
    - type: f1
      name: Macro F1
      value: 0.8898766824816503
    - type: precision
      name: Macro Precision
      value: 0.8801934151701145
    - type: recall
      name: Macro Recall
      value: 0.9001920589792443
---

# NER for Spanish Emergency Reports (ECU-911)

**Author/Maintainer:** Danny Paltin ([@dannyLeo16](https://huggingface.co/dannyLeo16))  
**Task:** Token Classification (NER)  
**Language:** Spanish (es)  
**Finetuned from:** `dccuchile/bert-base-spanish-wwm-cased`  
**Entities (BIO):** `PER` and `LOC` → `["O","B-PER","I-PER","B-LOC","I-LOC"]`

This model is a Spanish BERT fine-tuned to identify **persons** and **locations** in short emergency incident descriptions (ECU-911-style). It was developed for the research project:

> **“Representación del conocimiento para emergencias del ECU-911 mediante PLN, ontologías OWL y reglas SWRL.”**

---

## Model Details
- **Architecture:** BERT (Whole Word Masking, cased)
- **Tokenizer:** `dccuchile/bert-base-spanish-wwm-cased`
- **Max length:** uses base tokenizer `model_max_length` (padding to max length)
- **Libraries:** 🤗 Transformers, 🤗 Datasets, PyTorch
- **Labels:** `O, B-PER, I-PER, B-LOC, I-LOC`

---

## Training Data
- **Source:** Custom Spanish emergency reports (Ecuador, ECU-911-style) with token-level BIO annotations.
- **Size:** **510** texts; **34,232** tokens (avg **67.12** tokens/text).
- **Entity counts (BIO spans):** **PER = 421**, **LOC = 1,643**.
- **Token-level label distribution:** `O=30,132`, `B-LOC=1,643`, `I-LOC=1,617`, `B-PER=421`, `I-PER=419`.
- **Splits:** 80% train / 10% validation / 10% test (split aleatorio durante el entrenamiento).

> **Privacy/Ethics.** Data should be anonymized and free of PII. Do not deploy on personal/live data without consent and compliance with local regulation.

---

## Training Procedure
- **Objective:** Token classification (cross-entropy); continuation subwords ignored with `-100`.
- **Hyperparameters:**
  - `learning_rate = 2e-5`
  - `num_train_epochs = 3`
  - `per_device_train_batch_size = 8`
  - `per_device_eval_batch_size = 8`
  - `weight_decay = 0.01`
  - `evaluation_strategy = "epoch"`, `save_strategy = "epoch"`
  - `load_best_model_at_end = true` *(por `eval_loss`)*
- **Data collator:** `DataCollatorForTokenClassification` (padding a `max_length`)


---

## Evaluation
**Validation (epoch 3):**  
- Accuracy: **0.9480**  
- Macro F1: **0.7998**  
- Macro Precision: **0.7914**  
- Macro Recall: **0.8118**  
- Eval loss: **0.1458**

**Test:**  
- Accuracy: **0.9740**  
- Macro F1: **0.8899**  
- Macro Precision: **0.8802**  
- Macro Recall: **0.9002**  
- Eval loss: **0.0834**

*(Computed with `sklearn.metrics`, excluding `-100` positions.)*

---

## Intended Use
- NER over Spanish emergency/incident text (ECU-911-like).
- Downstream knowledge representation (OWL/SWRL).
- Academic research and prototyping.

### Limitations
- Domain-specific; performance may drop on other domains.
- Only `PER` and `LOC` entities.
- May struggle with colloquialisms, misspellings, or code-switching.

---

## How to use

```python
from transformers import pipeline

ner = pipeline(
    "token-classification",
    model="dannyLeo16/ner_model_bert_base",
    tokenizer="dannyLeo16/ner_model_bert_base",
    aggregation_strategy="simple"
)
text = "Se reporta accidente en la Av. de las Américas con dos personas heridas."
ner(text)