README.md

---
library_name: transformers
license: cc-by-sa-4.0
base_model: bert-base-uncased
datasets:
- giovannip/eu-delegation-constraints-annotations
language:
- en
tags:
- legal
- european-union
- delegation
- constraints
- multilabel-classification
metrics:
- precision
- recall
- f1
- matthews_correlation
pipeline_tag: text-classification
---

# Model card for eu-delegation-constraints-bert


This model is a fine-tuned version of **[`bert-base-uncased`](https://huggingface.co/bert-base-uncased)** trained on the  
[`giovannip/eu-delegation-constraints-annotations`](https://huggingface.co/datasets/giovannip/eu-delegation-constraints-annotations) dataset.  
It detects *delegating*, *constraining*, and *soft obligation* provisions in sentences from **EU secondary legislation** (directives and regulations, 1958–2019).

The model is part of the benchmark suite introduced in  
> Franchino, F., Migliorati, M., Pagano, G., & Vignoli, V. (2025).  
> *Identifying Delegation and Constraints in Legislative Texts: A Computational Method Applied to the European Union.*  
> *European Union Politics.*

---


## How to use the model

### Simple text-classification pipeline

```python
from transformers import pipeline

# Load the fine-tuned model
classifier = pipeline(
    "text-classification",
    model="giovannip/eu-delegation-constraints-bert",
    tokenizer="giovannip/eu-delegation-constraints-bert",
    return_all_scores=True,
    function_to_apply="sigmoid"  
)

# Example: 
sentence = "The Commission shall adopt implementing acts to lay down the detailed arrangements for achieving the objectives referred to in paragraph 1."

preds = classifier(sentence)[0]

# Display results (sorted by score)
for p in sorted(preds, key=lambda x: x['score'], reverse=True):
    print(f"{p['label']:10s} | {p['score']:.3f}")
```

### Explicit code


```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "giovannip/eu-delegation-constraints-bert"

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

# Ensure multi-label mode
model.config.problem_type = "multi_label_classification"

# Example
text = "Member States shall adopt measures necessary to ensure compliance with this Directive."

# Tokenize and run inference
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
with torch.no_grad():
    logits = model(**inputs).logits
probs = torch.sigmoid(logits).squeeze().tolist()

labels = list(model.config.id2label.values())
results = sorted(zip(labels, probs), key=lambda x: x[1], reverse=True)

print("\nIndependent multi-label predictions:")
for label, score in results:
    print(f"{label:10s} | {score:.3f}")


```

---

## Model description

- **Architecture:** BERT-base, uncased.  
- **Task:** Multi-label sentence classification  
- **Labels (14):** delegation, constraint, and soft-obligation categories for four actors (Member States, NCAs, Commission, Agencies) plus agenda-setting powers  
- **Objective:** Binary cross-entropy with logits (BCEWithLogitsLoss)  
- **Training:** Fine-tuned for 5 epochs on the full annotated corpus after 5-fold cross-validation benchmarking

---

## Cross-validation performance (mean across 5 folds, 13 labels)

| Metric | Mean (%) |
|:--------|---------:|
| **Precision** | 87.7 |
| **Recall** | 87.9 |
| **F1-score** | 87.6 |
| **Matthews Corr. Coef. (MCC)** | 86.8 |

---

## Intended uses

- Research on delegation and constraints in EU law  
- Legal-text classification models  

---

## 🧩 Training and evaluation setup

- **Training data:** 3 000 expert-annotated sentences  
- **Evaluation:** 5-fold cross-validation  
- **Optimizer:** AdamW (`lr=2e-5`)  
- **Batch size:** 8  
- **Epochs:** 5  
- **Seed:** 42  

---

## Framework versions

- Transformers 4.46.2  
- PyTorch 2.8.0 + CUDA 12.6  
- Datasets 4.4.1  
- Tokenizers 0.20.3  

---

## Citation

**APA**

Franchino, F., Migliorati, M., Pagano, G., & Vignoli, V. (2025).  
*Identifying Delegation and Constraints in Legislative Texts: A Computational Method Applied to the European Union.*  
*European Union Politics.*

**BibTeX**

```bibtex
@article{franchino2025delegation,
  title={Identifying Delegation and Constraints in Legislative Texts: A Computational Method Applied to the European Union},
  author={Franchino, Fabio and Migliorati, Marta and Pagano, Giovanni and Vignoli, Valerio},
  journal={European Union Politics},
  year={2025}
}