README.md

---
language:
- en
tags:
- text-classification
- pytorch
metrics:
- accuracy
- f1-score
extra_gated_prompt: 'Our models are intended for academic use only. If you are not
  affiliated with an academic institution, please provide a rationale for using our
  models.

  If you use our models for your work or research, please cite this paper: Sebők,
  M., Máté, Á., Ring, O., Kovács, V., & Lehoczki, R. (2024). Leveraging Open Large
  Language Models for Multilingual Policy Topic Classification: The Babel Machine
  Approach. Social Science Computer Review, 0(0). https://doi.org/10.1177/08944393241259434'
extra_gated_fields:
  Name: text
  Country: country
  Institution: text
  E-mail: text
  Use case: text
---
# xlm-roberta-large-english-judiciary-cap-v3
## Model description
An `xlm-roberta-large` model fine-tuned on english training data containing judiciary documents labeled with [major topic codes](https://www.comparativeagendas.net/pages/master-codebook) from the [Comparative Agendas Project](https://www.comparativeagendas.net/).

## How to use the model

```python
from transformers import AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
pipe = pipeline(
    model="poltextlab/xlm-roberta-large-english-judiciary-cap-v3",
    task="text-classification",
    tokenizer=tokenizer,
    use_fast=False,
    token="<your_hf_read_only_token>"
)

text = "We will place an immediate 6-month halt on the finance driven closure of beds and wards, and set up an independent audit of needs and facilities."
pipe(text)
```

### Gated access
Due to the gated access, you must pass the `token` parameter when loading the model. In earlier versions of the Transformers package, you may need to use the `use_auth_token` parameter instead.

## Model performance
The model was evaluated on a test set of 1833 examples.<br>
Model accuracy is **0.77**.
| label        |   precision |   recall |   f1-score |   support |
|:-------------|------------:|---------:|-----------:|----------:|
| 0            |        0.46 |     0.35 |       0.4  |        34 |
| 1            |        0.79 |     0.81 |       0.8  |       296 |
| 2            |        0.59 |     0.68 |       0.63 |        34 |
| 3            |        0.67 |     0.67 |       0.67 |         9 |
| 4            |        0.86 |     0.73 |       0.78 |       171 |
| 5            |        0.54 |     0.45 |       0.49 |        29 |
| 6            |        0.76 |     0.65 |       0.7  |        20 |
| 7            |        0.79 |     0.89 |       0.84 |        56 |
| 8            |        0.63 |     0.67 |       0.65 |        33 |
| 9            |        0.67 |     0.81 |       0.73 |        81 |
| 10           |        0.89 |     0.82 |       0.85 |       489 |
| 11           |        0.7  |     0.82 |       0.75 |        28 |
| 12           |        0.67 |     0.67 |       0.67 |         9 |
| 13           |        0.77 |     0.84 |       0.81 |       251 |
| 14           |        0.6  |     0.76 |       0.67 |        37 |
| 15           |        0.79 |     0.62 |       0.7  |        24 |
| 16           |        0.54 |     0.33 |       0.41 |        21 |
| 17           |        0    |     0    |       0    |         7 |
| 18           |        0.6  |     0.7  |       0.65 |       139 |
| 19           |        0.74 |     0.78 |       0.76 |        63 |
| 20           |        0    |     0    |       0    |         2 |
| 21           |        0    |     0    |       0    |         0 |
| macro avg    |        0.59 |     0.59 |       0.59 |      1833 |
| weighted avg |        0.77 |     0.77 |       0.76 |      1833 |

### Fine-tuning procedure
This model was fine-tuned with the following key hyperparameters:

- **Number of Training Epochs**: 10
- **Batch Size**: 8
- **Learning Rate**: 5e-06
- **Early Stopping**: enabled with a patience of 2 epochs

## Inference platform
This model is used by the [CAP Babel Machine](https://babel.poltextlab.com), an open-source and free natural language processing tool, designed to simplify and speed up projects for comparative research.  

## Cooperation
Model performance can be significantly improved by extending our training sets. We appreciate every submission of CAP-coded corpora (of any domain and language) at poltextlab{at}poltextlab{dot}com or by using the [CAP Babel Machine](https://babel.poltextlab.com).

## Reference
Sebők, M., Máté, Á., Ring, O., Kovács, V., & Lehoczki, R. (2024). Leveraging Open Large Language Models for Multilingual Policy Topic Classification: The Babel Machine Approach. Social Science Computer Review, 0(0). https://doi.org/10.1177/08944393241259434

## Debugging and issues
This architecture uses the `sentencepiece` tokenizer. In order to use the model before `transformers==4.27` you need to install it manually.

If you encounter a `RuntimeError` when loading the model using the `from_pretrained()` method, adding `ignore_mismatched_sizes=True` should solve the issue.