aina-translator-ca-es-legal

Aina Project's Catalan to Spanish MT model specialized on the legal domain

Table of Contents

<details> <summary>Click to expand</summary>

• Model description
• Intended uses and limitations
• How to use
• Limitations and bias
• Training
• Evaluation
• Additional information

</details>

Model description

aina-translator-ca-es-legal is a bilingual MT model specialized in the translation of texts from the legal domain. The base model from which it is derived is aina-translator-ca-es.

Intended uses and limitations

The model is intended to be used for the translation of legal, juridical and forensic Catalan texts into Spanish.

How to use

Usage

Required libraries:

pip install ctranslate2 pyonmttok

Translate a sentence using python

import ctranslate2
import pyonmttok
from huggingface_hub import snapshot_download
model_dir = snapshot_download(repo_id="projecte-aina/aina-translator-ca-es-legal", revision="main")

tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = model_dir + "/spm.model")
tokenized=tokenizer.tokenize("Benvingut al traductor legal del projecte Aina!")

translator = ctranslate2.Translator(model_dir)
translated = translator.translate_batch([tokenized[0]])
print(tokenizer.detokenize(translated[0][0]['tokens']))

Limitations and bias

At the time of submission, no measures have been taken to estimate the bias and toxicity embedded in the model. However, we are well aware that our models may be biased. We intend to conduct research in these areas in the future, and if completed, this model card will be updated.

Training

This model is a fine-tuned version of the base model aina-translator-ca-es. Detailed information about the pre-training can be found in the model card of the latter. The fine-tuned model was trained for a further 20 epochs on a domain-specific dataset.

Fine-tuning data

Information about the pre-training data con be found in the model card of aina-translator-ca-es. The fine-tuning corpus consists of 7M ca-es parallel sentences. This corpus was built from legal, juridical and forensic texts provided by various representatives of the Generalitat de Catalunya. The corpus may contain synthetically generated text on the target side (in this case, Spanish). The data was partially extracted from pdf and docx documents, semi-manually cleaned, filtered and aligned to obtain the final corpus.

Evaluation

Variable and metrics

We use the BLEU score for evaluation on various domain-specific testsets:

AAPP Corpus of texts from the Public Administrations of Catalonia

CAJG - Corpus of resolutions of the Comissió d'Assistència Jurídica Gratuïta de Catalunya (CAJG): Internal, domain-specific evaluation set, specifically created for evaluation purposes.

Actas2020 - Corpus of proceedings of the Sala de Govern of the Tribunal Superior de Justicia de Catalunya: Internal, domain-specific evaluation set, specifically created for evaluation purposes.

Evaluation results

Below are the evaluation results expressed in BLEU for machine translation from Catalan to Spanish compared to Google Translate and our generalist model aina-translator-ca-es:

Additional information

Author

The Language Technologies Unit from Barcelona Supercomputing Center.

Contact

For further information, please send an email to [email protected].

Copyright

Copyright(c) 2024 by Language Technologies Unit, Barcelona Supercomputing Center.

License

Apache License, Version 2.0

Funding

This work/research has been promoted and financed by the Government of Catalonia through the Aina project.

Disclaimer

<details> <summary>Click to expand</summary>

The model published in this repository is intended for a generalist purpose and is available to third parties under a permissive Apache License, Version 2.0.

Be aware that the model may have biases and/or any other undesirable distortions.

When third parties deploy or provide systems and/or services to other parties using this model (or any system based on it) or become users of the model, they should note that it is their responsibility to mitigate the risks arising from its use and, in any event, to comply with applicable regulations, including regulations regarding the use of Artificial Intelligence.

In no event shall the owner and creator of the model (Barcelona Supercomputing Center) be liable for any results arising from the use made by third parties.

</details>