Downloads · 30 days
5
9% of all-time downloads
drelhaj/marian-finetuned-mcwc-es-to-ar
marian-finetuned-mcwc-es-to-ar is a machine learning model from drelhaj. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-ar, adapted using high-quality sentence-aligned constitutional text from the Multilingual Corpus of World’s Constitutions (MCWC) 📄 MCWC paper (OSACT 2024)…
Downloads · 30 days
5
9% of all-time downloads
All-time downloads
57
Public
Repo size
309 MB
Likes
0
Public
Click a slice to open those files.
.h5307 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-ar, adapted using high-quality sentence-aligned constitutional text from the Multilingual Corpus of World’s Constitutions (MCWC)
📄 MCWC paper (OSACT 2024): https://aclanthology.org/2024.osact-1.7/
This variant handles: Spanish → Arabic translation.
The MCWC provides a curated multilingual collection of constitutional texts from countries across the world. The corpus emphasises data cleanliness, high-quality sentence alignment, and detailed metadata (including country and continent mappings). It supports research in:
This model was fine-tuned on the Spanish–Arabic segment of the MCWC, enabling translation that is more attuned to legal and constitutional language than general-purpose MT systems.
This model is suitable for tasks such as:
It is not intended for casual or conversational translation, as it is optimised for formal and legal text.
The model was trained on the MCWC’s Spanish–Arabic aligned sentence pairs.
The MCWC dataset includes:
More details may be found in the accompanying paper:
El-Haj, M. & Ezzini, S. (2024). “The Multilingual Corpus of World’s Constitutions (MCWC).”
OSACT @ LREC-COLING 2024.
https://aclanthology.org/2024.osact-1.7/
The following hyperparameters were used during training:
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 2.2782 | 2.0503 | 0 |
| 1.9158 | 2.0047 | 1 |
| 1.7463 | 1.9950 | 2 |
If you use this model, please cite the MCWC paper:
El-Haj, M. & Ezzini, S. (2024).
The Multilingual Corpus of World’s Constitutions (MCWC).
Proceedings of OSACT @ LREC-COLING 2024.
https://aclanthology.org/2024.osact-1.7/