A comparison of pipelines for the translation of a low resource language based on transformers
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908540810035200 |
|---|---|
| author | Bonfanti, Chiara Colombino, Michele Coucourde, Giulia Memari, Faeze Pinardi, Stefano Meo, Rosa |
| author_facet | Bonfanti, Chiara Colombino, Michele Coucourde, Giulia Memari, Faeze Pinardi, Stefano Meo, Rosa |
| contents | This work compares three pipelines for training transformer-based neural networks to produce machine translators for Bambara, a Mandè language spoken in Africa by about 14,188,850 people. The first pipeline trains a simple transformer to translate sentences from French into Bambara. The second fine-tunes LLaMA3 (3B-8B) instructor models using decoder-only architectures for French-to-Bambara translation. Models from the first two pipelines were trained with different hyperparameter combinations to improve BLEU and chrF scores, evaluated on both test sentences and official Bambara benchmarks. The third pipeline uses language distillation with a student-teacher dual neural network to integrate Bambara into a pre-trained LaBSE model, which provides language-agnostic embeddings. A BERT extension is then applied to LaBSE to generate translations. All pipelines were tested on Dokotoro (medical) and Bayelemagaba (mixed domains). Results show that the first pipeline, although simpler, achieves the best translation accuracy (10% BLEU, 21% chrF on Bayelemagaba), consistent with low-resource translation results. On the Yiri dataset, created for this work, it achieves 33.81% BLEU and 41% chrF. Instructor-based models perform better on single datasets than on aggregated collections, suggesting they capture dataset-specific patterns more effectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12514 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A comparison of pipelines for the translation of a low resource language based on transformers Bonfanti, Chiara Colombino, Michele Coucourde, Giulia Memari, Faeze Pinardi, Stefano Meo, Rosa Computation and Language Computational Engineering, Finance, and Science Computers and Society Machine Learning This work compares three pipelines for training transformer-based neural networks to produce machine translators for Bambara, a Mandè language spoken in Africa by about 14,188,850 people. The first pipeline trains a simple transformer to translate sentences from French into Bambara. The second fine-tunes LLaMA3 (3B-8B) instructor models using decoder-only architectures for French-to-Bambara translation. Models from the first two pipelines were trained with different hyperparameter combinations to improve BLEU and chrF scores, evaluated on both test sentences and official Bambara benchmarks. The third pipeline uses language distillation with a student-teacher dual neural network to integrate Bambara into a pre-trained LaBSE model, which provides language-agnostic embeddings. A BERT extension is then applied to LaBSE to generate translations. All pipelines were tested on Dokotoro (medical) and Bayelemagaba (mixed domains). Results show that the first pipeline, although simpler, achieves the best translation accuracy (10% BLEU, 21% chrF on Bayelemagaba), consistent with low-resource translation results. On the Yiri dataset, created for this work, it achieves 33.81% BLEU and 41% chrF. Instructor-based models perform better on single datasets than on aggregated collections, suggesting they capture dataset-specific patterns more effectively. |
| title | A comparison of pipelines for the translation of a low resource language based on transformers |
| topic | Computation and Language Computational Engineering, Finance, and Science Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2509.12514 |