Papers by Cheick Tidiani Cissé
Kumatigi: Quality-Driven Data Augmentation for Low-Resource Machine Translation (2026.findings-acl)
Copied to clipboard
| Challenge: | Neural machine translation for extremely low-resource languages faces compounding challenges: limited parallel data, orthographic inconsistency, and inconsistent metadata for principled training. |
| Approach: | They propose a quality-annotated French-Bambara corpus combining systematic curation with data augmentation strategies tailored to Bambaran. |
| Outcome: | The proposed framework achieves up to +3–4 BLEU over strong baselines. |