Gallegos-Macías

RAÍZ: A Hybrid Transformer-Based Machine Translation Architecture with Linguistic Preprocessing and Community Validation for Low-Resource Indigenous Languages (Spanish – Nahuatl and Spanish – Mazahua)

The findings provide evidence that low-resource translation improves when neural learning is combined with linguistically informed and culturally aware processing, and offer a transferable foundation for future research on Indigenous language technology, language preservation and community-centred NLP.