3 papers
Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages
Aarón Galiano-Jiménez, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez +1
This paper explores sequence-level knowledge distillation (KD) of multilingual pre-trained encoder-decoder translation models. We argue that the teacher model's output distribution…
Curated Datasets and Neural Models for Machine Translation of Informal Registers between Mayan and Spanish Vernaculars
Andrés Lou, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez +1
The Mayan languages comprise a language family with an ancient history, millions of speakers, and immense cultural value, that, nevertheless, remains severely underrepresented in t…
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach
Víctor M. Sánchez-Cartagena, Miquel Esplà-Gomis, Juan Antonio Pérez-Ortiz +1
In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce.…