no code implementations • 28 Apr 2024 • Pin-Jie Lin, Merel Scholman, Muhammed Saeed, Vera Demberg
We test the effect of this data augmentation on two critical NLP tasks: machine translation and sentiment analysis.
1 code implementation • 1 Jul 2023 • Pin-Jie Lin, Muhammed Saeed, Ernie Chang, Merel Scholman
In this work, we target on improving upon both text classification and translation of Nigerian Pidgin (Naija) by collecting a large-scale parallel English-Pidgin corpus and further propose a framework of cross-lingual adaptive training that includes both continual and task adaptive training so as to adapt a base pre-trained model to low-resource languages.