Search Results for author: Innocent Mchechesi

Found 1 papers, 0 papers with code

Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For English-isiZulu Machine Translation.

no code implementations NAACL (MIA) 2022 Muhammad Umair Nasir, Innocent Mchechesi

Stemming from the limited availability of datasets and textual resources for low-resource languages such as isiZulu, there is a significant need to be able to harness knowledge from pre-trained models to improve low resource machine translation.

Machine Translation Transfer Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.