Search Results for author:
Found 3 papers, 2 papers with code
Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For English-isiZulu Machine Translation.
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.
Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For English-isiZulu Machine Translation
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.
Ranked #1 on
Low-Resource Neural Machine Translation
on Umsuka
Low-Resource Neural Machine Translation
Transfer Learning
+1
A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation
We focus on two questions: 1) How can pre-trained models be used for languages not included in the initial pre-training?
