metadata
license: afl-3.0
Citation Information
@inproceedings{adelani-etal-2022-thousand,
title = "A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for {A}frican News Translation",
author = "Adelani, David and
Alabi, Jesujoba and
Fan, Angela and
Kreutzer, Julia and
Shen, Xiaoyu and
Reid, Machel and
Ruiter, Dana and
Klakow, Dietrich and
Nabende, Peter and
Chang, Ernie and
Gwadabe, Tajuddeen and
Sackey, Freshia and
Dossou, Bonaventure F. P. and
Emezue, Chris and
Leong, Colin and
Beukman, Michael and
Muhammad, Shamsuddeen and
Jarso, Guyo and
Yousuf, Oreen and
Niyongabo Rubungo, Andre and
Hacheme, Gilles and
Wairagala, Eric Peter and
Nasir, Muhammad Umair and
Ajibade, Benjamin and
Ajayi, Tunde and
Gitau, Yvonne and
Abbott, Jade and
Ahmed, Mohamed and
Ochieng, Millicent and
Aremu, Anuoluwapo and
Ogayo, Perez and
Mukiibi, Jonathan and
Ouoba Kabore, Fatoumata and
Kalipe, Godson and
Mbaye, Derguene and
Tapo, Allahsera Auguste and
Memdjokam Koagne, Victoire and
Munkoh-Buabeng, Edwin and
Wagner, Valencia and
Abdulmumin, Idris and
Awokoya, Ayodele and
Buzaaba, Happy and
Sibanda, Blessing and
Bukula, Andiswa and
Manthalu, Sam",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.223",
doi = "10.18653/v1/2022.naacl-main.223",
pages = "3053--3070",
abstract = "Recent advances in the pre-training for language models leverage large-scale datasets to create multilingual models. However, low-resource languages are mostly left out in these datasets. This is primarily because many widely spoken languages that are not well represented on the web and therefore excluded from the large-scale crawls for datasets. Furthermore, downstream users of these models are restricted to the selection of languages originally chosen for pre-training. This work investigates how to optimally leverage existing pre-trained models to create low-resource translation systems for 16 African languages. We focus on two questions: 1) How can pre-trained models be used for languages not included in the initial pretraining? and 2) How can the resulting translation models effectively transfer to new domains? To answer these questions, we create a novel African news corpus covering 16 languages, of which eight languages are not part of any existing evaluation dataset. We demonstrate that the most effective strategy for transferring both additional languages and additional domains is to leverage small quantities of high-quality translation data to fine-tune large pre-trained models.",
}