SERENGETI: Massively Multilingual Language Models for Africa
Ife Adebara, AbdelRahim Elmadany, Muhammad Abdul-Mageed, Alcides Alcoba Inciarte
Abstract
Multilingual pretrained language models (mPLMs) acquire valuable, generalizable linguistic information during pretraining and have advanced the state of the art on task-specific finetuning. To date, only ~31 out of ~2,000 African languages are covered in existing language models. We ameliorate this limitation by developing SERENGETI, a set of massively multilingual language model that covers 517 African languages and language varieties. We evaluate our novel models on eight natural language understanding tasks across 20 datasets, comparing to 4 mPLMs that cover 4-23 African languages. SERENGETI outperforms other models on 11 datasets across the eights tasks, achieving 82.27 average F_1. We also perform analyses of errors from our models, which allows us to investigate the influence of language genealogy and linguistic similarity when the models are applied under zero-shot settings. We will publicly release our models for research. Anonymous link
BibTeX
@inproceedings{adebara-etal-2023-serengeti,
title = "{SERENGETI}: Massively Multilingual Language Models for {A}frica",
author = "Adebara, Ife and
Elmadany, AbdelRahim and
Abdul-Mageed, Muhammad and
Alcoba Inciarte, Alcides",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.97/",
doi = "10.18653/v1/2023.findings-acl.97",
pages = "1498--1537"
}