@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",
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 {\textasciitilde}31 out of {\textasciitilde}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",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adebara-etal-2023-serengeti">
<titleInfo>
<title>SERENGETI: Massively Multilingual Language Models for Africa</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ife</namePart>
<namePart type="family">Adebara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alcides</namePart>
<namePart type="family">Alcoba Inciarte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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</abstract>
<identifier type="citekey">adebara-etal-2023-serengeti</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.97</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.97</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1498</start>
<end>1537</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SERENGETI: Massively Multilingual Language Models for Africa
%A Adebara, Ife
%A Elmadany, AbdelRahim
%A Abdul-Mageed, Muhammad
%A Alcoba Inciarte, Alcides
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F adebara-etal-2023-serengeti
%X 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
%R 10.18653/v1/2023.findings-acl.97
%U https://aclanthology.org/2023.findings-acl.97
%U https://doi.org/10.18653/v1/2023.findings-acl.97
%P 1498-1537
Markdown (Informal)
[SERENGETI: Massively Multilingual Language Models for Africa](https://aclanthology.org/2023.findings-acl.97) (Adebara et al., Findings 2023)
ACL
- Ife Adebara, AbdelRahim Elmadany, Muhammad Abdul-Mageed, and Alcides Alcoba Inciarte. 2023. SERENGETI: Massively Multilingual Language Models for Africa. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1498–1537, Toronto, Canada. Association for Computational Linguistics.