@inproceedings{buzaaba-etal-2026-afrisud,
title = "{A}fri{SUD}: A Dependency Treebank Collection for Evaluating Models on {A}frican Languages",
author = "Buzaaba, Happy and
Dione, Cheikh Mouhamadou Bamba and
Adelani, David Ifeoluwa and
Kahane, Sylvain and
Guillaume, Bruno and
Gerdes, Kim and
Muhammad, Shamsuddeen Hassan and
Guan, Kevin and
Aremu, Anuoluwapo and
Etori, Naome A and
Inyang, Utitofon and
Nabende, Peter and
Bamutura, David Sabiiti and
Bukula, Andiswa and
Akinade, Idris and
Uchechukwu, Chinedu and
Mabuya, Rooweither and
Fellbaum, Christiane",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1896/",
pages = "43227--43248",
ISBN = "979-8-89176-459-0",
abstract = "Despite their linguistic diversity and global significance, African languages remain underrepresented in research and resources to support NLP. We aim to bridge this gap by introducing \textbf{AfriSUD}, the first multilingual collection of syntactically annotated treebanks for nine diverse African languages spanning major language families and regions across Sub-Saharan Africa. Using the Surface-Syntactic Universal Dependencies (SUD) framework, our community-led effort provides high-quality, native-speaker-verified data that capture typological key features such as agglutination and tone. We evaluate a range of models on AfriSUD for part-of-speech tagging and dependency parsing, including non-transformer baselines, multilingual pretrained encoders, and LLMs. Our results reveal a significant syntax gap, where models still show clear limitations across the nine languages, suggesting that existing architectures may not fully capture the structural diversity of African-language syntax."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="buzaaba-etal-2026-afrisud">
<titleInfo>
<title>AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Happy</namePart>
<namePart type="family">Buzaaba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheikh</namePart>
<namePart type="given">Mouhamadou</namePart>
<namePart type="given">Bamba</namePart>
<namePart type="family">Dione</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Kahane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Guillaume</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="family">Gerdes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuoluwapo</namePart>
<namePart type="family">Aremu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naome</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Etori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Utitofon</namePart>
<namePart type="family">Inyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Sabiiti</namePart>
<namePart type="family">Bamutura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andiswa</namePart>
<namePart type="family">Bukula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Akinade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chinedu</namePart>
<namePart type="family">Uchechukwu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christiane</namePart>
<namePart type="family">Fellbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Despite their linguistic diversity and global significance, African languages remain underrepresented in research and resources to support NLP. We aim to bridge this gap by introducing AfriSUD, the first multilingual collection of syntactically annotated treebanks for nine diverse African languages spanning major language families and regions across Sub-Saharan Africa. Using the Surface-Syntactic Universal Dependencies (SUD) framework, our community-led effort provides high-quality, native-speaker-verified data that capture typological key features such as agglutination and tone. We evaluate a range of models on AfriSUD for part-of-speech tagging and dependency parsing, including non-transformer baselines, multilingual pretrained encoders, and LLMs. Our results reveal a significant syntax gap, where models still show clear limitations across the nine languages, suggesting that existing architectures may not fully capture the structural diversity of African-language syntax.</abstract>
<identifier type="citekey">buzaaba-etal-2026-afrisud</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1896/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>43227</start>
<end>43248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages
%A Buzaaba, Happy
%A Dione, Cheikh Mouhamadou Bamba
%A Adelani, David Ifeoluwa
%A Kahane, Sylvain
%A Guillaume, Bruno
%A Gerdes, Kim
%A Muhammad, Shamsuddeen Hassan
%A Guan, Kevin
%A Aremu, Anuoluwapo
%A Etori, Naome A.
%A Inyang, Utitofon
%A Nabende, Peter
%A Bamutura, David Sabiiti
%A Bukula, Andiswa
%A Akinade, Idris
%A Uchechukwu, Chinedu
%A Mabuya, Rooweither
%A Fellbaum, Christiane
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F buzaaba-etal-2026-afrisud
%X Despite their linguistic diversity and global significance, African languages remain underrepresented in research and resources to support NLP. We aim to bridge this gap by introducing AfriSUD, the first multilingual collection of syntactically annotated treebanks for nine diverse African languages spanning major language families and regions across Sub-Saharan Africa. Using the Surface-Syntactic Universal Dependencies (SUD) framework, our community-led effort provides high-quality, native-speaker-verified data that capture typological key features such as agglutination and tone. We evaluate a range of models on AfriSUD for part-of-speech tagging and dependency parsing, including non-transformer baselines, multilingual pretrained encoders, and LLMs. Our results reveal a significant syntax gap, where models still show clear limitations across the nine languages, suggesting that existing architectures may not fully capture the structural diversity of African-language syntax.
%U https://aclanthology.org/2026.emnlp-main.1896/
%P 43227-43248
Markdown (Informal)
[AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages](https://aclanthology.org/2026.emnlp-main.1896/) (Buzaaba et al., EMNLP 2026)
ACL
- Happy Buzaaba, Cheikh Mouhamadou Bamba Dione, David Ifeoluwa Adelani, Sylvain Kahane, Bruno Guillaume, Kim Gerdes, Shamsuddeen Hassan Muhammad, Kevin Guan, Anuoluwapo Aremu, Naome A Etori, Utitofon Inyang, Peter Nabende, David Sabiiti Bamutura, Andiswa Bukula, Idris Akinade, Chinedu Uchechukwu, Rooweither Mabuya, and Christiane Fellbaum. 2026. AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 43227–43248, Budapest, Hungary. Association for Computational Linguistics.