@inproceedings{kwon-etal-2026-afroscope,
title = "{AFROSCOPE}: A Framework for Studying the Linguistic Landscape of {A}frica",
author = "Kwon, Sang Yun and
Elmadany, AbdelRahim A. and
Abdul-Mageed, Muhammad",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1308/",
pages = "27651--27676",
ISBN = "979-8-89176-462-0",
abstract = "Language Identification (LID), the task of determining the language of a given text, is a fundamental preprocessing step for multilingual NLP. While recent work has expanded African LID, existing systems remain limited in both language coverage and fine-grained discrimination among closely related languages and varieties. We introduce AFROSCOPE, a unified framework for African LID that includes AFROSCOPE-DATA, a dataset covering 640 languages, and AFROSCOPE-MODELS, a suite of strong LID models with broad African language coverage. To address persistent confusions among related or geographically proximate languages, we propose a hierarchical classification approach leveraging AFROSCOPE-MIRROR, a specialized embedding model for targeted disambiguation. This approach improves macro-F1 by 4.55 points on a confusable-language subset compared to our strongest base model. We further analyze cross-lingual transfer and domain effects, showing how language-family structure, script compatibility, and domain coverage shape LID performance. Finally, we position African LID as an enabling technology for measuring Africa{'}s linguistic landscape in digital text and release AFROSCOPE-DATA and AFROSCOPE-MODELS online."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kwon-etal-2026-afroscope">
<titleInfo>
<title>AFROSCOPE: A Framework for Studying the Linguistic Landscape of Africa</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sang</namePart>
<namePart type="given">Yun</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="given">A</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>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Language Identification (LID), the task of determining the language of a given text, is a fundamental preprocessing step for multilingual NLP. While recent work has expanded African LID, existing systems remain limited in both language coverage and fine-grained discrimination among closely related languages and varieties. We introduce AFROSCOPE, a unified framework for African LID that includes AFROSCOPE-DATA, a dataset covering 640 languages, and AFROSCOPE-MODELS, a suite of strong LID models with broad African language coverage. To address persistent confusions among related or geographically proximate languages, we propose a hierarchical classification approach leveraging AFROSCOPE-MIRROR, a specialized embedding model for targeted disambiguation. This approach improves macro-F1 by 4.55 points on a confusable-language subset compared to our strongest base model. We further analyze cross-lingual transfer and domain effects, showing how language-family structure, script compatibility, and domain coverage shape LID performance. Finally, we position African LID as an enabling technology for measuring Africa’s linguistic landscape in digital text and release AFROSCOPE-DATA and AFROSCOPE-MODELS online.</abstract>
<identifier type="citekey">kwon-etal-2026-afroscope</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1308/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>27651</start>
<end>27676</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AFROSCOPE: A Framework for Studying the Linguistic Landscape of Africa
%A Kwon, Sang Yun
%A Elmadany, AbdelRahim A.
%A Abdul-Mageed, Muhammad
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F kwon-etal-2026-afroscope
%X Language Identification (LID), the task of determining the language of a given text, is a fundamental preprocessing step for multilingual NLP. While recent work has expanded African LID, existing systems remain limited in both language coverage and fine-grained discrimination among closely related languages and varieties. We introduce AFROSCOPE, a unified framework for African LID that includes AFROSCOPE-DATA, a dataset covering 640 languages, and AFROSCOPE-MODELS, a suite of strong LID models with broad African language coverage. To address persistent confusions among related or geographically proximate languages, we propose a hierarchical classification approach leveraging AFROSCOPE-MIRROR, a specialized embedding model for targeted disambiguation. This approach improves macro-F1 by 4.55 points on a confusable-language subset compared to our strongest base model. We further analyze cross-lingual transfer and domain effects, showing how language-family structure, script compatibility, and domain coverage shape LID performance. Finally, we position African LID as an enabling technology for measuring Africa’s linguistic landscape in digital text and release AFROSCOPE-DATA and AFROSCOPE-MODELS online.
%U https://aclanthology.org/2026.findings-emnlp.1308/
%P 27651-27676
Markdown (Informal)
[AFROSCOPE: A Framework for Studying the Linguistic Landscape of Africa](https://aclanthology.org/2026.findings-emnlp.1308/) (Kwon et al., Findings 2026)
ACL