@inproceedings{nwatu-etal-2026-atlasnlp,
title = "{A}tlas{NLP}: A Country-Aware Atlas of Dataset Representation in {NLP}",
author = "Nwatu, Joan and
Amare, Tsedeniya Solomon and
Bai, Longju and
Balcha, Bontu Fufa and
Bashir, Zayd and
Borah, Angana and
Burzo, Zara and
Choi, Yubin and
Deng, Naihao and
Gupta, Samika and
Faloughi, Michel and
Kwizera, Claude and
Ma, Ziqiao and
Panizo, Cynthia Yacel Fuertes and
Seehorn, Ellie and
Shen, Hui and
Tang, Jiayi and
Zhao, Zesen and
Zheng, Boyuan and
Mihalcea, Rada",
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.2415/",
pages = "54839--54867",
ISBN = "979-8-89176-459-0",
abstract = "Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and informing AI policy. However, geographic metadata is very rarely available, and country-level representation is often hidden behind broad language-level claims. We introduce **AtlasNLP**, a country-aware atlas of over 13,000 NLP dataset records across normalized NLP task categories, tracking both the populations represented and where datasets are produced. AtlasNLP includes **AtlasNLP-Gold**, a human-curated reference set, and **AtlasNLP-Core**, an ACL-derived large-scale collection. Using this resource, we show that (1) dataset coverage is highly uneven across countries and tasks; (2) dataset production and representation are geographically asymmetric; and (3) language coverage does not imply geographic representation. These findings reveal blind spots in current dataset documentation practices and motivate more explicit geographic metadata for country-aware NLP evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nwatu-etal-2026-atlasnlp">
<titleInfo>
<title>AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joan</namePart>
<namePart type="family">Nwatu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsedeniya</namePart>
<namePart type="given">Solomon</namePart>
<namePart type="family">Amare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longju</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bontu</namePart>
<namePart type="given">Fufa</namePart>
<namePart type="family">Balcha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zayd</namePart>
<namePart type="family">Bashir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angana</namePart>
<namePart type="family">Borah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zara</namePart>
<namePart type="family">Burzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naihao</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samika</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Faloughi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claude</namePart>
<namePart type="family">Kwizera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziqiao</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cynthia</namePart>
<namePart type="given">Yacel</namePart>
<namePart type="given">Fuertes</namePart>
<namePart type="family">Panizo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Seehorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zesen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boyuan</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</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>Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and informing AI policy. However, geographic metadata is very rarely available, and country-level representation is often hidden behind broad language-level claims. We introduce **AtlasNLP**, a country-aware atlas of over 13,000 NLP dataset records across normalized NLP task categories, tracking both the populations represented and where datasets are produced. AtlasNLP includes **AtlasNLP-Gold**, a human-curated reference set, and **AtlasNLP-Core**, an ACL-derived large-scale collection. Using this resource, we show that (1) dataset coverage is highly uneven across countries and tasks; (2) dataset production and representation are geographically asymmetric; and (3) language coverage does not imply geographic representation. These findings reveal blind spots in current dataset documentation practices and motivate more explicit geographic metadata for country-aware NLP evaluation.</abstract>
<identifier type="citekey">nwatu-etal-2026-atlasnlp</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2415/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>54839</start>
<end>54867</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP
%A Nwatu, Joan
%A Amare, Tsedeniya Solomon
%A Bai, Longju
%A Balcha, Bontu Fufa
%A Bashir, Zayd
%A Borah, Angana
%A Burzo, Zara
%A Choi, Yubin
%A Deng, Naihao
%A Gupta, Samika
%A Faloughi, Michel
%A Kwizera, Claude
%A Ma, Ziqiao
%A Panizo, Cynthia Yacel Fuertes
%A Seehorn, Ellie
%A Shen, Hui
%A Tang, Jiayi
%A Zhao, Zesen
%A Zheng, Boyuan
%A Mihalcea, Rada
%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 nwatu-etal-2026-atlasnlp
%X Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and informing AI policy. However, geographic metadata is very rarely available, and country-level representation is often hidden behind broad language-level claims. We introduce **AtlasNLP**, a country-aware atlas of over 13,000 NLP dataset records across normalized NLP task categories, tracking both the populations represented and where datasets are produced. AtlasNLP includes **AtlasNLP-Gold**, a human-curated reference set, and **AtlasNLP-Core**, an ACL-derived large-scale collection. Using this resource, we show that (1) dataset coverage is highly uneven across countries and tasks; (2) dataset production and representation are geographically asymmetric; and (3) language coverage does not imply geographic representation. These findings reveal blind spots in current dataset documentation practices and motivate more explicit geographic metadata for country-aware NLP evaluation.
%U https://aclanthology.org/2026.emnlp-main.2415/
%P 54839-54867
Markdown (Informal)
[AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP](https://aclanthology.org/2026.emnlp-main.2415/) (Nwatu et al., EMNLP 2026)
ACL
- Joan Nwatu, Tsedeniya Solomon Amare, Longju Bai, Bontu Fufa Balcha, Zayd Bashir, Angana Borah, Zara Burzo, Yubin Choi, Naihao Deng, Samika Gupta, Michel Faloughi, Claude Kwizera, Ziqiao Ma, Cynthia Yacel Fuertes Panizo, Ellie Seehorn, Hui Shen, Jiayi Tang, Zesen Zhao, Boyuan Zheng, and Rada Mihalcea. 2026. AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 54839–54867, Budapest, Hungary. Association for Computational Linguistics.