@inproceedings{chakraborty-etal-2026-datasets,
title = "Datasets and Methods for Improving the Cultural Capabilities of {NLP} Systems: A Survey",
author = "Chakraborty, Tania and
Caplan, Eylon and
Wu, Zhaoqing and
Cushing, Kevin and
Qin, Bruce and
Havaldar, Shreya and
Goldwasser, Dan",
editor = "Card, Dallas and
Field, Anjalie and
Keith, Katherine and
Mendelsohn, Julia",
booktitle = "Proceedings of the Seventh Workshop on Natural Language Processing and Computational Social Science",
month = jul,
year = "2026",
address = "San Diego",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlpcss-1.14/",
doi = "10.18653/v1/2026.nlpcss-1.14",
pages = "198--248",
ISBN = "979-8-89176-426-2",
abstract = "In recent years, there has been a surge of interest in Cultural NLP, with substantial efforts to create globally inclusive NLP systems. The rapid growth of literature in this field makes it difficult to track trends in methods and data resources. To address this, we survey over 375 papers to answer three complementary questions: (1) What Cultural Capabilities (CCs) are being targeted in NLP systems? (2) How are cultural data resources being created? and (3) What methods are being used to improve the CCs of those systems? We discuss trends observed across the three questions, and identify relevant research gaps. To facilitate further research in this field, we release our full list of surveyed papers, in the form of an interactive web interface, CultureMine, which includes a feature to allow researchers to add their work; we hope this facilitates future research and proves to be a valuable resource for the Cultural NLP community."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakraborty-etal-2026-datasets">
<titleInfo>
<title>Datasets and Methods for Improving the Cultural Capabilities of NLP Systems: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tania</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eylon</namePart>
<namePart type="family">Caplan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoqing</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Cushing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruce</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shreya</namePart>
<namePart type="family">Havaldar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Goldwasser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Natural Language Processing and Computational Social Science</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dallas</namePart>
<namePart type="family">Card</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anjalie</namePart>
<namePart type="family">Field</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Keith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Mendelsohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-426-2</identifier>
</relatedItem>
<abstract>In recent years, there has been a surge of interest in Cultural NLP, with substantial efforts to create globally inclusive NLP systems. The rapid growth of literature in this field makes it difficult to track trends in methods and data resources. To address this, we survey over 375 papers to answer three complementary questions: (1) What Cultural Capabilities (CCs) are being targeted in NLP systems? (2) How are cultural data resources being created? and (3) What methods are being used to improve the CCs of those systems? We discuss trends observed across the three questions, and identify relevant research gaps. To facilitate further research in this field, we release our full list of surveyed papers, in the form of an interactive web interface, CultureMine, which includes a feature to allow researchers to add their work; we hope this facilitates future research and proves to be a valuable resource for the Cultural NLP community.</abstract>
<identifier type="citekey">chakraborty-etal-2026-datasets</identifier>
<identifier type="doi">10.18653/v1/2026.nlpcss-1.14</identifier>
<location>
<url>https://aclanthology.org/2026.nlpcss-1.14/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>198</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Datasets and Methods for Improving the Cultural Capabilities of NLP Systems: A Survey %A Chakraborty, Tania %A Caplan, Eylon %A Wu, Zhaoqing %A Cushing, Kevin %A Qin, Bruce %A Havaldar, Shreya %A Goldwasser, Dan %Y Card, Dallas %Y Field, Anjalie %Y Keith, Katherine %Y Mendelsohn, Julia %S Proceedings of the Seventh Workshop on Natural Language Processing and Computational Social Science %D 2026 %8 July %I Association for Computational Linguistics %C San Diego %@ 979-8-89176-426-2 %F chakraborty-etal-2026-datasets %X In recent years, there has been a surge of interest in Cultural NLP, with substantial efforts to create globally inclusive NLP systems. The rapid growth of literature in this field makes it difficult to track trends in methods and data resources. To address this, we survey over 375 papers to answer three complementary questions: (1) What Cultural Capabilities (CCs) are being targeted in NLP systems? (2) How are cultural data resources being created? and (3) What methods are being used to improve the CCs of those systems? We discuss trends observed across the three questions, and identify relevant research gaps. To facilitate further research in this field, we release our full list of surveyed papers, in the form of an interactive web interface, CultureMine, which includes a feature to allow researchers to add their work; we hope this facilitates future research and proves to be a valuable resource for the Cultural NLP community. %R 10.18653/v1/2026.nlpcss-1.14 %U https://aclanthology.org/2026.nlpcss-1.14/ %U https://doi.org/10.18653/v1/2026.nlpcss-1.14 %P 198-248
Markdown (Informal)
[Datasets and Methods for Improving the Cultural Capabilities of NLP Systems: A Survey](https://aclanthology.org/2026.nlpcss-1.14/) (Chakraborty et al., NLP+CSS 2026)