@inproceedings{su-etal-2026-dual,
title = "A Dual-View Analysis of Multiple Languages in Colonial Newspapers",
author = "Su, Zhan and
Chen, Xiaoya and
Mo, Fengran and
Vos, Ida L. and
Tiwari, Prayag and
Zhang, Yazhou and
Zheng, Qian and
da Silva Perez, Nat{\'a}lia",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1029/",
pages = "20559--20573",
ISBN = "979-8-89176-395-1",
abstract = "Historical newspapers from the colonial period offer valuable evidence of how racializing language evolved over time. However, there are challenges in studying this type of historical data: 1) Data scarcity: acquiring large, annotated historical datasets is difficult, hindering the possibility of analyzing racialization comprehensively; 2) Digitized materials frequently contain Optical Character Recognition (OCR) errors and other types of noise that complicate text extraction and computational analysis; 3) Colonial newspapers are often multilingual and written in archaic prose, hindering the effectiveness of NLP tools developed for modern, single language texts. This paper addresses these challenges by conducting a dual-view, jointly studying multilingual event extraction and temporal semantic shift tasks. Specifically, we introduce a contextual question answering (CQA) and a visual question answering (VQA) derived from eighteenth- and nineteenth-century colonial newspapers. Content-wise, we focus on how enslaved people were described by enslavers as well as how they articulated their own condition through QA pairs of newspapers written in Dutch, English-French, and Spanish. Our results show that LLMs are still limited for low-resource VQA tasks. For temporal semantic change, we train temporal word embedding with a compass. The study concludes that racialization is a fluid process of linguistic recalibration where the decline of slavery merely shifted the language of control onto new categories of labor and identity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="su-etal-2026-dual">
<titleInfo>
<title>A Dual-View Analysis of Multiple Languages in Colonial Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhan</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoya</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengran</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ida</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Vos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prayag</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yazhou</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natália</namePart>
<namePart type="family">da Silva Perez</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Historical newspapers from the colonial period offer valuable evidence of how racializing language evolved over time. However, there are challenges in studying this type of historical data: 1) Data scarcity: acquiring large, annotated historical datasets is difficult, hindering the possibility of analyzing racialization comprehensively; 2) Digitized materials frequently contain Optical Character Recognition (OCR) errors and other types of noise that complicate text extraction and computational analysis; 3) Colonial newspapers are often multilingual and written in archaic prose, hindering the effectiveness of NLP tools developed for modern, single language texts. This paper addresses these challenges by conducting a dual-view, jointly studying multilingual event extraction and temporal semantic shift tasks. Specifically, we introduce a contextual question answering (CQA) and a visual question answering (VQA) derived from eighteenth- and nineteenth-century colonial newspapers. Content-wise, we focus on how enslaved people were described by enslavers as well as how they articulated their own condition through QA pairs of newspapers written in Dutch, English-French, and Spanish. Our results show that LLMs are still limited for low-resource VQA tasks. For temporal semantic change, we train temporal word embedding with a compass. The study concludes that racialization is a fluid process of linguistic recalibration where the decline of slavery merely shifted the language of control onto new categories of labor and identity.</abstract>
<identifier type="citekey">su-etal-2026-dual</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1029/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>20559</start>
<end>20573</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dual-View Analysis of Multiple Languages in Colonial Newspapers
%A Su, Zhan
%A Chen, Xiaoya
%A Mo, Fengran
%A Vos, Ida L.
%A Tiwari, Prayag
%A Zhang, Yazhou
%A Zheng, Qian
%A da Silva Perez, Natália
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F su-etal-2026-dual
%X Historical newspapers from the colonial period offer valuable evidence of how racializing language evolved over time. However, there are challenges in studying this type of historical data: 1) Data scarcity: acquiring large, annotated historical datasets is difficult, hindering the possibility of analyzing racialization comprehensively; 2) Digitized materials frequently contain Optical Character Recognition (OCR) errors and other types of noise that complicate text extraction and computational analysis; 3) Colonial newspapers are often multilingual and written in archaic prose, hindering the effectiveness of NLP tools developed for modern, single language texts. This paper addresses these challenges by conducting a dual-view, jointly studying multilingual event extraction and temporal semantic shift tasks. Specifically, we introduce a contextual question answering (CQA) and a visual question answering (VQA) derived from eighteenth- and nineteenth-century colonial newspapers. Content-wise, we focus on how enslaved people were described by enslavers as well as how they articulated their own condition through QA pairs of newspapers written in Dutch, English-French, and Spanish. Our results show that LLMs are still limited for low-resource VQA tasks. For temporal semantic change, we train temporal word embedding with a compass. The study concludes that racialization is a fluid process of linguistic recalibration where the decline of slavery merely shifted the language of control onto new categories of labor and identity.
%U https://aclanthology.org/2026.findings-acl.1029/
%P 20559-20573
Markdown (Informal)
[A Dual-View Analysis of Multiple Languages in Colonial Newspapers](https://aclanthology.org/2026.findings-acl.1029/) (Su et al., Findings 2026)
ACL
- Zhan Su, Xiaoya Chen, Fengran Mo, Ida L. Vos, Prayag Tiwari, Yazhou Zhang, Qian Zheng, and Natália da Silva Perez. 2026. A Dual-View Analysis of Multiple Languages in Colonial Newspapers. In Findings of the Association for Computational Linguistics: ACL 2026, pages 20559–20573, San Diego, California, United States. Association for Computational Linguistics.