@inproceedings{churina-etal-2026-disentangling,
title = "Disentangling Codemixing in Chats: The {NUS} {ABC} Codemixed Corpus",
author = "Churina, Svetlana and
Gupta, Akshat and
Mujtahid, Nur Insyirah Binte Imam and
Jaidka, Kokil",
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.80/",
pages = "1602--1624",
ISBN = "979-8-89176-395-1",
abstract = "Code-mixing involves the seamless integration of linguistic elements from multiple languages within a single discourse, reflecting natural multilingual communication patterns. Despite its prominence in informal interactions such as social media, chat messages and instant-messaging exchanges, there has been a lack of publicly available corpora that are author-labeled and suitable for modeling human conversations and relationships. This study introduces the first labeled and general-purpose corpus for understanding code-mixing in context while maintaining rigorous privacy and ethical standards. It includes over 355,641 messages spanning various code-mixing patterns, with a primary focus on English, Mandarin, and other languages. We expect the Codemix Corpus to serve as a foundational dataset for research in computational linguistics, sociolinguistics, and NLP applications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="churina-etal-2026-disentangling">
<titleInfo>
<title>Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Churina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshat</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nur</namePart>
<namePart type="given">Insyirah</namePart>
<namePart type="given">Binte</namePart>
<namePart type="given">Imam</namePart>
<namePart type="family">Mujtahid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kokil</namePart>
<namePart type="family">Jaidka</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>Code-mixing involves the seamless integration of linguistic elements from multiple languages within a single discourse, reflecting natural multilingual communication patterns. Despite its prominence in informal interactions such as social media, chat messages and instant-messaging exchanges, there has been a lack of publicly available corpora that are author-labeled and suitable for modeling human conversations and relationships. This study introduces the first labeled and general-purpose corpus for understanding code-mixing in context while maintaining rigorous privacy and ethical standards. It includes over 355,641 messages spanning various code-mixing patterns, with a primary focus on English, Mandarin, and other languages. We expect the Codemix Corpus to serve as a foundational dataset for research in computational linguistics, sociolinguistics, and NLP applications.</abstract>
<identifier type="citekey">churina-etal-2026-disentangling</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.80/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1602</start>
<end>1624</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus
%A Churina, Svetlana
%A Gupta, Akshat
%A Mujtahid, Nur Insyirah Binte Imam
%A Jaidka, Kokil
%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 churina-etal-2026-disentangling
%X Code-mixing involves the seamless integration of linguistic elements from multiple languages within a single discourse, reflecting natural multilingual communication patterns. Despite its prominence in informal interactions such as social media, chat messages and instant-messaging exchanges, there has been a lack of publicly available corpora that are author-labeled and suitable for modeling human conversations and relationships. This study introduces the first labeled and general-purpose corpus for understanding code-mixing in context while maintaining rigorous privacy and ethical standards. It includes over 355,641 messages spanning various code-mixing patterns, with a primary focus on English, Mandarin, and other languages. We expect the Codemix Corpus to serve as a foundational dataset for research in computational linguistics, sociolinguistics, and NLP applications.
%U https://aclanthology.org/2026.findings-acl.80/
%P 1602-1624
Markdown (Informal)
[Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus](https://aclanthology.org/2026.findings-acl.80/) (Churina et al., Findings 2026)
ACL
- Svetlana Churina, Akshat Gupta, Nur Insyirah Binte Imam Mujtahid, and Kokil Jaidka. 2026. Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus. In Findings of the Association for Computational Linguistics: ACL 2026, pages 1602–1624, San Diego, California, United States. Association for Computational Linguistics.