@inproceedings{zhang-etal-2024-mc2,
title = "{MC}$^2$: Towards Transparent and Culturally-Aware {NLP} for Minority Languages in {C}hina",
author = "Zhang, Chen and
Tao, Mingxu and
Huang, Quzhe and
Lin, Jiuheng and
Chen, Zhibin and
Feng, Yansong",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.479",
pages = "8832--8850",
abstract = "Current large language models demonstrate deficiencies in understanding low-resource languages, particularly the minority languages in China. This limitation stems from the scarcity of available pre-training data. To address this accessibility challenge, we present MC$^2$, a Multilingual Corpus of Minority Languages in China, which is the largest open-source corpus of its kind so far. MC$^2$ includes four underrepresented languages: Tibetan, Uyghur, Kazakh, and Mongolian. Notably, we focus on the less common writing systems of Kazakh and Mongolian, i.e., Kazakh Arabic script and traditional Mongolian script, respectively, which have been long neglected in previous corpus construction efforts. Recognizing the prevalence of language contamination within existing corpora, we adopt a quality-centric solution for collecting MC$^2$, prioritizing accuracy while enhancing diversity. Furthermore, we underscore the importance of attending to the multiplicity of writing systems, which is closely related to the cultural awareness of the resulting models. The MC$^2$ corpus and related models are made public to the community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-mc2">
<titleInfo>
<title>MC²: Towards Transparent and Culturally-Aware NLP for Minority Languages in China</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingxu</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quzhe</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiuheng</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhibin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current large language models demonstrate deficiencies in understanding low-resource languages, particularly the minority languages in China. This limitation stems from the scarcity of available pre-training data. To address this accessibility challenge, we present MC², a Multilingual Corpus of Minority Languages in China, which is the largest open-source corpus of its kind so far. MC² includes four underrepresented languages: Tibetan, Uyghur, Kazakh, and Mongolian. Notably, we focus on the less common writing systems of Kazakh and Mongolian, i.e., Kazakh Arabic script and traditional Mongolian script, respectively, which have been long neglected in previous corpus construction efforts. Recognizing the prevalence of language contamination within existing corpora, we adopt a quality-centric solution for collecting MC², prioritizing accuracy while enhancing diversity. Furthermore, we underscore the importance of attending to the multiplicity of writing systems, which is closely related to the cultural awareness of the resulting models. The MC² corpus and related models are made public to the community.</abstract>
<identifier type="citekey">zhang-etal-2024-mc2</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.479</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>8832</start>
<end>8850</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MC²: Towards Transparent and Culturally-Aware NLP for Minority Languages in China
%A Zhang, Chen
%A Tao, Mingxu
%A Huang, Quzhe
%A Lin, Jiuheng
%A Chen, Zhibin
%A Feng, Yansong
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhang-etal-2024-mc2
%X Current large language models demonstrate deficiencies in understanding low-resource languages, particularly the minority languages in China. This limitation stems from the scarcity of available pre-training data. To address this accessibility challenge, we present MC², a Multilingual Corpus of Minority Languages in China, which is the largest open-source corpus of its kind so far. MC² includes four underrepresented languages: Tibetan, Uyghur, Kazakh, and Mongolian. Notably, we focus on the less common writing systems of Kazakh and Mongolian, i.e., Kazakh Arabic script and traditional Mongolian script, respectively, which have been long neglected in previous corpus construction efforts. Recognizing the prevalence of language contamination within existing corpora, we adopt a quality-centric solution for collecting MC², prioritizing accuracy while enhancing diversity. Furthermore, we underscore the importance of attending to the multiplicity of writing systems, which is closely related to the cultural awareness of the resulting models. The MC² corpus and related models are made public to the community.
%U https://aclanthology.org/2024.acl-long.479
%P 8832-8850
Markdown (Informal)
[MC2: Towards Transparent and Culturally-Aware NLP for Minority Languages in China](https://aclanthology.org/2024.acl-long.479) (Zhang et al., ACL 2024)
ACL