原文
@inproceedings{yang-etal-2025-nushurescue,
title = {{N}{\"u}shu{R}escue: Reviving the Endangered N{\"u}shu Language with {AI}},
author = "Yang, Ivory and
Ma, Weicheng and
Vosoughi, Soroush",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.468/",
pages = "7020--7034",
abstract = {The preservation and revitalization of endangered and extinct languages is a meaningful endeavor, conserving cultural heritage while enriching fields like linguistics and anthropology. However, these languages are typically low-resource, making their reconstruction labor-intensive and costly. This challenge is exemplified by N{\"u}shu, a rare script historically used by Yao women in China for self-expression within a patriarchal society. To address this challenge, we introduce N{\"u}shuRescue, an AI-driven framework designed to train large language models (LLMs) on endangered languages with minimal data. N{\"u}shuRescue automates evaluation and expands target corpora to accelerate linguistic revitalization. As a foundational component, we developed NCGold, a 500-sentence N{\"u}shu-Chinese parallel corpus, the first publicly available dataset of its kind. Leveraging GPT-4-Turbo, with no prior exposure to N{\"u}shu and only 35 short examples from NCGold, N{\"u}shuRescue achieved 48.69{\%} translation accuracy on 50 withheld sentences and generated NCSilver, a set of 98 newly translated modern Chinese sentences of varying lengths. In addition, we developed FastText-based and Seq2Seq models to further support research on N{\"u}shu. N{\"u}shuRescue provides a versatile and scalable tool for the revitalization of endangered languages, minimizing the need for extensive human input. All datasets and code have been made publicly available at \url{https://github.com/ivoryayang/NushuRescue}.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-nushurescue">
<titleInfo>
<title>NüshuRescue: Reviving the Endangered Nüshu Language with AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivory</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weicheng</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soroush</namePart>
<namePart type="family">Vosoughi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The preservation and revitalization of endangered and extinct languages is a meaningful endeavor, conserving cultural heritage while enriching fields like linguistics and anthropology. However, these languages are typically low-resource, making their reconstruction labor-intensive and costly. This challenge is exemplified by Nüshu, a rare script historically used by Yao women in China for self-expression within a patriarchal society. To address this challenge, we introduce NüshuRescue, an AI-driven framework designed to train large language models (LLMs) on endangered languages with minimal data. NüshuRescue automates evaluation and expands target corpora to accelerate linguistic revitalization. As a foundational component, we developed NCGold, a 500-sentence Nüshu-Chinese parallel corpus, the first publicly available dataset of its kind. Leveraging GPT-4-Turbo, with no prior exposure to Nüshu and only 35 short examples from NCGold, NüshuRescue achieved 48.69% translation accuracy on 50 withheld sentences and generated NCSilver, a set of 98 newly translated modern Chinese sentences of varying lengths. In addition, we developed FastText-based and Seq2Seq models to further support research on Nüshu. NüshuRescue provides a versatile and scalable tool for the revitalization of endangered languages, minimizing the need for extensive human input. All datasets and code have been made publicly available at https://github.com/ivoryayang/NushuRescue.</abstract>
<identifier type="citekey">yang-etal-2025-nushurescue</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.468/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>7020</start>
<end>7034</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T NüshuRescue: Reviving the Endangered Nüshu Language with AI %A Yang, Ivory %A Ma, Weicheng %A Vosoughi, Soroush %Y Rambow, Owen %Y Wanner, Leo %Y Apidianaki, Marianna %Y Al-Khalifa, Hend %Y Eugenio, Barbara Di %Y Schockaert, Steven %S Proceedings of the 31st International Conference on Computational Linguistics %D 2025 %8 January %I Association for Computational Linguistics %C Abu Dhabi, UAE %F yang-etal-2025-nushurescue %X The preservation and revitalization of endangered and extinct languages is a meaningful endeavor, conserving cultural heritage while enriching fields like linguistics and anthropology. However, these languages are typically low-resource, making their reconstruction labor-intensive and costly. This challenge is exemplified by Nüshu, a rare script historically used by Yao women in China for self-expression within a patriarchal society. To address this challenge, we introduce NüshuRescue, an AI-driven framework designed to train large language models (LLMs) on endangered languages with minimal data. NüshuRescue automates evaluation and expands target corpora to accelerate linguistic revitalization. As a foundational component, we developed NCGold, a 500-sentence Nüshu-Chinese parallel corpus, the first publicly available dataset of its kind. Leveraging GPT-4-Turbo, with no prior exposure to Nüshu and only 35 short examples from NCGold, NüshuRescue achieved 48.69% translation accuracy on 50 withheld sentences and generated NCSilver, a set of 98 newly translated modern Chinese sentences of varying lengths. In addition, we developed FastText-based and Seq2Seq models to further support research on Nüshu. NüshuRescue provides a versatile and scalable tool for the revitalization of endangered languages, minimizing the need for extensive human input. All datasets and code have been made publicly available at https://github.com/ivoryayang/NushuRescue. %U https://aclanthology.org/2025.coling-main.468/ %P 7020-7034
Markdown (Informal)
[NüshuRescue: Reviving the Endangered Nüshu Language with AI](https://aclanthology.org/2025.coling-main.468/) (Yang et al., COLING 2025)