@inproceedings{zheng-yu-2025-incorporating,
title = "Incorporating Lexicon-Aligned Prompting in Large Language Model for {T}angut{--}{C}hinese Translation",
author = "Zheng, Yuxi and
Yu, Jingsong",
editor = "Anderson, Adam and
Gordin, Shai and
Li, Bin and
Liu, Yudong and
Passarotti, Marco C. and
Sprugnoli, Rachele",
booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
month = may,
year = "2025",
address = "The Albuquerque Convention Center, Laguna",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.alp-1.16/",
doi = "10.18653/v1/2025.alp-1.16",
pages = "127--136",
ISBN = "979-8-89176-235-0",
abstract = "This paper proposes a machine translation approach for Tangut{--}Chinese using a large language model (LLM) enhanced with lexical knowledge. We fine-tune a Qwen-based LLM using Tangut{--}Chinese parallel corpora and dictionary definitions. Experimental results demonstrate that incorporating single-character dictionary definitions leads to the best BLEU-4 score of 72.33 for literal translation. Additionally, applying a chain-of-thought prompting strategy significantly boosts free translation performance to 64.20. The model also exhibits strong few-shot learning abilities, with performance improving as the training dataset size increases. Our approach effectively translates both simple and complex Tangut sentences, offering a robust solution for low-resource language translation and contributing to the digital preservation of Tangut texts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-yu-2025-incorporating">
<titleInfo>
<title>Incorporating Lexicon-Aligned Prompting in Large Language Model for Tangut–Chinese Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxi</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingsong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Ancient Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">The Albuquerque Convention Center, Laguna</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-235-0</identifier>
</relatedItem>
<abstract>This paper proposes a machine translation approach for Tangut–Chinese using a large language model (LLM) enhanced with lexical knowledge. We fine-tune a Qwen-based LLM using Tangut–Chinese parallel corpora and dictionary definitions. Experimental results demonstrate that incorporating single-character dictionary definitions leads to the best BLEU-4 score of 72.33 for literal translation. Additionally, applying a chain-of-thought prompting strategy significantly boosts free translation performance to 64.20. The model also exhibits strong few-shot learning abilities, with performance improving as the training dataset size increases. Our approach effectively translates both simple and complex Tangut sentences, offering a robust solution for low-resource language translation and contributing to the digital preservation of Tangut texts.</abstract>
<identifier type="citekey">zheng-yu-2025-incorporating</identifier>
<identifier type="doi">10.18653/v1/2025.alp-1.16</identifier>
<location>
<url>https://aclanthology.org/2025.alp-1.16/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>127</start>
<end>136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Lexicon-Aligned Prompting in Large Language Model for Tangut–Chinese Translation
%A Zheng, Yuxi
%A Yu, Jingsong
%Y Anderson, Adam
%Y Gordin, Shai
%Y Li, Bin
%Y Liu, Yudong
%Y Passarotti, Marco C.
%Y Sprugnoli, Rachele
%S Proceedings of the Second Workshop on Ancient Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C The Albuquerque Convention Center, Laguna
%@ 979-8-89176-235-0
%F zheng-yu-2025-incorporating
%X This paper proposes a machine translation approach for Tangut–Chinese using a large language model (LLM) enhanced with lexical knowledge. We fine-tune a Qwen-based LLM using Tangut–Chinese parallel corpora and dictionary definitions. Experimental results demonstrate that incorporating single-character dictionary definitions leads to the best BLEU-4 score of 72.33 for literal translation. Additionally, applying a chain-of-thought prompting strategy significantly boosts free translation performance to 64.20. The model also exhibits strong few-shot learning abilities, with performance improving as the training dataset size increases. Our approach effectively translates both simple and complex Tangut sentences, offering a robust solution for low-resource language translation and contributing to the digital preservation of Tangut texts.
%R 10.18653/v1/2025.alp-1.16
%U https://aclanthology.org/2025.alp-1.16/
%U https://doi.org/10.18653/v1/2025.alp-1.16
%P 127-136
Markdown (Informal)
[Incorporating Lexicon-Aligned Prompting in Large Language Model for Tangut–Chinese Translation](https://aclanthology.org/2025.alp-1.16/) (Zheng & Yu, ALP 2025)
ACL