@inproceedings{zhou-etal-2026-acse,
title = "{ACSE}: An Ancient Character Semantic-Aware Embedding for Large Language Models",
author = "Zhou, Zhihan and
Shi, Daqian and
Shi, Lida and
Song, Rui and
Qiu, Peiqiang and
Diao, Xiaolei and
Xu, Hao",
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.437/",
pages = "9000--9012",
ISBN = "979-8-89176-395-1",
abstract = "Research on ancient Chinese language is of great significance for tracing Chinese history and civilization. In the field of large language models, studies on the pre-Qin excavated documents such as Oracle Bone Inscriptions, Bronze Inscriptions, and Bamboo Book of Chu remain insufficient. This is because these ancient characters have a low level of digitization, training corpora are extremely scarce, and they typically contain complex and rich semantic information. Therefore, we propose an ancient character semantic-aware embedding for large language models. This embedding integrates both the glyph and lexicality of ancient characters and maps them to the modern Chinese semantic space. We also design a two-stage method for lightweight and parameter-efficient training of the embedding. Finally, we conduct extensive experiments on excavated documents from the pre-Qin period, and the results demonstrate the effectiveness of our approach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2026-acse">
<titleInfo>
<title>ACSE: An Ancient Character Semantic-Aware Embedding for Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daqian</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lida</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiqiang</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaolei</namePart>
<namePart type="family">Diao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Xu</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>Research on ancient Chinese language is of great significance for tracing Chinese history and civilization. In the field of large language models, studies on the pre-Qin excavated documents such as Oracle Bone Inscriptions, Bronze Inscriptions, and Bamboo Book of Chu remain insufficient. This is because these ancient characters have a low level of digitization, training corpora are extremely scarce, and they typically contain complex and rich semantic information. Therefore, we propose an ancient character semantic-aware embedding for large language models. This embedding integrates both the glyph and lexicality of ancient characters and maps them to the modern Chinese semantic space. We also design a two-stage method for lightweight and parameter-efficient training of the embedding. Finally, we conduct extensive experiments on excavated documents from the pre-Qin period, and the results demonstrate the effectiveness of our approach.</abstract>
<identifier type="citekey">zhou-etal-2026-acse</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.437/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>9000</start>
<end>9012</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ACSE: An Ancient Character Semantic-Aware Embedding for Large Language Models
%A Zhou, Zhihan
%A Shi, Daqian
%A Shi, Lida
%A Song, Rui
%A Qiu, Peiqiang
%A Diao, Xiaolei
%A Xu, Hao
%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 zhou-etal-2026-acse
%X Research on ancient Chinese language is of great significance for tracing Chinese history and civilization. In the field of large language models, studies on the pre-Qin excavated documents such as Oracle Bone Inscriptions, Bronze Inscriptions, and Bamboo Book of Chu remain insufficient. This is because these ancient characters have a low level of digitization, training corpora are extremely scarce, and they typically contain complex and rich semantic information. Therefore, we propose an ancient character semantic-aware embedding for large language models. This embedding integrates both the glyph and lexicality of ancient characters and maps them to the modern Chinese semantic space. We also design a two-stage method for lightweight and parameter-efficient training of the embedding. Finally, we conduct extensive experiments on excavated documents from the pre-Qin period, and the results demonstrate the effectiveness of our approach.
%U https://aclanthology.org/2026.findings-acl.437/
%P 9000-9012
Markdown (Informal)
[ACSE: An Ancient Character Semantic-Aware Embedding for Large Language Models](https://aclanthology.org/2026.findings-acl.437/) (Zhou et al., Findings 2026)
ACL
- Zhihan Zhou, Daqian Shi, Lida Shi, Rui Song, Peiqiang Qiu, Xiaolei Diao, and Hao Xu. 2026. ACSE: An Ancient Character Semantic-Aware Embedding for Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2026, pages 9000–9012, San Diego, California, United States. Association for Computational Linguistics.