@inproceedings{huang-2024-ancient,
title = "{A}ncient {C}hinese Punctuation via In-Context Learning",
author = "Huang, Jie",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lt4hala-1.33",
pages = "261--265",
abstract = "EvaHan2024 focuses on sentence punctuation in ancient Chinese. Xunzi large language base model, which is specifically trained for ancient Chinese processing, is advised in the campaign. In general, we adopted the in-context learning (ICL) paradigm for this task and designed a post-processing scheme to ensure the standardability of final results. When constructing ICL prompts, we did feature extraction by LLM QA and selected demonstrations based on non-parametric metrics. We used Xunzi in two stages and neither did further training, so the model was generic and other fundamental abilities remained unaffected. Moreover, newly acquired training data can be directly utilized after identical feature extraction, showcasing the scalability of our system. As for the result, we achieved an F1-score of 67.7{\%} on a complex test dataset consisting of multiple types of documents and 77.98{\%} on Zuozhuan data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-2024-ancient">
<titleInfo>
<title>Ancient Chinese Punctuation via In-Context Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>EvaHan2024 focuses on sentence punctuation in ancient Chinese. Xunzi large language base model, which is specifically trained for ancient Chinese processing, is advised in the campaign. In general, we adopted the in-context learning (ICL) paradigm for this task and designed a post-processing scheme to ensure the standardability of final results. When constructing ICL prompts, we did feature extraction by LLM QA and selected demonstrations based on non-parametric metrics. We used Xunzi in two stages and neither did further training, so the model was generic and other fundamental abilities remained unaffected. Moreover, newly acquired training data can be directly utilized after identical feature extraction, showcasing the scalability of our system. As for the result, we achieved an F1-score of 67.7% on a complex test dataset consisting of multiple types of documents and 77.98% on Zuozhuan data.</abstract>
<identifier type="citekey">huang-2024-ancient</identifier>
<location>
<url>https://aclanthology.org/2024.lt4hala-1.33</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>261</start>
<end>265</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ancient Chinese Punctuation via In-Context Learning
%A Huang, Jie
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F huang-2024-ancient
%X EvaHan2024 focuses on sentence punctuation in ancient Chinese. Xunzi large language base model, which is specifically trained for ancient Chinese processing, is advised in the campaign. In general, we adopted the in-context learning (ICL) paradigm for this task and designed a post-processing scheme to ensure the standardability of final results. When constructing ICL prompts, we did feature extraction by LLM QA and selected demonstrations based on non-parametric metrics. We used Xunzi in two stages and neither did further training, so the model was generic and other fundamental abilities remained unaffected. Moreover, newly acquired training data can be directly utilized after identical feature extraction, showcasing the scalability of our system. As for the result, we achieved an F1-score of 67.7% on a complex test dataset consisting of multiple types of documents and 77.98% on Zuozhuan data.
%U https://aclanthology.org/2024.lt4hala-1.33
%P 261-265
Markdown (Informal)
[Ancient Chinese Punctuation via In-Context Learning](https://aclanthology.org/2024.lt4hala-1.33) (Huang, LT4HALA-WS 2024)
ACL