Ancient Chinese Sentence Segmentation and Punctuation on Xunzi LLM

Shitu Huo, Wenhui Chen


Abstract
This paper describes the system submitted for the EvaHan 2024 Task on ancient Chinese sentence segmentation and punctuation. Our study utillizes the Xunzi large language model as the base model to evaluate the overall performance and the performance by record type. The applied methodologies and the prompts utilized in our study have shown to be helpful and effective in aiding the model’s performance evaluation.
Anthology ID:
2024.lt4hala-1.29
Volume:
Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Rachele Sprugnoli, Marco Passarotti
Venues:
LT4HALA | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
242–245
Language:
URL:
https://aclanthology.org/2024.lt4hala-1.29
DOI:
Bibkey:
Cite (ACL):
Shitu Huo and Wenhui Chen. 2024. Ancient Chinese Sentence Segmentation and Punctuation on Xunzi LLM. In Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024, pages 242–245, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Ancient Chinese Sentence Segmentation and Punctuation on Xunzi LLM (Huo & Chen, LT4HALA-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lt4hala-1.29.pdf