Simple Tagging System with RoBERTa for Ancient Chinese

Binghao Tang, Boda Lin, Si Li


Abstract
This paper describes the system submitted for the EvaHan 2022 Shared Task on word segmentation and part-of-speech tagging for Ancient Chinese. Our system is based on the pre-trained language model SIKU-RoBERTa and the simple tagging layers. Our system significantly outperforms the official baselines in the released test sets and shows the effectiveness.
Anthology ID:
2022.lt4hala-1.24
Volume:
Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Rachele Sprugnoli, Marco Passarotti
Venue:
LT4HALA
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
159–163
Language:
URL:
https://aclanthology.org/2022.lt4hala-1.24
DOI:
Bibkey:
Cite (ACL):
Binghao Tang, Boda Lin, and Si Li. 2022. Simple Tagging System with RoBERTa for Ancient Chinese. In Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages, pages 159–163, Marseille, France. European Language Resources Association.
Cite (Informal):
Simple Tagging System with RoBERTa for Ancient Chinese (Tang et al., LT4HALA 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lt4hala-1.24.pdf