System Report for CCL23-Eval Task 7: Chinese Grammatical Error Diagnosis Based on Model Fusion

Yanmei Ma, Laiqi Wang, Zhenghua Chen, Yanran Zhou, Ya Han, Jie Zhang


Abstract
“The purpose of the Chinese Grammatical Error Diagnosis task is to identify the positions andtypes of grammar errors in Chinese texts. In Track 2 of CCL2023-CLTC, Chinese grammarerrors are classified into four categories: Redundant Words, Missing Words, Word Selection, andWord Ordering Errors. We conducted data filtering, model research, and model fine-tuning insequence. Then, we performed weighted fusion of models based on perplexity calculations andintroduced various post-processing strategies. As a result, the performance of the model on thetest set, measured by COM, reached 49.12.”
Anthology ID:
2023.ccl-3.28
Volume:
Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
Month:
August
Year:
2023
Address:
Harbin, China
Editors:
Maosong Sun, Bing Qin, Xipeng Qiu, Jing Jiang, Xianpei Han
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
250–261
Language:
English
URL:
https://aclanthology.org/2023.ccl-3.28
DOI:
Bibkey:
Cite (ACL):
Yanmei Ma, Laiqi Wang, Zhenghua Chen, Yanran Zhou, Ya Han, and Jie Zhang. 2023. System Report for CCL23-Eval Task 7: Chinese Grammatical Error Diagnosis Based on Model Fusion. In Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations), pages 250–261, Harbin, China. Chinese Information Processing Society of China.
Cite (Informal):
System Report for CCL23-Eval Task 7: Chinese Grammatical Error Diagnosis Based on Model Fusion (Ma et al., CCL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.ccl-3.28.pdf