[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

Team QUST at SemEval-2023 Task 3: A Comprehensive Study of Monolingual and Multilingual Approaches for Detecting Online News Genre, Framing and Persuasion Techniques

Ye Jiang


Abstract
This paper describes the participation of team QUST in the SemEval2023 task3. The monolingual models are first evaluated with the under-sampling of the majority classes in the early stage of the task. Then, the pre-trained multilingual model is fine-tuned with a combination of the class weights and the sample weights. Two different fine-tuning strategies, the task-agnostic and the task-dependent, are further investigated. All experiments are conducted under the 10-fold cross-validation, the multilingual approaches are superior to the monolingual ones. The submitted system achieves the second best in Italian and Spanish (zero-shot) in subtask-1.
Anthology ID:
2023.semeval-1.40
Volume:
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Giovanni Da San Martino, Harish Tayyar Madabushi, Ritesh Kumar, Elisa Sartori
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
300–306
Language:
URL:
https://aclanthology.org/2023.semeval-1.40
DOI:
10.18653/v1/2023.semeval-1.40
Bibkey:
Cite (ACL):
Ye Jiang. 2023. Team QUST at SemEval-2023 Task 3: A Comprehensive Study of Monolingual and Multilingual Approaches for Detecting Online News Genre, Framing and Persuasion Techniques. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 300–306, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Team QUST at SemEval-2023 Task 3: A Comprehensive Study of Monolingual and Multilingual Approaches for Detecting Online News Genre, Framing and Persuasion Techniques (Jiang, SemEval 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.semeval-1.40.pdf