Abstract
This paper describes our approach for Subtask 1 of Task 3 at SemEval-2023. In this subtask, task participants were asked to classify multilingual news articles for one of three classes: Reporting, Opinion Piece or Satire. By training an AdapterFusion layer composing the task-adapters from different languages, we successfully combine the language-exclusive knowledge and show that this improves the results in nearly all cases, including in zero-shot scenarios.- Anthology ID:
- 2023.semeval-1.162
- 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:
- 1166–1171
- Language:
- URL:
- https://aclanthology.org/2023.semeval-1.162
- DOI:
- 10.18653/v1/2023.semeval-1.162
- Cite (ACL):
- Fabian Billert and Stefan Conrad. 2023. HHU at SemEval-2023 Task 3: An Adapter-based Approach for News Genre Classification. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1166–1171, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- HHU at SemEval-2023 Task 3: An Adapter-based Approach for News Genre Classification (Billert & Conrad, SemEval 2023)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2023.semeval-1.162.pdf