Abstract
In order to effectively predict the speaker’s informing emotion from text fragments, we propose a transfer learning framework based on the BERT pre-training model through deep semantic feature extraction and cascade structure of dynamic weight linear classifier. In the speaker informing emotion prediction task, a 0.70 F1 score is achieved, illustrating the effectiveness of cross-domain emotion recognition.- Anthology ID:
- 2025.semeval-1.147
- Volume:
- Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
- Month:
- July
- Year:
- 2025
- Address:
- Vienna, Austria
- Editors:
- Sara Rosenthal, Aiala Rosá, Debanjan Ghosh, Marcos Zampieri
- Venues:
- SemEval | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1113–1117
- Language:
- URL:
- https://preview.aclanthology.org/ingest-brigap/2025.semeval-1.147/
- DOI:
- Cite (ACL):
- Zhou Jiang and Dengtao Zhang. 2025. zhouyijiang1 at SemEval-2025 Task 11: A Multi-tag Detection Method based on Pre-training Language Models. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 1113–1117, Vienna, Austria. Association for Computational Linguistics.
- Cite (Informal):
- zhouyijiang1 at SemEval-2025 Task 11: A Multi-tag Detection Method based on Pre-training Language Models (Jiang & Zhang, SemEval 2025)
- PDF:
- https://preview.aclanthology.org/ingest-brigap/2025.semeval-1.147.pdf