Abstract
Multi-task Learning methods have achieved great progress in text classification. However, existing methods assume that multi-task text classification problems are convex multiobjective optimization problems, which is unrealistic in real-world applications. To address this issue, this paper presents a novel Tchebycheff procedure to optimize the multi-task classification problems without convex assumption. The extensive experiments back up our theoretical analysis and validate the superiority of our proposals.- Anthology ID:
- 2020.acl-main.388
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4217–4226
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.388
- DOI:
- 10.18653/v1/2020.acl-main.388
- Cite (ACL):
- Yuren Mao, Shuang Yun, Weiwei Liu, and Bo Du. 2020. Tchebycheff Procedure for Multi-task Text Classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4217–4226, Online. Association for Computational Linguistics.
- Cite (Informal):
- Tchebycheff Procedure for Multi-task Text Classification (Mao et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.388.pdf