Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels
Zixia Jia, Junpeng Li, Shichuan Zhang, Anji Liu, Zilong Zheng
Abstract
Traditional supervised learning heavily relies on human-annotated datasets, especially in data-hungry neural approaches. However, various tasks, especially multi-label tasks like document-level relation extraction, pose challenges in fully manual annotation due to the specific domain knowledge and large class sets. Therefore, we address the multi-label positive-unlabelled learning (MLPUL) problem, where only a subset of positive classes is annotated. We propose Mixture Learner for Partially Annotated Classification (MLPAC), an RL-based framework combining the exploration ability of reinforcement learning and the exploitation ability of supervised learning. Experimental results across various tasks, including document-level relation extraction, multi-label image classification, and binary PU learning, demonstrate the generalization and effectiveness of our framework.- Anthology ID:
- 2024.acl-long.731
- Original:
- 2024.acl-long.731v1
- Version 2:
- 2024.acl-long.731v2
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13553–13569
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.731
- DOI:
- 10.18653/v1/2024.acl-long.731
- Cite (ACL):
- Zixia Jia, Junpeng Li, Shichuan Zhang, Anji Liu, and Zilong Zheng. 2024. Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13553–13569, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels (Jia et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.acl-long.731.pdf