Abstract
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.- Anthology ID:
- D19-1444
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4354–4364
- Language:
- URL:
- https://aclanthology.org/D19-1444
- DOI:
- 10.18653/v1/D19-1444
- Cite (ACL):
- Jiawei Wu, Wenhan Xiong, and William Yang Wang. 2019. Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4354–4364, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification (Wu et al., EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D19-1444.pdf
- Data
- FIGER, RCV1