A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling
Wang, Ye, Pan, Huazheng, Zhang, Tao, Wu, Wen, Hu, Wenxin
–arXiv.org Artificial Intelligence
The goal of document-level relation extraction (RE) is to identify relations between entities that span multiple sentences. Recently, incomplete labeling in document-level RE has received increasing attention, and some studies have used methods such as positive-unlabeled learning to tackle this issue, but there is still a lot of room for improvement. Motivated by this, we propose a positive-augmentation and positive-mixup positive-unlabeled metric learning framework (P3M). Specifically, we formulate document-level RE as a metric learning problem. We aim to pull the distance closer between entity pair embedding and their corresponding relation embedding, while pushing it farther away from the none-class relation embedding. Additionally, we adapt the positive-unlabeled learning to this loss objective. In order to improve the generalizability of the model, we use dropout to augment positive samples and propose a positive-none-class mixup method. Extensive experiments show that P3M improves the F1 score by approximately 4-10 points in document-level RE with incomplete labeling, and achieves state-of-the-art results in fully labeled scenarios. Furthermore, P3M has also demonstrated robustness to prior estimation bias in incomplete labeled scenarios.
arXiv.org Artificial Intelligence
Jun-26-2023
- Country:
- North America
- Dominican Republic (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- New York > New York County
- New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > San Francisco County
- San Francisco (0.04)
- Washington > King County
- Europe
- Germany (0.04)
- Belgium (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Italy > Tuscany
- Florence (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- France
- Provence-Alpes-Côte d'Azur > Bouches-du-Rhône
- Marseille (0.04)
- Hauts-de-France > Nord
- Lille (0.04)
- Provence-Alpes-Côte d'Azur > Bouches-du-Rhône
- Asia
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- China
- Middle East > UAE
- North America
- Genre:
- Research Report (1.00)
- Industry:
- Education (0.34)
- Technology: