Jointly Extracting Relations with Class Ties via Effective Deep Ranking
This work addresses relation extraction for natural language processing, offering an incremental improvement by modeling class ties more effectively.
The paper tackles the problem of distantly supervised relation extraction by exploiting class ties between relations for entity tuples, proposing a unified model integrating CNN with ranking loss functions and addressing class imbalance. The model achieves state-of-the-art performance, significantly outperforming baselines on a widely used dataset.
Connections between relations in relation extraction, which we call class ties, are common. In distantly supervised scenario, one entity tuple may have multiple relation facts. Exploiting class ties between relations of one entity tuple will be promising for distantly supervised relation extraction. However, previous models are not effective or ignore to model this property. In this work, to effectively leverage class ties, we propose to make joint relation extraction with a unified model that integrates convolutional neural network (CNN) with a general pairwise ranking framework, in which three novel ranking loss functions are introduced. Additionally, an effective method is presented to relieve the severe class imbalance problem from NR (not relation) for model training. Experiments on a widely used dataset show that leveraging class ties will enhance extraction and demonstrate the effectiveness of our model to learn class ties. Our model outperforms the baselines significantly, achieving state-of-the-art performance.