Jointly Extracting Relations with Class Ties via Effective Deep Ranking. (arXiv:1612.07602v2 [cs.AI] UPDATED)

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 with a general pairwise ranking framework, in which two novel ranking loss functions are introduced. Additionally, an effective method is presented to relieve the impact of NR (not relation) for model training, which significantly boosts our model performance. Experiments on a widely used dataset show that leveraging class ties will enhance extraction and demonstrate that our model is effective to learn class ties. Our model outperforms baselines significantly, achieving state-of-the-art performance.

from cs.AI updates on arXiv.org http://ift.tt/2i7dI2c
via IFTTT