Deep Ranking Based Cost-sensitive Multi-label Learning for Distant Supervision Relation Extraction

Abstract

Knowledge base provides a potential way to improve the intelligence of information retrieval (IR) systems, for that knowledge base has numerous relations between entities which can help the IR systems to conduct inference from one entity to another entity. Relation extraction is one of the fundamental techniques to construct a knowledge base. Distant supervision is a semi-supervised learning method for relation extraction which learns with labeled and unlabeled data. However, this approach suffers the problem of relation overlapping in which one entity tuple may have multiple relation facts. We believe that relation types can have latent connections, which we call class ties, and can be exploited to enhance relation extraction. However, this property between relation classes has not been fully explored before. In this paper, to exploit class ties between relations to improve relation extraction, we propose a general ranking based multi-label learning framework combined with convolutional neural networks, in which ranking based loss functions with regularization technique are introduced to learn the latent connections between relations. Furthermore, to deal with the problem of class imbalance in distant supervision relation extraction, we further adopt cost-sensitive learning to rescale the costs from the positive and negative labels. Extensive experiments on a widely used dataset show the effectiveness of our model to exploit class ties and to relieve class imbalance problem.

arXiv commentPreprint submitted to Journal of Information Processing and Management. arXiv admin note: text overlap with arXiv:1612.07602

References in corpus (8)

• Multi-Instance Multi-Label Learning
• Reinforcement Learning for Relation Classification from Noisy Data
• Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
• Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions
• Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training
• Incorporating Relation Paths in Neural Relation Extraction
• Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach
• Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization