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

## TL;DR

This paper introduces a deep ranking-based multi-label learning framework with cost-sensitive techniques for distant supervision relation extraction, effectively exploiting relation class ties and addressing class imbalance.

## Contribution

It proposes a novel deep learning model that leverages class ties and cost-sensitive learning to improve relation extraction from distant supervision data.

## Key findings

- Model outperforms existing methods on benchmark datasets.
- Effectively exploits latent relation class connections.
- Reduces impact of class imbalance in 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.