Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector

Abstract

Distant supervised relation extraction has been successfully applied to large corpus with thousands of relations. However, the inevitable wrong labeling problem by distant supervision will hurt the performance of relation extraction. In this paper, we propose a method with neural noise converter to alleviate the impact of noisy data, and a conditional optimal selector to make proper prediction. Our noise converter learns the structured transition matrix on logit level and captures the property of distant supervised relation extraction dataset. The conditional optimal selector on the other hand helps to make proper prediction decision of an entity pair even if the group of sentences is overwhelmed by no-relation sentences. We conduct experiments on a widely used dataset and the results show significant improvement over competitive baseline methods.

arXiv commentAccepted to AAAI 2019

References in corpus (4)

• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Classifying Relations by Ranking with Convolutional Neural Networks
• Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
• Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projection