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

TL;DR

This paper introduces a neural noise converter and a conditional optimal selector to improve the accuracy of distantly supervised relation extraction by effectively handling noisy labels and making better prediction decisions.

Contribution

It proposes a novel neural noise converter and a conditional optimal selector to address noise issues in distantly supervised relation extraction.

Findings

Significant improvement over baseline methods on a widely used dataset.

Effective reduction of noise impact in relation extraction.

Enhanced prediction accuracy for entity pairs despite noisy data.

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.