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

Authors

  • Shanchan Wu Alibaba Group
  • Kai Fan Alibaba Group
  • Qiong Zhang Alibaba Group

DOI:

https://doi.org/10.1609/aaai.v33i01.33017273

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.

Downloads

Published

2019-07-17

How to Cite

Wu, S., Fan, K., & Zhang, Q. (2019). Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7273-7280. https://doi.org/10.1609/aaai.v33i01.33017273

Issue

Section

AAAI Technical Track: Natural Language Processing