Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector
This work addresses noisy data issues in relation extraction for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackles the wrong labeling problem in distantly supervised relation extraction by proposing a neural noise converter to mitigate noisy data impact and a conditional optimal selector for better predictions, achieving significant improvement over competitive baselines on a widely used dataset.
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.