Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction
Kailong Hao, Botao Yu, Wei Ping Hu · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · 2021
Distantly supervised relation extraction (RE)automatically aligns unstructured text with relation instances in a knowledge base (KB).Due to the incompleteness of current KBs, sentences implying certain relations may be annotated as N/A instances, which causes the socalled false negative (FN) problem.Current RE methods usually overlook this problem, inducing improper biases in both training and testing procedures.To address this issue, we propose a two-stage approach.First, it finds out possible FN samples by heuristically leveraging the memory mechanism of deep neural networks.Then, it aligns those unlabeled data with the training data into a unified feature space by adversarial training to assign pseudo labels and further utilize the information contained in them.Experiments on two wildlyused benchmark datasets demonstrate the effectiveness of our approach.