Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction

Abstract

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.

Enhanced Semi-supervised Relation Extraction Based on Label Confusion Learning and Multisource Semantic Aggregation

“…The former [4][5][6][7] requires a lot of annotated data to train models and limits its applicability. The latter [8][9][10] uses Knowledge Bases (KBs) to automatically label the two entities appearing in the same sentence and their KB relationship, thereby alleviating the burden of manual annotation. However, the main challenge with remote supervision is that KB relationships may not always apply to all sentences in RE task, especially if the target relationship cannot be found in the existing KB.…”