Low-resource Relation Extraction (LRE) aims to extract relation facts from
limited labeled corpora when human annotation is scarce. Existing works either
utilize self-training scheme to generate pseudo labels that will cause the
gradual drift problem, or leverage meta-learning scheme which does not solicit
feedback explicitly. To alleviate selection bias due to the lack of feedback
loops in existing LRE learning paradigms, we developed a Gradient Imitation
Reinforcement Learning method to encourage pseudo label data to imitate the
gradient descent direction on labeled data and bootstrap its optimization
capability through trial and error. We also propose a framework called GradLRE,
which handles two major scenarios in low-resource relation extraction. Besides
the scenario where unlabeled data is sufficient, GradLRE handles the situation
where no unlabeled data is available, by exploiting a contextualized
augmentation method to generate data. Experimental results on two public
datasets demonstrate the effectiveness of GradLRE on low resource relation
extraction when comparing with baselines.

本研究提出两种新的方法 GradLRE 和 Gradient Imitation Reinforcement Learning 来解决低资源关系抽取中缺乏反馈循环和选择偏差等问题，并利用上下文感知增强方法生成数据，在两个公共数据集上的实验结果表明，相比于基线，这些新方法在解决低资源关系抽取问题方面具有明显的优势。