Continual few-shot relation extraction (RE) aims to continuously train a model for new relations with few labeled training data, of which the major challenges are the catastrophic forgetting of old relations and the overfitting caused by data sparsity. In this paper, we propose a new model, namely SCKD, to accomplish the continual few-shot RE task. Specifically, we design serial knowledge distillation to preserve the prior knowledge from previous models and conduct contrastive learning with pseudo samples to keep the representations of samples in different relations sufficiently distinguishable. Our experiments on two benchmark datasets validate the effectiveness of SCKD for continual few-shot RE and its superiority in knowledge transfer and memory utilization over state-of-the-art models.

翻译：持续小样本关系抽取（RE）旨在利用少量标注训练数据持续训练模型以处理新关系，其主要挑战在于旧关系的灾难性遗忘以及数据稀疏导致的过拟合。本文提出了一种新模型SCKD，用于完成持续小样本关系抽取任务。具体而言，我们设计了串行知识蒸馏来保留先前模型中的先验知识，并通过伪样本进行对比学习，以确保不同关系下样本的表征具有充分的区分度。在两个基准数据集上的实验验证了SCKD在持续小样本关系抽取中的有效性，以及其在知识迁移和内存利用方面相较于当前最优模型的优越性。