arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.04513cs.IR
收藏

基于原型对比学习的连续关系抽取算法

Improving Continual Relation Extraction through Prototypical Contrastive Learning

Chengwei Hu, Deqing Yang, Haoliang Jin, Zhen Chen, Yanghua Xiao

摘要:

连续关系抽取(ContinualRelationExtraction,CRE)是针对新数据的连续迭代到达抽取关系的方法,其主要挑战是旧任务的灾难性遗忘。为了解决这一问题,本文提出了一种新的基于对比学习的连续关系抽取框架,即CRECL,它由一个分类网络和一个原型对比网络组成,实现了CRE的增量类学习。具体而言,在对比网络中,给定实例与存储在存储器模块中的每个候选关系的原型进行对比。这种对比学习策略保证了所有任务的数据分布更具有可区分性,从而进一步减轻了灾难性遗忘。我们的实验结果不仅证明了我们的CRECL的国家的最先进的基线上的两个公共数据集的优势,但也验证了CRECL的对比学习的有效性,提高CRE性能。

英文摘要:

Continual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks. In order to alleviate this critical problem for enhanced CRE performance, we propose a novel Continual Relation Extraction framework with Contrastive Learning, namely CRECL, which is built with a classification network and a prototypical contrastive network to achieve the incremental-class learning of CRE. Specifically, in the contrastive network a given instance is contrasted with the prototype of each candidate relations stored in the memory module. Such contrastive learning scheme ensures the data distributions of all tasks more distinguishable, so as to alleviate the catastrophic forgetting further. Our experiment results not only demonstrate our CRECL's advantage over the state-of-the-art baselines on two public datasets, but also verify the effectiveness of CRECL's contrastive learning on improving CRE performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑