基于对比学习与梯度惩罚的实体关系联合抽取模型

Entity-Relation Joint Extraction Model Based on Contrastive Learning and Gradient Penalty

针对使用全局指针网络进行实体关系抽取时特征信息不明显的实体关系类型数据稀疏问题,以及数据中存在的类别不平衡和错误标注问题,提出一种基于对比学习和梯度惩罚方法并使用改进的RoBERTa预训练模型的实体关系联合抽取模型,在阿里天池中文医疗信息处理评测基准数据集CBLUE2.0上进行实验的结果表明,该模型相比全局指针网络效果更优,能更有效完成复杂数据的实体关系抽取.

Aiming at the problem of sparse entity relationship type data with unclear feature information when using global pointer networks for entity relationship extraction,as well as the problem of class imbalance and incorrect labeling in the data,we proposed a entity-relation joint extraction model based on contrastive learning and gradient penalty methods while utilizing an enhanced RoBERTa pre-trained model.Experimental results on the Alibaba Tianchi Chinese medical information processin g benchmark CBLUE2.0 dataset show that this model outperforms the global pointer network,and can more effectively extract entity relationship from complex data.