计算机科学
关系(数据库)
判别式
保险丝(电气)
数据挖掘
集合(抽象数据类型)
人工智能
机器学习
电气工程
程序设计语言
工程类
作者
Lei Wang,Jianfeng Qu,Tianyu Xu,Zhixu Li,Wei Chen,Jiajie Xu,Lei Zhao
出处
期刊:World Wide Web
[Springer Nature]
日期:2023-07-03
卷期号:26 (5): 3207-3226
标识
DOI:10.1007/s11280-023-01184-w
摘要
Few-shot relation classification is to recognize the semantic relation between an entity pair with very few samples. Prototypical network has proven to be a simple yet effective few-shot learning method for relation extraction. However, under the condition of data scarcity, the relation prototypes we achieve are usually biased compared to the real ones computed from all samples within a relation class. To alleviate this issue, we propose hybrid enhancement-based prototypical networks. In particular, our model contains three main enhancement modules: 1) a query-guided prototype enhancement module using rich interactive information between the support instances and the query instance as guidance to obtain more accurate prototype representations; 2) a query enhancement module to diminish the distribution gap between the query set and the support set; 3) a support enhancement module adopting a pseudo-label strategy to expand the scale of available data. On basis of these modules, we further design a novel prototype attention fusion mechanism to fuse information and compute discriminative relation prototypes for classification. In this way, we hope to obtain unbiased representations closer to our expected prototypes by improving the available data scale and data utilization efficiency. Extensive experimental results on the widely-used FewRel dataset demonstrate the superiority of our proposed model.
科研通智能强力驱动
Strongly Powered by AbleSci AI