Distant supervised relation extraction based on residual attention  

作　　者：Zhiyun ZHENG Yun LIU Dun LI Xingjin ZHANG 

机构地区：[1]School of Information Engineering,Zhengzhou University,Zhengzhou,450001,China

出　　处：《Frontiers of Computer Science》2022年第6期167-169,共3页中国计算机科学前沿（英文版）

摘　　要：1 Introduction Relation extraction refers to extracting the semantic relation between entities from unstructured text data to form triple data(entity e_(1),entity e_(2),relation r)that is easy to for computer processing.Distant Supervised Relation Extraction(DSRE)[1]obtains relation triples by the heuristic alignment between the knowledge base and large-scale text.For example,if the relation between"Steve Jobs"and"Apple"in the knowledge base is"Founder",the sentences containing these two entities in the text will be used as examples of the relation"Founder"to train the relation extraction model.

关 键 词：RELATION SEMANTIC BASE 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]