Fine-grained relation extraction with focal multi-task learning  

作　　者：Xinsong ZHANG Tianyi LIU Weijia JIA Pengshuai LI 

机构地区：[1]School of Electronic Information and Electrical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China [2]State Key Lab of IoT for Smart City,University of Macao,Macao 999078,China

出　　处：《Science China(Information Sciences)》2020年第6期225-227,共3页中国科学（信息科学）（英文版）

基　　金：supported by National Basic Research Program of China(973 Project)(Grant No.2015CB352401);National Natural Science Foundation of China(Grant Nos.61532013,61872239);FDCT/0007/2018/A1,DCT-MoST Joint-Project(Grant No.025/2015/AMJ);University of Macao Grants(Grant Nos.MYRG2018-00237-RTO,CPG2018-00032-FST,SRG 2018-00111-FST)。

摘　　要：Dear editor,Relation extraction aims to identify relation facts for pairs of entities in raw texts to construct triplets such as[Arthur Lee,place born,Memphis].To automatically extract relation facts,the distant supervision strategy[1]has been proposed,which assumes that,if there exists a relation between two entities in a known knowledge base.

关 键 词：FINE-GRAINED focal multi-task learning entities 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]