Entity and relation extraction is an indispensable part of domain knowledge graph construction,which can serve relevant knowledge needs in a specific domain,such as providing support for product research,sales,risk control,and domain hotspot analysis.The existing entity and relation extraction methods that depend on pretrained models have shown promising performance on open datasets.However,the performance of these methods degrades when they face domain-specific datasets.Entity extraction models treat characters as basic semantic units while ignoring known character dependency in specific domains.Relation extraction is based on the hypothesis that the relations hidden in sentences are unified,thereby neglecting that relations may be diverse in different entity tuples.To address the problems above,this paper first introduced prior knowledge composed of domain dictio-naries to enhance characters'dependence.Second,domain rules were built to eliminate noise in entity relations and promote potential entity relation extraction.Finally,exper-iments were designed to verify the effectiveness of our proposed methods.Experimental results on two domains,including laser industry and unmanned ship,showed the superiority of our methods.The Fl value on laser industry entity,unmanned ship entity,laser industry relation,and unmanned ship relation datasets is improved by+1％,+6％,+2％,and+1％,respectively.In addition,the extraction accuracy of entity relation triplet reaches 83％and 76％on laser industry entity pair and unmanned ship entity pair datasets,respectively.

Xinzhi WANG;Jiahao LI;Ze ZHENG;Yudong CHANG;Min ZHU

School of Computer Engineering and Science,Shanghai University,Shanghai 200444,China;Baidu(China)Co.,Ltd.,Beijing 100085,China;The Sixth Medical Center of PLA General Hospital,Beijing 100048,China

工程管理前沿（英文版）

[1]Xinzhi WANG;Jiahao LI;Ze ZHENG;Yudong CHANG;Min ZHU-.Entity and relation extraction with rule-guided dictionary as domain knowledge)[J].工程管理前沿（英文版）,2022(04):610-622

tuples,dictio,naries,by+1,and+1

Entity,extraction,guided,dictionary,knowledge,indispensable,part,graph,construction,which,can,serve,relevant,needs,specific,such,providing,support,product,research,sales,risk,control,hotspot,analysis,existing,entity,methods,that,pretrained,models,have,shown,promising,performance,open,datasets,However,these,degrades,when,they,face,treat,characters,basic,semantic,units,while,ignoring,known,dependency,domains,Relation,hypothesis,relations,hidden,sentences,are,unified,thereby,neglecting,may,be,diverse,different,To,address,problems,above,this,paper,first,introduced,prior,composed,enhance,dependence,Second,rules,were,built,eliminate,noise,promote,potential,Finally,exper,iments,designed,verify,effectiveness,our,proposed,Experimental,results,two,including,laser,industry,unmanned,ship,showed,superiority,Fl,value,improved,+6,+2,respectively,In,addition,accuracy,triplet,reaches,pair

0.527805