知识图谱梳理课件

单击此处编辑母版标题样式,单击此处编辑母版文本样式,二级,三级,四级,五级,2020/1/29,#,知识图谱需要的技术,知识图谱需要的技术,知识图谱架构,知识图谱一般架构,:,来源自百度百科,复旦大学知识图谱架构,:,早期知识图谱架构,知识图谱架构知识图谱一般架构:来源自百度百科,知识图谱一般架构,:,来源自百度百科,知识图谱一般架构:来源自百度百科,知识图谱梳理课件,架构讨论,数据检索,预处理,构建关系矩阵网络,图谱参数调整,可视化数据,规范化处理,结果导读,早期知识图谱架构,架构讨论数据检索预处理构建关系矩阵网络图谱参数调整可视化数据,知识,抽取,实体概念抽取,实体概念映射,关系抽取,质量评估,知识抽取实体概念抽取,KDD,2014,Tutorial,on,Constructing,and,Mining,Web-scale,Knowledge,Graphs,New,York,August,24,2014,A,sampler,of,research,problems,Growth:,knowledge,graphs,are,incomplete!,Link,prediction,:,add,relations,Ontology,matching,:,connect,graphs,Knowledge,extraction,:,extract,new,entities,and,relations,from,web/text,Validation:,knowledge,graphs,are,not,always,correct!,Entity,resolution,:,merge,duplicate,entities,split,wrongly,merged,ones,Error,detection,:,remove,false,assertions,Interface:,how,to,make,it,easier,to,access,knowledge?,Semantic,parsing,:,interpret,the,meaning,of,queries,Question,answering,:,compute,answers,using,the,knowledge,graph,Intelligence:,can,AI,emerge,from,knowledge,graphs?,Automatic,reasoning,and,planning,Generalization,and,abstraction,9,KDD 2014 Tutorial on Construct,7,关系抽取,定义,:,常见手段,:,语,义模式匹配频繁模式抽取,基于密度聚类,基于,语义,相似,性,层次主题模型,弱监督,关系抽取定义:,KDD,2014,Tutorial,on,Constructing,and,Mining,Web-scale,Knowledge,Graphs,New,York,August,24,2014,Methods,and,techniques,Supervised,models,Semi-supervised,models,Distant,supervision,2.,Entity,resolution,Single,entity,methods,Relational,methods,3.,Link,prediction,Rule-based,methods,Probabilistic,models,Factorization,methods,Embedding,models,80,Not in this tutorial:,Entity classification,Group/expert detection,Ontology alignment,Object ranking,1.Relation extraction:,KDD 2014 Tutorial on Construct,9,KDD,2014,Tutorial,on,Constructing,and,Mining,Web-scale,Knowledge,Graphs,New,York,August,24,2014,Extracting,semantic,relations,between,sets,of,grounded,entities,Numerous,variants:,Undefined,vs,pre-determined,set,of,relations,Binary,vs,n-ary,relations,facet,discovery,Extracting,temporal,information,Supervision:,fully,un,semi,distant,-supervision,Cues,used:,only,lexical,vs,full,linguistic,features,82,Relation,Extraction,Kobe,Bryant,LA,Lakers,playFor,the,franchise,player,of,once,again,saved,man,of,the,match,for,the,Lakers”,his,team”,Los,Angeles”,“Kobe Bryant,“Kobe,“Kobe Bryant,?,KDD 2014 Tutorial on Construct,10,KDD,2014,Tutorial,on,Constructing,and,Mining,Web-scale,Knowledge,Graphs,New,York,August,24,2014,Supervised,relation,extraction,Sentence-level,labels,of,relation,mentions,Apple,CEO,Steve,Jobs,said.,=,(SteveJobs,CEO,Apple),Steve,Jobs,said,that,Apple,will.,=,NIL,Traditional,relation,extraction,datasets,ACE,2004,MUC-7,Biomedical,datasets,(e.g,BioNLP,clallenges),Learn,classifiers,from,+/-,examples,Typical,features:,context,words,+,POS,dependency,path,between,entities,named,entity,tags,token/parse-path/entity,distance,83,KDD 2014 Tutorial on Construct,11,KDD,2014,Tutorial,on,Constructing,and,Mining,Web-scale,Knowledge,Graphs,New,York,August,24,2014,Semi-supervised,relation,extraction,Generic,algorithm(,遗传算法,),1.,2.,3.,4.,5.,Start,with,seed,triples,/,golden,seed,patterns,Extract,patterns,that,match,seed,triples/patterns,Take,the,top-k,extracted,patterns/triples,Add,to,seed,patterns/triples,Go,to,2,Many,published,approaches,in,this,category:,Dual,Iterative,Pattern,Relation,Extractor,Brin,98,Snowball,Agichtein,&,Gravano,00,TextRunner,Banko,et,al.,07,almost,unsupervised,Differ,in,pattern,definition,and,selection,86,KDD 2014 Tutorial on Construct,12,founderOf,KDD,2014,Tutorial,on,Constructing,and,Mining,Web-scale,Knowledge,Graphs,New,York,August,24,2014,Distantly-supervised,relation,extraction,88,Existing,knowledge,base,+,unlabeled,text,generate,examples,Locate,pairs,of,related,entities,in,text,Hypothesizes,that,the,relation,is,expressed,Google,CEO,Larry,Page,announced,that.,Steve,Jobs,has,been,Apple,for,a,while.,Pixar,lost,its,co-founder,Steve,Jobs,.,I,went,to,Paris,France,for,the,summer.,Google,CEO,capitalOf,Larry,Page,France,Apple,CEO,Pixar,Steve,Jobs,founderOfKDD 2014 Tutorial on,13,Distant,supervision:,modeling,hypotheses,Typical,architecture:,1.,Collect,many,pairs,of,entities,co-occurring,in,sentences,from,text,corpus,2.,If,2,entities,participate,in,a,relation,several,hypotheses:,1.,All,sentences,mentioning,them,express,it,Mintz,et,al.,09,“,Barack,Obama,is,the,44th,and,current,President,of,the,US,.”,(BO,employedBy,USA),89,KDD,2014,Tutorial,on,Constructing,and,Mining,Web-scale,Knowledge,Graphs,New,York,August,24,2014,Distant supervision:modeling,14,KDD,2014,Tutorial,on,Constructing,and,Mining,Web-scale,Knowledge,Graphs,New,York,August,24,2014,Sentence-level,features,Lexical:,words,in,between,and,around,mentions,and,their,parts-of-,speech,tags,(conjunctive,form),Syntactic:,dependency,parse,path,between,mentions,along,with,side,nodes,Named,Entity,Tags:,for,the,mentions,Conjunctions,of,the,above,features,Distant,supervision,is,used,on,to,lots,of,data,sparsity,of,conjunctive,forms,not,an,issue,92,KDD 2014 Tutorial on Construct,15,Distant,supervision:,modeling,hypotheses,T