Relation Detection And Recognition - 上海交通大学计算 .ppt

Relation Detection And Recognition *** *** *** Schema General Description Name Entity Recognition RDR Training Corpus Generate Relation Detection and Recognition Performance Analysis General Description-Algorithm EDR: CRF Character based RDR: SVM Pos is needed General Description-Workflow Schema General Description Name Entity Recognition RDR Training Corpus Generate Relation Detection and Recognition Performance Analysis Name Entity Recognition-Algorithm CRF++ Character based Most naive 北 nb 京 ne １ non 月 non １ non 日 non 讯 non 中 nb 华 nm 全 nm 国 nm 总 nm 工 nm 会 ne 今 non 日 non 发 non Name Entity Recognition-Accuracy nr precious:100% right:88 error:0 nt precious:100% right:36 error:0 ns precious:100% right:56 error:0 180/181 海湾战争 nz 9 22 Schema General Description Name Entity Recognition RDR Training Corpus Generate Relation Detection and Recognition Performance Analysis RDR Training Corpus Generate The vector SVM need: e1.type, e2.type,order, dist, w-2,w-1,w0,w1,w2,t-2,t-1,t0,t1,t2, w-2,w-1,w0,w1,w2,t-2,t-1,t0,t1,t2, relation Exp: 国家环保局局长解振华庄重宣布 国家环保局,2,解振华,1,3,11,NULL,NULL,国家环保局,局,长,局,长,解振华,庄,重,null,null,null,NN,NR,NN,NN,null,VA,DEC,E RDR Training Corpus Generate 1、NLP Pos tag: 国家/NN 环保局/NN 局长/NN 解振华/NR 庄重/VA 宣布：/DEC 2、Compare with Entity: 国家环保局/nt，解振华/nr 3、Find the type front and back null,null,null,NN,NR NN,NN,null,VA,DEC RDR Training Corpus Generate 4、Tag the train corpus by hands 国家环保局,2,解振华,1,3,11,NULL,NULL,国家环保局,局,长,局,长,解振华,庄,重,null,null,null,NN,NR,NN,NN,null,VA,DEC,E RDR Training Corpus Generate Use Assit Program: Tagged Corpus: 602 sentence 3000+relations Schema General Description Name Entity Recognition RDR Training Corpus Generate Relation Detection and Recognition Performance Analysis 概述 将关系识别问题看作多分类问题 输入：实体对向量集X(x1,x2,……xn) 其中 xi (f1, f2, ……fn ) 表示实体对(E1,E2) 输出： xi 所属的类型yi 使用SVM的方法构造分类器 选取合适的特征集来描述实体对，并映射 到高维实数空间，进行分类 SVM 支持向量机