Acquiring synonymous attribute phrases for named entities via online encyclopedia  

作　　者：伍大勇 Zhao Shiqi Liu Ting 

机构地区：[1]School of Computer Science and Technology,Harbin Institute of Technology [2]SBaidu.com Inc.

出　　处：《High Technology Letters》2013年第4期398-405,共8页高技术通讯（英文版）

基　　金：Supported by the National High Technology Research and Development Programme of China(No.2008AA01Z144);the National NaturalScience Foundation of China(No.61073126,61073129)

摘　　要：In this work,an approach is proposed to acquire synonymous attribute phrases of named entities(NEs) from an online encyclopedia.Synonymous attribute phrases are the phrases that express the same attribute with different surface forms for a class of NEs.Specifically,the proposed approach is composed of three stages.Firstly,the entries related to a given NE class are automatically selected from an online encyclopedia.Secondly,attribute phrases are extracted based on the statistics of phrase frequency.Thirdly,synonymous attributes are identified in a pairwise manner through a classification framework combining multiple features.The proposed approach is applied on Baidu Baike,a Chinese online encyclopedia,for four different NE classes.Experimental results show that the approach obtains an average precision of 74%and an average F-value of 65%for the four NE classes.In particular,thousands of synonymous attribute phrase pairs are acquired for each class,which demonstrates the effectiveness of the proposed approach.In this work,an approach is proposed to acquire synonymous attribute phrases of named entities （NEs） from an online encyclopedia.Synonymous attribute phrases are the phrases that express the same attribute with different surface forms for a class of NEs.Specifically,the proposed approach is composed of three stages.Firstly,the entries related to a given NE class are automatically selected from an online encyclopedia.Secondly,attribute phrases are extracted based on the statistics of phrase frequency.Thirdly,synonymous attributes are identified in a pairwise manner through a classification framework combining multiple features.The proposed approach is applied on Baidu Baike,a Chinese online encyclopedia,for four different NE classes.Experimental results show that the approach obtains an average precision of 74％ and an average F-value of 65％ for the four NE classes.In particular,thousands of synonymous attribute phrase pairs are acquired for each class,which demonstrates the effectiveness of the proposed approach.

关 键 词：attribute phrase named entity （NE） synonymous attribute online encyclopedia 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]