CoRE: A context-aware relation extraction method for relation completion

Handle URI:
http://hdl.handle.net/10754/563475
Title:
CoRE: A context-aware relation extraction method for relation completion
Authors:
Li, Zhixu; Sharaf, Mohamed Abdel Fattah; Sitbon, Laurianne; Du, Xiaoyong; Zhou, Xiaofang
Abstract:
We identify relation completion (RC) as one recurring problem that is central to the success of novel big data applications such as Entity Reconstruction and Data Enrichment. Given a semantic relation {\cal R}, RC attempts at linking entity pairs between two entity lists under the relation {\cal R}. To accomplish the RC goals, we propose to formulate search queries for each query entity \alpha based on some auxiliary information, so that to detect its target entity \beta from the set of retrieved documents. For instance, a pattern-based method (PaRE) uses extracted patterns as the auxiliary information in formulating search queries. However, high-quality patterns may decrease the probability of finding suitable target entities. As an alternative, we propose CoRE method that uses context terms learned surrounding the expression of a relation as the auxiliary information in formulating queries. The experimental results based on several real-world web data collections demonstrate that CoRE reaches a much higher accuracy than PaRE for the purpose of RC. © 1989-2012 IEEE.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Transactions on Knowledge and Data Engineering
Issue Date:
Apr-2014
DOI:
10.1109/TKDE.2013.148
Type:
Article
ISSN:
10414347
Sponsors:
This research was partially supported by National 863 High-tech Program (Grant No. 2012AA011001) and the Australian Research Council (Grant No. DP120102829). Part of this work has appeared as a short paper in CIKM '11 [18].
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorLi, Zhixuen
dc.contributor.authorSharaf, Mohamed Abdel Fattahen
dc.contributor.authorSitbon, Laurianneen
dc.contributor.authorDu, Xiaoyongen
dc.contributor.authorZhou, Xiaofangen
dc.date.accessioned2015-08-03T11:52:25Zen
dc.date.available2015-08-03T11:52:25Zen
dc.date.issued2014-04en
dc.identifier.issn10414347en
dc.identifier.doi10.1109/TKDE.2013.148en
dc.identifier.urihttp://hdl.handle.net/10754/563475en
dc.description.abstractWe identify relation completion (RC) as one recurring problem that is central to the success of novel big data applications such as Entity Reconstruction and Data Enrichment. Given a semantic relation {\cal R}, RC attempts at linking entity pairs between two entity lists under the relation {\cal R}. To accomplish the RC goals, we propose to formulate search queries for each query entity \alpha based on some auxiliary information, so that to detect its target entity \beta from the set of retrieved documents. For instance, a pattern-based method (PaRE) uses extracted patterns as the auxiliary information in formulating search queries. However, high-quality patterns may decrease the probability of finding suitable target entities. As an alternative, we propose CoRE method that uses context terms learned surrounding the expression of a relation as the auxiliary information in formulating queries. The experimental results based on several real-world web data collections demonstrate that CoRE reaches a much higher accuracy than PaRE for the purpose of RC. © 1989-2012 IEEE.en
dc.description.sponsorshipThis research was partially supported by National 863 High-tech Program (Grant No. 2012AA011001) and the Australian Research Council (Grant No. DP120102829). Part of this work has appeared as a short paper in CIKM '11 [18].en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectContext-aware relation extractionen
dc.subjectRelation completionen
dc.subjectRelation query expansionen
dc.titleCoRE: A context-aware relation extraction method for relation completionen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalIEEE Transactions on Knowledge and Data Engineeringen
dc.contributor.institutionSchool of Information Technology and Electrical Engineering, University of Queensland, Building 78, St Lucia Campus, Brisbane, QLD 4072, Australiaen
dc.contributor.institutionSchool of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Australiaen
dc.contributor.institutionMOE China, School of Information, Renmin University of China, Beijing 100872, Chinaen
dc.contributor.institutionSchool of Information Technology and Electrical Engineering, University of Queensland, Brisbane QLD 4072, Australiaen
dc.contributor.institutionSchool of Computer Science and Technology, Soochow University, Chinaen
kaust.authorLi, Zhixuen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.