关联数据冲突消解方法研究
|
摘要
关联数据源的独立自治特点导致不同数据源对真实世界相同实体可能提供冲突的描述,限制了关联数据的可用性。对关联数据进行冲突消解成为近年来语义网研究领域的热点问题。针对冲突在RDF三元组中出现的位置,对主语、谓词、宾语的冲突消解研究现状进行了综述。其中,对于主语冲突消解(也称实体共指消解),分析了基于语义等价推理与基于属性值相似度两类典型方法;对于谓词冲突消解(也称本体匹配),介绍了基于相似度、基于结构匹配以及基于实例三类方法;对于宾语冲突消解,介绍了冲突避免和真值发现两类方法。目前,国内外在关联数据主语与谓词的冲突消解问题已开展了大量研究,但对宾语冲突消解的研究还比较薄弱。文中总结了宾语冲突消解在多值冲突、时变数据、数据拷贝等方面的挑战,并对未来的研究工作进行了展望。
Different linked data sources may provide conflicting descriptions for the same real-world entities due to the autonomy of the sources,which limits the availability of linked data. Therefore,to resolve the conflicts in linked data has received extensive attention in semantic web research. According to the three elements of RDF( resource description framework) triples,we survey the research work on conflict resolution of subject,predicate,and object in linked data respectively. For the subject conflicts resolution( also called resolving entity coreference),we analyze two typical methods which are based on the semantic inference and the similarity of attribute values respectively.For the predicate conflicts resolution(also called ontology alignment),we introduce the similarity-based,structural matching-based and instance-based methods. For the object conflicts resolution,we present the conflict-ignoring methods and the truth discovery methods. At present,extensive research has been conducted on the conflict resolution of subject and predicate,but the research on object conflict resolution is still weak. In this paper,we summarize the challenges of object conflict resolution,including multi-value conflicts,time-varying data,data replication,and discuss the future research work.
Different linked data sources may provide conflicting descriptions for the same real-world entities due to the autonomy of the sources,which limits the availability of linked data. Therefore,to resolve the conflicts in linked data has received extensive attention in semantic web research. According to the three elements of RDF( resource description framework) triples,we survey the research work on conflict resolution of subject,predicate,and object in linked data respectively. For the subject conflicts resolution( also called resolving entity coreference),we analyze two typical methods which are based on the semantic inference and the similarity of attribute values respectively.For the predicate conflicts resolution(also called ontology alignment),we introduce the similarity-based,structural matching-based and instance-based methods. For the object conflicts resolution,we present the conflict-ignoring methods and the truth discovery methods. At present,extensive research has been conducted on the conflict resolution of subject and predicate,but the research on object conflict resolution is still weak. In this paper,we summarize the challenges of object conflict resolution,including multi-value conflicts,time-varying data,data replication,and discuss the future research work.
引文
[1] LIAN Xiang,CHEN Lei,WANG Guoren. Quality-aware subgraph matching over inconsistent probabilistic graph databases[J]. IEEE Transactions on Know ledge and Data Engineering,2016,28(6):1560-1574.
[2] LIU Wenqiang,LIU Jun,DUAN Haimeng,et al. Exploiting source-object netw orks to resolve object conflicts in linked data[C]//European semantic w eb conference.[s. l.]:Springer,2017:53-67.
[3]胡伟,柏文阳,瞿裕忠.语义Web中对象共指的消解研究[J].软件学报,2012,23(7):1729-1744.
[4] HALPIN H,HAYES P J,MCCUSKER J P,et al.When owl:sameas isn’t the same:an analysis of identity in linked data[C]//Proceedings of the 9th international semantic web conference.[s.l.]:Springer,2010:305-320.
[5] NIKOLOV A,UREN V,MOTTA E,et al.Refining instance coreferencing results using belief propagation[C]//Asian semantic w eb conference.Berlin:Springer,2008:405-419.
[6] WANG Shenghui,ENGLEBIENNE G,SCHLOBACH S.Learning concept mappings from instance similarity[C]//Proceedings of the 7th international conference on the semantic w eb.Karlsruhe,Germany:Springer,2008:339-355.
[7] HU Wei,CHEN Jianfeng,QU Yuzhong.A self-training approach for resolving object coreference on the semantic w eb[C]//Proceedings of the 20th international conference on w orld w ide w eb.Hyderabad,India:ACM,2011:87-96.
[8] SCHADD F C,ROOS N.Word-sense disambiguation for ontology mapping:concept disambiguation using virtual documents and information retrieval techniques[J]. Journal on Data Semantics,2015,4(3):167-186.
[9]潘有能,刘朝霞.基于WordNet的关联数据本体映射研究[J].情报杂志,2013,32(2):99-102.
[10] XIANG Chuncheng,CHANG Baobao,SUI Zhifang.An ontology matching approach based on affinity-preserving random w alks[C]//Proceedings of the 24th international conference on artificial intelligence. Buenos Aires,Argentina:AAAI Press,2015:1471-1478.
[11]王颖,刘群,王慧强,等.一种基于RDF图的本体匹配方法[J].计算机应用,2008,28(2):460-462.
[12] LI Juanzi,TANG Jie,LI Yi,et al.RiMOM:a dynamic multistrategy ontology alignment framew ork[J]. IEEE Transactions on Know ledge and Data Engineering,2009,21(8):1218-1232.
[13] WANG H,FANG Z,ZHANG L,et al. Effective online know ledge graph fusion[C]//International semantic w eb conference.[s.l.]:Springer,2015:286-302.
[14]蒋湛,姚晓明,林兰芬.基于特征自适应的本体映射方法[J].浙江大学学报:工学版,2014,48(1):76-84.
[15] NOLLE A,MEILICKE C,CHEKOL M W,et al.Schemabased debugging of federated data sources[C]//European conference on artificial intelligence.[s. l.]:Springer,2016:381-389.
[16] DONG X L,BERTI-EQUILLE L,SRIVASTAVA D. Integrating conflicting data:the role of source dependence[J].Proceedings of the VLDB Endow ment,2009,2(1):550-561.
[17]马如霞,孟小峰.基于数据源分类可信性的真值发现方法研究[J].计算机研究与发展,2015,52(9):1931-1940.
[18] LI Qi,LI Yaliang,GAO Jing,et al.Resolving conflicts in heterogeneous data by truth discovery and source reliability estimation[C]//Proceedings of the 2014 ACM SIGM OD international conference on management of data.Snow bird,Utah,USA:ACM,2014:1187-1198.
[19]陈超,申德荣,寇月,等.异构数据联合式的真值发现算法[J].东北大学学报:自然科学版,2017,38(10):1373-1376.
[20] ZHAO Bo,RUBINSTEIN B I P,GEMMELL J,et al. A Bayesian approach to discovering truth from conflicting sources for data integration[J]. Proceedings of the VLDB Endow ment,2012,5(6):550-561.
[2] LIU Wenqiang,LIU Jun,DUAN Haimeng,et al. Exploiting source-object netw orks to resolve object conflicts in linked data[C]//European semantic w eb conference.[s. l.]:Springer,2017:53-67.
[3]胡伟,柏文阳,瞿裕忠.语义Web中对象共指的消解研究[J].软件学报,2012,23(7):1729-1744.
[4] HALPIN H,HAYES P J,MCCUSKER J P,et al.When owl:sameas isn’t the same:an analysis of identity in linked data[C]//Proceedings of the 9th international semantic web conference.[s.l.]:Springer,2010:305-320.
[5] NIKOLOV A,UREN V,MOTTA E,et al.Refining instance coreferencing results using belief propagation[C]//Asian semantic w eb conference.Berlin:Springer,2008:405-419.
[6] WANG Shenghui,ENGLEBIENNE G,SCHLOBACH S.Learning concept mappings from instance similarity[C]//Proceedings of the 7th international conference on the semantic w eb.Karlsruhe,Germany:Springer,2008:339-355.
[7] HU Wei,CHEN Jianfeng,QU Yuzhong.A self-training approach for resolving object coreference on the semantic w eb[C]//Proceedings of the 20th international conference on w orld w ide w eb.Hyderabad,India:ACM,2011:87-96.
[8] SCHADD F C,ROOS N.Word-sense disambiguation for ontology mapping:concept disambiguation using virtual documents and information retrieval techniques[J]. Journal on Data Semantics,2015,4(3):167-186.
[9]潘有能,刘朝霞.基于WordNet的关联数据本体映射研究[J].情报杂志,2013,32(2):99-102.
[10] XIANG Chuncheng,CHANG Baobao,SUI Zhifang.An ontology matching approach based on affinity-preserving random w alks[C]//Proceedings of the 24th international conference on artificial intelligence. Buenos Aires,Argentina:AAAI Press,2015:1471-1478.
[11]王颖,刘群,王慧强,等.一种基于RDF图的本体匹配方法[J].计算机应用,2008,28(2):460-462.
[12] LI Juanzi,TANG Jie,LI Yi,et al.RiMOM:a dynamic multistrategy ontology alignment framew ork[J]. IEEE Transactions on Know ledge and Data Engineering,2009,21(8):1218-1232.
[13] WANG H,FANG Z,ZHANG L,et al. Effective online know ledge graph fusion[C]//International semantic w eb conference.[s.l.]:Springer,2015:286-302.
[14]蒋湛,姚晓明,林兰芬.基于特征自适应的本体映射方法[J].浙江大学学报:工学版,2014,48(1):76-84.
[15] NOLLE A,MEILICKE C,CHEKOL M W,et al.Schemabased debugging of federated data sources[C]//European conference on artificial intelligence.[s. l.]:Springer,2016:381-389.
[16] DONG X L,BERTI-EQUILLE L,SRIVASTAVA D. Integrating conflicting data:the role of source dependence[J].Proceedings of the VLDB Endow ment,2009,2(1):550-561.
[17]马如霞,孟小峰.基于数据源分类可信性的真值发现方法研究[J].计算机研究与发展,2015,52(9):1931-1940.
[18] LI Qi,LI Yaliang,GAO Jing,et al.Resolving conflicts in heterogeneous data by truth discovery and source reliability estimation[C]//Proceedings of the 2014 ACM SIGM OD international conference on management of data.Snow bird,Utah,USA:ACM,2014:1187-1198.
[19]陈超,申德荣,寇月,等.异构数据联合式的真值发现算法[J].东北大学学报:自然科学版,2017,38(10):1373-1376.
[20] ZHAO Bo,RUBINSTEIN B I P,GEMMELL J,et al. A Bayesian approach to discovering truth from conflicting sources for data integration[J]. Proceedings of the VLDB Endow ment,2012,5(6):550-561.