{"id":"https://openalex.org/W2170383858","doi":"https://doi.org/10.1109/skg.2010.38","title":"A Holistic Solution for Duplicate Entity Identification in Deep Web Data Integration","display_name":"A Holistic Solution for Duplicate Entity Identification in Deep Web Data Integration","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2170383858","doi":"https://doi.org/10.1109/skg.2010.38","mag":"2170383858"},"language":"en","primary_location":{"id":"doi:10.1109/skg.2010.38","is_oa":false,"landing_page_url":"https://doi.org/10.1109/skg.2010.38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100319765","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0003-3016-7381"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Institute of Computer Science and Technology, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101010043","display_name":"Xiaofeng Meng","orcid":"https://orcid.org/0000-0002-7889-2120"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Meng","raw_affiliation_strings":["School of Information, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.35551915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"130","issue":null,"first_page":"267","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11363","display_name":"Dental Radiography and Imaging","score":0.9692000150680542,"subfield":{"id":"https://openalex.org/subfields/3504","display_name":"Oral Surgery"},"field":{"id":"https://openalex.org/fields/35","display_name":"Dentistry"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.78419029712677},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.7130733132362366},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.6939177513122559},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6514077186584473},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5733758807182312},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5493577718734741},{"id":"https://openalex.org/keywords/web-mapping","display_name":"Web mapping","score":0.5357095003128052},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.5312457084655762},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5281745791435242},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.5186609029769897},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.5050297379493713},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49117037653923035},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.41246268153190613},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32991164922714233},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.22120574116706848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78419029712677},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.7130733132362366},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.6939177513122559},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6514077186584473},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5733758807182312},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5493577718734741},{"id":"https://openalex.org/C24733836","wikidata":"https://www.wikidata.org/wiki/Q649186","display_name":"Web mapping","level":4,"score":0.5357095003128052},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.5312457084655762},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5281745791435242},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.5186609029769897},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.5050297379493713},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49117037653923035},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.41246268153190613},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32991164922714233},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.22120574116706848},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/skg.2010.38","is_oa":false,"landing_page_url":"https://doi.org/10.1109/skg.2010.38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.649.1701","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.649.1701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://idke.ruc.edu.cn/publications/2010/new-liuwei-SKG2010-A Holistic Solution for Duplicate Entity Identification in Deep Web Data Integration.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W51908901","https://openalex.org/W1485156179","https://openalex.org/W1559390933","https://openalex.org/W1607067400","https://openalex.org/W1612155886","https://openalex.org/W1647671624","https://openalex.org/W1768893245","https://openalex.org/W1969831559","https://openalex.org/W2007682403","https://openalex.org/W2015551056","https://openalex.org/W2034190452","https://openalex.org/W2040925009","https://openalex.org/W2046020929","https://openalex.org/W2052390074","https://openalex.org/W2053539645","https://openalex.org/W2065199439","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2098016092","https://openalex.org/W2101168711","https://openalex.org/W2105484782","https://openalex.org/W2108991785","https://openalex.org/W2111625757","https://openalex.org/W2128341918","https://openalex.org/W2129598390","https://openalex.org/W2135223301","https://openalex.org/W2135326109","https://openalex.org/W2138745909","https://openalex.org/W2143607396","https://openalex.org/W2151023586","https://openalex.org/W2161600801","https://openalex.org/W2164625277","https://openalex.org/W3146259567","https://openalex.org/W4230502578","https://openalex.org/W4232071090","https://openalex.org/W4252421678","https://openalex.org/W6602040338","https://openalex.org/W6628896031","https://openalex.org/W6636915900","https://openalex.org/W6681167186","https://openalex.org/W6683628169"],"related_works":["https://openalex.org/W2182629206","https://openalex.org/W4385950365","https://openalex.org/W2134078223","https://openalex.org/W2330648582","https://openalex.org/W2415191659","https://openalex.org/W2945931694","https://openalex.org/W2183707945","https://openalex.org/W2080799101","https://openalex.org/W2811217915","https://openalex.org/W3174726539"],"abstract_inverted_index":{"The":[0,142],"proliferation":[1],"of":[2,27,49,93],"deep":[3,21,65,127,157],"Web":[4,22,40,66,80,87,100,110,140,158],"offers":[5],"users":[6],"a":[7,17,117],"great":[8],"opportunity":[9],"to":[10,32,64,85,120,132],"search":[11],"high-quality":[12],"information":[13],"from":[14,37],"Web.":[15],"As":[16],"necessary":[18],"step":[19],"in":[20],"data":[23,58,67,159],"integration,":[24],"the":[25,34,38,91,95,122,150],"goal":[26,130],"duplicate":[28,35,73,135],"entity":[29,74,136],"identification":[30],"is":[31,102,131,153],"discover":[33],"records":[36],"integrated":[39],"databases":[41,81,101],"for":[42,98,108,156],"further":[43],"applications(e.g.":[44],"price-comparison":[45],"services).":[46],"However,":[47],"most":[48],"existing":[50],"works":[51],"address":[52,121],"this":[53,113],"issue":[54],"only":[55],"between":[56],"two":[57,78,109,146],"sources,":[59],"which":[60],"are":[61],"not":[62],"practical":[63],"integration":[68],"systems.":[69],"That":[70],"is,":[71],"one":[72,134],"matcher":[75,137],"trained":[76],"over":[77,138],"specific":[79],"cannot":[82],"be":[83],"applied":[84],"other":[86],"databases.":[88,111,141],"In":[89,112],"addition,":[90],"cost":[92],"preparing":[94],"training":[96],"set":[97],"n":[99],"C_n^2":[103],"times":[104],"higher":[105],"than":[106],"that":[107,149],"paper,":[114],"we":[115],"propose":[116],"holistic":[118],"solution":[119,152],"new":[123],"challenges":[124],"posed":[125],"by":[126],"Web,":[128],"whose":[129],"build":[133],"multiple":[139],"extensive":[143],"experiments":[144],"on":[145],"domains":[147],"show":[148],"proposed":[151],"highly":[154],"effective":[155],"integration.":[160]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}