{"id":"https://openalex.org/W2158418361","doi":"https://doi.org/10.1145/2124295.2124305","title":"Beyond 100 million entities","display_name":"Beyond 100 million entities","publication_year":2012,"publication_date":"2012-02-08","ids":{"openalex":"https://openalex.org/W2158418361","doi":"https://doi.org/10.1145/2124295.2124305","mag":"2158418361"},"language":"en","primary_location":{"id":"doi:10.1145/2124295.2124305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2124295.2124305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.softnet.tuc.gr/~ioannou/publications/files/conf-wsdm-papadakisINPN12.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056976720","display_name":"George Papadakis","orcid":"https://orcid.org/0000-0002-7298-9431"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Papadakis","raw_affiliation_strings":["National Technical University of Athens &amp; L3S Research Center, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens &amp; L3S Research Center, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084886581","display_name":"Ekaterini Ioannou","orcid":"https://orcid.org/0000-0002-4922-6639"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ekaterini Ioannou","raw_affiliation_strings":["Technical University of Crete, Chania, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Crete, Chania, Greece","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037478463","display_name":"Claudia Nieder\u00e9e","orcid":"https://orcid.org/0000-0002-2959-0484"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Nieder\u00e9e","raw_affiliation_strings":["L3S Research Center, Hanover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hanover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726723","display_name":"Themis Palpanas","orcid":"https://orcid.org/0000-0002-8031-0265"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Themis Palpanas","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074427964","display_name":"Wolfgang Nejdl","orcid":"https://orcid.org/0000-0003-3374-2193"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Nejdl","raw_affiliation_strings":["L3S Research Center &amp; Leibniz University of Hanover, Hanover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center &amp; Leibniz University of Hanover, Hanover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.849077582359314},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7009146213531494},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6004146337509155},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5769824385643005},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5567982792854309},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.4890216290950775},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4606483280658722},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.42435866594314575},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.41938716173171997},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3443407416343689},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.2752280831336975},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1173853874206543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849077582359314},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7009146213531494},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6004146337509155},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5769824385643005},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5567982792854309},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.4890216290950775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4606483280658722},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.42435866594314575},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.41938716173171997},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3443407416343689},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2752280831336975},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1173853874206543},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2124295.2124305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2124295.2124305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unitn.it:11572/91637","is_oa":true,"landing_page_url":"http://hdl.handle.net/11572/91637","pdf_url":"http://www.softnet.tuc.gr/~ioannou/publications/files/conf-wsdm-papadakisINPN12.pdf","source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/36417","is_oa":true,"landing_page_url":"http://doi.org/10.1145/2124295.2124305","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unitn.it:11572/88864","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/88864","pdf_url":null,"source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unitn.it:11572/91637","is_oa":true,"landing_page_url":"http://hdl.handle.net/11572/91637","pdf_url":"http://www.softnet.tuc.gr/~ioannou/publications/files/conf-wsdm-papadakisINPN12.pdf","source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2053426945","display_name":"GLOCAL: Event-based Retrieval of Networked Media","funder_award_id":"248984","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2158418361.pdf","grobid_xml":"https://content.openalex.org/works/W2158418361.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W142015572","https://openalex.org/W343945789","https://openalex.org/W1540269031","https://openalex.org/W1646278814","https://openalex.org/W1967208734","https://openalex.org/W1982287794","https://openalex.org/W1992930793","https://openalex.org/W1993783004","https://openalex.org/W2005320059","https://openalex.org/W2015191210","https://openalex.org/W2024770506","https://openalex.org/W2029554959","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2073539176","https://openalex.org/W2088008685","https://openalex.org/W2104335224","https://openalex.org/W2108991785","https://openalex.org/W2109834209","https://openalex.org/W2111116800","https://openalex.org/W2111625757","https://openalex.org/W2117974736","https://openalex.org/W2140789797","https://openalex.org/W2161936973","https://openalex.org/W2163616098","https://openalex.org/W6632038546","https://openalex.org/W6645909579","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W113172935","https://openalex.org/W3208717180","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2014400548","https://openalex.org/W2472770163","https://openalex.org/W4301779090","https://openalex.org/W2029826694","https://openalex.org/W4298139853","https://openalex.org/W1990272589"],"abstract_inverted_index":{"A":[0],"prerequisite":[1],"for":[2,73],"leveraging":[3],"the":[4,11,17,26,52,62,76,82,102,110],"vast":[5],"amount":[6],"of":[7,19,55,61,99,104,112],"data":[8,23,39],"available":[9],"on":[10,94],"Web":[12],"is":[13,42],"Entity":[14],"Resolution,":[15],"i.e.,":[16],"process":[18,35],"identifying":[20],"and":[21,58],"linking":[22],"that":[24],"describe":[25],"same":[27,63],"real-world":[28],"objects.":[29],"To":[30],"make":[31],"this":[32],"inherently":[33],"quadratic":[34],"applicable":[36],"to":[37,91],"large":[38],"sets,":[40],"blocking":[41,69,86,105],"typically":[43],"employed:":[44],"entities":[45,60],"(records)":[46],"are":[47,65,71,88],"grouped":[48],"into":[49],"clusters":[50],"-":[51,54],"blocks":[53],"matching":[56],"candidates":[57],"only":[59],"block":[64],"compared.":[66],"However,":[67],"novel":[68],"techniques":[70,87],"required":[72],"dealing":[74],"with":[75],"noisy,":[77],"heterogeneous,":[78],"semi-structured,":[79],"user-generateddata":[80],"in":[81],"Web,":[83],"as":[84],"traditional":[85],"inapplicable":[89],"due":[90],"their":[92],"reliance":[93],"schema":[95],"information.":[96],"The":[97],"introduction":[98],"redundancy,":[100],"improves":[101],"robustness":[103],"methods":[106],"but":[107],"comes":[108],"at":[109],"price":[111],"additional":[113],"computational":[114],"cost.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
