{"id":"https://openalex.org/W1992930793","doi":"https://doi.org/10.1145/1935826.1935903","title":"Efficient entity resolution for large heterogeneous information spaces","display_name":"Efficient entity resolution for large heterogeneous information spaces","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W1992930793","doi":"https://doi.org/10.1145/1935826.1935903","mag":"1992930793"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935903","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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/A5056976720","display_name":"George Papadakis","orcid":"https://orcid.org/0000-0002-7298-9431"},"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":"George Papadakis","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"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/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":"Ekaterini Ioannou","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"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, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037943398","display_name":"P\u00e9ter Fankhauser","orcid":"https://orcid.org/0000-0001-7128-9188"},"institutions":[{"id":"https://openalex.org/I4210133470","display_name":"Fraunhofer Institute for Secure Information Technology","ror":"https://ror.org/03qt2gs44","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210133470","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Fankhauser","raw_affiliation_strings":["Fraunhofer IPSI, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IPSI, Darmstadt, Germany","institution_ids":["https://openalex.org/I4210133470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"535","last_page":"544"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9848999977111816,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8569671511650085},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5334907174110413},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5119917988777161},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.43315589427948},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34277066588401794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32514292001724243},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.29751938581466675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569671511650085},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5334907174110413},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5119917988777161},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.43315589427948},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34277066588401794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32514292001724243},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29751938581466675}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1935826.1935903","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.6164","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.6164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.l3s.de/%7Eioannou/publications/files/conf-wsdm-papadakisINF11.pdf","raw_type":"text"},{"id":"pmh:oai:publica.fraunhofer.de:publica/375341","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/375341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W343945789","https://openalex.org/W1540269031","https://openalex.org/W1646278814","https://openalex.org/W2007682403","https://openalex.org/W2017102965","https://openalex.org/W2024770506","https://openalex.org/W2029554959","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2087183379","https://openalex.org/W2088008685","https://openalex.org/W2104335224","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2111625757","https://openalex.org/W2112912553","https://openalex.org/W2115219423","https://openalex.org/W2117974736","https://openalex.org/W2128661986","https://openalex.org/W2138105615","https://openalex.org/W2141634619","https://openalex.org/W2161936973","https://openalex.org/W2296421186","https://openalex.org/W3004104752","https://openalex.org/W6632038546","https://openalex.org/W6676669657","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W4234886518","https://openalex.org/W2389591058","https://openalex.org/W2382112581","https://openalex.org/W3124036233","https://openalex.org/W4229787472","https://openalex.org/W2486541857","https://openalex.org/W2108840191","https://openalex.org/W2759366996","https://openalex.org/W2110679372","https://openalex.org/W2354081742"],"abstract_inverted_index":{"We":[0],"have":[1],"recently":[2],"witnessed":[3],"an":[4,120],"enormous":[5],"growth":[6],"in":[7],"the":[8,18,31,39,61,87,90,145,164],"volume":[9],"of":[10,35,69,89],"structured":[11],"and":[12,25,33,67,93,114,143,170],"semi-structured":[13],"data":[14,28,92,160],"sets":[15,29,161],"available":[16],"on":[17,86,156],"Web.":[19],"An":[20],"important":[21],"prerequisite":[22],"for":[23,105,111,123],"using":[24],"combining":[26],"such":[27],"is":[30,167],"detection":[32],"merge":[34],"information":[36,116],"that":[37,131,163],"describes":[38],"same":[40],"real-world":[41],"entities,":[42],"a":[43,102],"task":[44,53],"known":[45,95],"as":[46],"Entity":[47],"Resolution.":[48],"To":[49],"make":[50],"this":[51,98],"quadratic":[52],"efficient,":[54],"blocking":[55,79],"techniques":[56,130],"are":[57],"typically":[58],"employed.":[59],"However,":[60],"high":[62,135],"dynamics,":[63],"loose":[64],"schema":[65],"binding,":[66],"heterogeneity":[68],"(semi-)structured":[70],"data,":[71],"impose":[72],"new":[73],"challenges":[74],"to":[75],"entity":[76,106],"resolution.":[77],"Existing":[78],"approaches":[80],"become":[81],"inapplicable":[82],"because":[83],"they":[84],"rely":[85],"homogeneity":[88],"considered":[91],"a-priory":[94],"schemata.":[96],"In":[97],"paper,":[99],"we":[100],"introduce":[101],"novel":[103],"approach":[104,166],"resolution,":[107],"scaling":[108],"it":[109,149],"up":[110],"large,":[112,158],"noisy,":[113],"heterogeneous":[115,159],"spaces.":[117],"It":[118],"combines":[119],"attribute-agnostic":[121],"mechanism":[122],"building":[124],"blocks":[125,133],"with":[126,134],"intelligent":[127],"block":[128],"processing":[129],"boost":[132],"expected":[136],"utility,":[137],"propagate":[138],"knowledge":[139],"about":[140],"identified":[141],"matches,":[142],"preempt":[144],"resolution":[146],"process":[147],"when":[148],"gets":[150],"too":[151],"expensive.":[152],"Our":[153],"extensive":[154],"evaluation":[155],"real-world,":[157],"verifies":[162],"suggested":[165],"both":[168],"effective":[169],"efficient.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}