{"id":"https://openalex.org/W2103561765","doi":"https://doi.org/10.1109/icdcs.2007.96","title":"D-Swoosh: A Family of Algorithms for Generic, Distributed Entity Resolution","display_name":"D-Swoosh: A Family of Algorithms for Generic, Distributed Entity Resolution","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2103561765","doi":"https://doi.org/10.1109/icdcs.2007.96","mag":"2103561765"},"language":"en","primary_location":{"id":"doi:10.1109/icdcs.2007.96","doi":"https://doi.org/10.1109/icdcs.2007.96","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcs.2007.96","pdf_url":null,"source":{"id":"https://openalex.org/S4393916864","display_name":"Proceedings of the ... International Conference on Distributed Computing Systems/Proceedings of the International Conference on Distributed Computing Systems","issn_l":"1063-6927","issn":["1063-6927"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"27th International Conference on Distributed Computing Systems (ICDCS '07)","raw_type":"proceedings-article"},"volume":null,"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/A5103212061","display_name":"Omar Benjelloun","orcid":"https://orcid.org/0000-0002-4173-7709","observed_orcids":["https://orcid.org/0000-0002-4173-7709","https://orcid.org/0000-0001-9803-3801"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omar Benjelloun","raw_affiliation_strings":["University of Stanford, USA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055883336","display_name":"H\u00e9ctor Garc\u00eda-Molina","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hector Garcia-Molina","raw_affiliation_strings":["University of Stanford, USA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Heng Gong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Gong","raw_affiliation_strings":["University of Stanford, USA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hideki Kawai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hideki Kawai","raw_affiliation_strings":["University of Stanford, USA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063017819","display_name":"Tait E. Larson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tait E. Larson","raw_affiliation_strings":["University of Stanford, USA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084927411","display_name":"David Menestrina","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Menestrina","raw_affiliation_strings":["University of Stanford, USA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079327520","display_name":"Sutthipong Thavisomboon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sutthipong Thavisomboon","raw_affiliation_strings":["University of Stanford, USA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":7.4267,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.9733809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T11269","display_name":"Algorithms and Data Compression","score":0.0,"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/entity-resolution","display_name":"entity resolution","score":0.9520000219345093},{"id":"https://openalex.org/keywords/distributed-algorithms","display_name":"distributed algorithms","score":0.6340000033378601},{"id":"https://openalex.org/keywords/record-matching","display_name":"record matching","score":0.6679999828338623},{"id":"https://openalex.org/keywords/record-merging","display_name":"record merging","score":0.9449999928474426},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"parallel computing","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847320556640625},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.8182445764541626},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7437758445739746},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5602173805236816},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4807679355144501},{"id":"https://openalex.org/C140086265","wikidata":"https://www.wikidata.org/wiki/Q11341754","display_name":"Merge algorithm","level":4,"score":0.44103673100471497},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.42893195152282715},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39249759912490845},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37465035915374756},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3203655481338501},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3158559203147888},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23634907603263855},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13989320397377014},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10904800891876221},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.0},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdcs.2007.96","doi":"https://doi.org/10.1109/icdcs.2007.96","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcs.2007.96","pdf_url":null,"source":{"id":"https://openalex.org/S4393916864","display_name":"Proceedings of the ... International Conference on Distributed Computing Systems/Proceedings of the International Conference on Distributed Computing Systems","issn_l":"1063-6927","issn":["1063-6927"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"27th International Conference on Distributed Computing Systems (ICDCS '07)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.6468","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.6468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ilpubs.stanford.edu:8090/856/1/2007-24.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1569123402","https://openalex.org/W2023448865","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2052390074","https://openalex.org/W2052960791","https://openalex.org/W2055405704","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2100198355","https://openalex.org/W2102350406","https://openalex.org/W2110765100","https://openalex.org/W2123561513","https://openalex.org/W2129598390","https://openalex.org/W2131053137","https://openalex.org/W2170523074","https://openalex.org/W2170902582","https://openalex.org/W2171574281","https://openalex.org/W2294565236","https://openalex.org/W3131990685","https://openalex.org/W4294549613"],"related_works":["https://openalex.org/W7100644645","https://openalex.org/W107023076","https://openalex.org/W7096072479","https://openalex.org/W2123561513","https://openalex.org/W332501843","https://openalex.org/W117442233","https://openalex.org/W1925598861","https://openalex.org/W917424677","https://openalex.org/W2490088997","https://openalex.org/W2620941783"],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"(ER)":[2],"matches":[3],"and":[4,14,25,49,52],"merges":[5],"records":[6,57],"that":[7,54,62],"refer":[8],"to":[9,21,60],"the":[10,38],"same":[11],"real-world":[12],"entities,":[13],"is":[15],"typically":[16],"a":[17,31,69,74],"compute-intensive":[18],"process":[19],"due":[20],"complex":[22],"matching":[23,65],"functions":[24],"high":[26],"data":[27,85],"volumes.":[28],"We":[29,67],"present":[30],"family":[32],"of":[33,76],"algorithms,":[34],"D-Swoosh,":[35],"for":[36],"distributing":[37],"ER":[39],"workload":[40],"across":[41],"multiple":[42],"processors.":[43,78],"The":[44],"algorithms":[45],"use":[46,81],"generic":[47],"match":[48],"merge":[50],"functions,":[51],"ensure":[53],"new":[55],"merged":[56],"are":[58],"distributed":[59],"processors":[61],"may":[63],"have":[64],"records.":[66],"perform":[68],"detailed":[70],"performance":[71],"evaluation":[72],"on":[73],"testbed":[75],"15":[77],"Our":[79],"experiments":[80],"actual":[82],"comparison":[83],"shopping":[84],"provided":[86],"by":[87],"Yahoo!.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2016-06-24T00:00:00"}
