{"id":"https://openalex.org/W2053328473","doi":"https://doi.org/10.1145/1146598.1146738","title":"Matching and integration across heterogeneous data sources","display_name":"Matching and integration across heterogeneous data sources","publication_year":2006,"publication_date":"2006-05-21","ids":{"openalex":"https://openalex.org/W2053328473","doi":"https://doi.org/10.1145/1146598.1146738","mag":"2053328473"},"language":"en","primary_location":{"id":"doi:10.1145/1146598.1146738","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1146598.1146738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 international conference on Digital government research","raw_type":"proceedings-article"},"type":"article","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/A5041476585","display_name":"Patrick Pantel","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Patrick Pantel","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA","Univ. of Southern California, Marina del Rey, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Univ. of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039759712","display_name":"Andrew Philpot","orcid":null},"institutions":[{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Philpot","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA","Univ. of Southern California, Marina del Rey, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Univ. of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060225743","display_name":"Eduard Hovy","orcid":"https://orcid.org/0000-0002-3270-7903"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard Hovy","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA","Univ. of Southern California, Marina del Rey, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Univ. of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041476585"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"],"apc_list":null,"apc_paid":null,"fwci":1.685,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8450283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"438","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T11106","display_name":"Data Management and Algorithms","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7091912031173706},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.599511444568634},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5660578608512878},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45639699697494507},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28291305899620056},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06528112292289734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7091912031173706},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.599511444568634},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5660578608512878},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45639699697494507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28291305899620056},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06528112292289734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1146598.1146738","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1146598.1146738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 international conference on Digital government research","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W101250378","https://openalex.org/W163016242","https://openalex.org/W1500338977","https://openalex.org/W1547461197","https://openalex.org/W1592911914","https://openalex.org/W1660390307","https://openalex.org/W1727944201","https://openalex.org/W1995875735","https://openalex.org/W2034757509","https://openalex.org/W2042389627","https://openalex.org/W2142104809","https://openalex.org/W2150365753","https://openalex.org/W2170192471","https://openalex.org/W2172549414","https://openalex.org/W3198160809","https://openalex.org/W4285719527","https://openalex.org/W6648982606"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2126703991","https://openalex.org/W2610897791","https://openalex.org/W4366463707"],"abstract_inverted_index":{"A":[0],"sea":[1],"of":[2,10,71,78],"undifferentiated":[3],"information":[4,72],"is":[5,13],"forming":[6],"from":[7],"the":[8,75,84,99,107],"body":[9],"data":[11,34,40,63],"that":[12],"collected":[14],"by":[15,98],"people":[16],"and":[17,27,53,60,103,109],"organizations,":[18],"across":[19,64],"government,":[20],"for":[21,39,55,61],"different":[22,25,29],"purposes,":[23],"at":[24,106],"times,":[26],"using":[28],"methodologies.":[30],"The":[31],"resulting":[32],"massive":[33],"heterogeneity":[35],"requires":[36],"automatic":[37],"methods":[38],"alignment,":[41],"matching":[42],"and/or":[43],"merging.":[44],"In":[45],"this":[46],"poster,":[47],"we":[48],"describe":[49],"two":[50],"systems,":[51],"Guspin\u2122":[52],"Sift\u2122,":[54],"automatically":[56],"identifying":[57],"equivalence":[58],"classes":[59],"aligning":[62],"databases.":[65],"Our":[66],"technology,":[67],"based":[68],"on":[69],"principles":[70],"theory,":[73],"measures":[74],"relative":[76],"importance":[77],"data,":[79],"leveraging":[80],"them":[81],"to":[82,93],"quantify":[83],"similarity":[85],"between":[86],"entities.":[87],"These":[88],"systems":[89],"have":[90],"been":[91],"applied":[92],"solve":[94],"real":[95],"problems":[96],"faced":[97],"Environmental":[100],"Protection":[101],"Agency":[102],"its":[104],"counterparts":[105],"state":[108],"local":[110],"government":[111],"level.":[112]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}