{"id":"https://openalex.org/W2042145781","doi":"https://doi.org/10.1145/1146598.1146721","title":"Entity consolidation and alignment in semi-structured data sources","display_name":"Entity consolidation and alignment in semi-structured data sources","publication_year":2006,"publication_date":"2006-05-21","ids":{"openalex":"https://openalex.org/W2042145781","doi":"https://doi.org/10.1145/1146598.1146721","mag":"2042145781"},"language":"en","primary_location":{"id":"doi:10.1145/1146598.1146721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1146598.1146721","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/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":true,"raw_author_name":"Eduard Hovy","raw_affiliation_strings":["University 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"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"University 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/A5041476585","display_name":"Patrick Pantel","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":"Patrick Pantel","raw_affiliation_strings":["University 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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060225743"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15769518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"400","last_page":"401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.79804527759552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7859718799591064},{"id":"https://openalex.org/keywords/semi-structured-data","display_name":"Semi-structured data","score":0.7639520168304443},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6084168553352356},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6001952290534973},{"id":"https://openalex.org/keywords/consolidation","display_name":"Consolidation (business)","score":0.5369545817375183},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4038168787956238},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3373393416404724},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3340340256690979},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2910845875740051},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.11003735661506653}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.79804527759552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859718799591064},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.7639520168304443},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6084168553352356},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6001952290534973},{"id":"https://openalex.org/C2776014549","wikidata":"https://www.wikidata.org/wiki/Q3050847","display_name":"Consolidation (business)","level":2,"score":0.5369545817375183},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4038168787956238},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3373393416404724},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3340340256690979},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2910845875740051},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.11003735661506653},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1146598.1146721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1146598.1146721","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W4313444821","https://openalex.org/W4318818298","https://openalex.org/W3117578681","https://openalex.org/W2365827997"],"abstract_inverted_index":{"A":[0],"large":[1],"portion":[2],"of":[3,47,81,88],"collected":[4],"data":[5,53,71,74,110],"is":[6],"stored":[7],"in":[8,39],"semi-structured":[9,73],"form,":[10],"i.e.,":[11],"organized":[12],"or":[13,17,24],"related":[14],"through":[15],"columns":[16],"lists":[18],"but":[19],"without":[20],"any":[21],"formal":[22],"schema":[23],"metadata.":[25],"For":[26],"example,":[27],"many":[28],"government":[29],"organizations":[30],"and":[31,36,68,106,118],"companies":[32],"feature":[33],"employee":[34],"directories":[35],"project":[37],"affiliations":[38],"HTML":[40],"tables":[41],"on":[42,79],"their":[43],"websites.":[44],"Making":[45],"sense":[46],"these":[48],"requires":[49],"automatic":[50],"methods":[51],"for":[52,64,69,109],"alignment,":[54],"matching":[55],"and/or":[56],"merging.":[57],"Here,":[58],"we":[59],"describe":[60],"Guspin,":[61],"a":[62],"tool":[63],"automatically":[65],"consolidating":[66],"entities":[67],"aligning":[70],"across":[72],"sources.":[75],"Our":[76],"project,":[77],"based":[78],"principles":[80],"information":[82],"theory,":[83],"measures":[84],"the":[85,94,114],"relative":[86],"importance":[87],"data,":[89],"leveraging":[90],"them":[91],"to":[92,103],"quantify":[93],"similarity":[95],"between":[96],"entities.":[97],"We":[98],"have":[99],"applied":[100],"our":[101],"technology":[102],"discover":[104],"duplicates":[105],"perform":[107],"alignments":[108],"sources":[111],"provided":[112],"by":[113],"Environmental":[115],"Protection":[116],"Agency":[117],"California":[119],"environmental":[120],"agencies.":[121]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
