{"id":"https://openalex.org/W2101622439","doi":"https://doi.org/10.1145/1401890.1401977","title":"A unified approach for schema matching, coreference and canonicalization","display_name":"A unified approach for schema matching, coreference and canonicalization","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2101622439","doi":"https://doi.org/10.1145/1401890.1401977","mag":"2101622439"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://works.bepress.com/andrew_mccallum/91/download/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058514754","display_name":"Michael Wick","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael L. Wick","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037673735","display_name":"Khashayar Rohanimanesh","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khashayar Rohanimanesh","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108851994","display_name":"Karl Schultz","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karl Schultz","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107835063","display_name":"Andrew McCallum","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McCallum","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA","University of Massachusetts, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058514754"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":7.4425,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97009798,"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":"722","last_page":"730"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9976000189781189,"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":0.9886999726295471,"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/coreference","display_name":"Coreference","score":0.93575119972229},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.914881706237793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.876444399356842},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7797591090202332},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5969284176826477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5102195739746094},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.4974656403064728},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4548135995864868},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4394400417804718},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42137137055397034},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3799230754375458},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.1357206404209137}],"concepts":[{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.93575119972229},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.914881706237793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.876444399356842},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7797591090202332},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5969284176826477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5102195739746094},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.4974656403064728},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4548135995864868},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4394400417804718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42137137055397034},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3799230754375458},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.1357206404209137},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1401890.1401977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1157","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/91","pdf_url":"https://works.bepress.com/andrew_mccallum/91/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew McCallum","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.219.1066","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.219.1066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umass.edu/~mccallum/papers/mwick08unified.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.570.1317","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.570.1317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://disi.unitn.it/~p2p/RelatedWork/Matching/wick_kdd08.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1157","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/91","pdf_url":"https://works.bepress.com/andrew_mccallum/91/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew McCallum","raw_type":"text"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311089","display_name":"National Security Agency","ror":"https://ror.org/0047bvr32"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2101622439.pdf","grobid_xml":"https://content.openalex.org/works/W2101622439.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W69204817","https://openalex.org/W128101668","https://openalex.org/W1496319844","https://openalex.org/W1505906253","https://openalex.org/W1526729636","https://openalex.org/W1547546052","https://openalex.org/W1547705211","https://openalex.org/W1590030008","https://openalex.org/W1766412966","https://openalex.org/W2008896880","https://openalex.org/W2090987348","https://openalex.org/W2115461474","https://openalex.org/W2116690618","https://openalex.org/W2121123524","https://openalex.org/W2123480907","https://openalex.org/W2123569689","https://openalex.org/W2133236963","https://openalex.org/W2142250121","https://openalex.org/W2142276227","https://openalex.org/W2147706904","https://openalex.org/W2147880316","https://openalex.org/W2148572968","https://openalex.org/W2150365753","https://openalex.org/W2153977007","https://openalex.org/W2161682962","https://openalex.org/W2164455818","https://openalex.org/W2171472464","https://openalex.org/W4387589449"],"related_works":["https://openalex.org/W1885838195","https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W1128683088","https://openalex.org/W2372910313","https://openalex.org/W3138074544","https://openalex.org/W4310041472","https://openalex.org/W2938811602","https://openalex.org/W2036644834"],"abstract_inverted_index":{"The":[0],"automatic":[1],"consolidation":[2],"of":[3,85],"database":[4],"records":[5],"from":[6,54],"many":[7],"heterogeneous":[8],"sources":[9],"into":[10],"a":[11,64,81,97,106,131,138],"single":[12],"repository":[13],"requires":[14],"solving":[15,91],"several":[16],"information":[17],"integration":[18,44],"tasks.":[19],"Although":[20],"tasks":[21,93],"such":[22],"as":[23],"coreference,":[24,72],"schema":[25,70,143],"matching,":[26,71],"and":[27,73,87,137],"canonicalization":[28,74],"are":[29,33],"closely":[30],"related,":[31],"they":[32],"most":[34],"commonly":[35],"studied":[36],"in":[37,121],"isolation.":[38],"Systems":[39],"that":[40,67,89,105,116],"do":[41],"tackle":[42],"multiple":[43],"problems":[45],"traditionally":[46],"solve":[47,118],"each":[48,119],"independently,":[49],"allowing":[50],"errors":[51,95],"to":[52,57,111],"propagate":[53],"one":[55],"task":[56,120],"another.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"describe":[63],"discriminatively-trained":[65],"model":[66,79,108],"reasons":[68],"about":[69],"jointly.":[75],"We":[76,128],"evaluate":[77],"our":[78],"on":[80],"real-world":[82],"data":[83],"set":[84],"people":[86],"demonstrate":[88,129],"simultaneously":[90],"these":[92],"reduces":[94],"over":[96,114],"cascaded":[98],"or":[99,123],"isolated":[100],"approach.":[101],"Our":[102],"experiments":[103],"show":[104],"joint":[107],"is":[109],"able":[110],"improve":[112],"substantially":[113],"systems":[115],"either":[117],"isolation":[122],"with":[124],"the":[125],"conventional":[126],"cascade.":[127],"nearly":[130],"50%":[132],"error":[133,140],"reduction":[134,141],"for":[135,142],"coreference":[136],"40%":[139],"matching.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}