{"id":"https://openalex.org/W2149714235","doi":"https://doi.org/10.1145/1401890.1401931","title":"Unsupervised deduplication using cross-field dependencies","display_name":"Unsupervised deduplication using cross-field dependencies","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2149714235","doi":"https://doi.org/10.1145/1401890.1401931","mag":"2149714235"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401931","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401931","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/92/download/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110618474","display_name":"Rob Hall","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":"Rob Hall","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028501178","display_name":"Charles Sutton","orcid":"https://orcid.org/0000-0002-0041-3820"},"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":"Charles Sutton","raw_affiliation_strings":["University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008354502","display_name":"Andrew McCallum","orcid":"https://orcid.org/0000-0003-2843-6992"},"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"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110618474"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":4.3747,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94126371,"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":"310","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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":0.9990000128746033,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9922999739646912,"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/T10028","display_name":"Topic Modeling","score":0.9871000051498413,"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/data-deduplication","display_name":"Data deduplication","score":0.8634212017059326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7547361850738525},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6327565312385559},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6098178625106812},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5888491868972778},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5360024571418762},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.475498765707016},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.4465739130973816},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.44168031215667725},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4356672763824463},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41962939500808716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40510278940200806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37481844425201416},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.35761070251464844},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.33952346444129944},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16710418462753296},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15426906943321228}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8634212017059326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547361850738525},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6327565312385559},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6098178625106812},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5888491868972778},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5360024571418762},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.475498765707016},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.4465739130973816},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.44168031215667725},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4356672763824463},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41962939500808716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40510278940200806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37481844425201416},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.35761070251464844},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.33952346444129944},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16710418462753296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15426906943321228},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1401890.1401931","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401931","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-1159","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/92","pdf_url":"https://works.bepress.com/andrew_mccallum/92/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:10.1.1.366.9160","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.366.9160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://maroo.cs.umass.edu/pub/web/getpdf.php?id=843","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1159","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/92","pdf_url":"https://works.bepress.com/andrew_mccallum/92/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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2149714235.pdf","grobid_xml":"https://content.openalex.org/works/W2149714235.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1536860849","https://openalex.org/W1774330103","https://openalex.org/W1880262756","https://openalex.org/W1979629649","https://openalex.org/W2080972498","https://openalex.org/W2097730395","https://openalex.org/W2133236963","https://openalex.org/W2137268161","https://openalex.org/W2147706904","https://openalex.org/W2148019918","https://openalex.org/W2154099718","https://openalex.org/W2158266063","https://openalex.org/W2159481891","https://openalex.org/W2165091599","https://openalex.org/W2171472464","https://openalex.org/W2187534804","https://openalex.org/W2595697910","https://openalex.org/W2745560456","https://openalex.org/W4254259096","https://openalex.org/W6683373780","https://openalex.org/W6684292603"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W2497860580","https://openalex.org/W2891616219","https://openalex.org/W3204672119"],"abstract_inverted_index":{"Recent":[0],"work":[1],"in":[2,32,34,74,135,141],"deduplication":[3,8,91],"has":[4],"shown":[5],"that":[6,93,127],"collective":[7],"of":[9,104],"different":[10],"attribute":[11],"types":[12],"can":[13],"improve":[14],"performance.":[15],"But":[16],"although":[17],"these":[18],"techniques":[19],"cluster":[20],"the":[21,35,90],"attributes":[22],"collectively,":[23],"they":[24],"do":[25],"not":[26,62],"model":[27,88,99,115,122],"them":[28],"collectively.":[29],"For":[30],"example,":[31],"citations":[33],"research":[36,55],"literature,":[37],"canonical":[38],"venue":[39],"strings":[40,43],"and":[41,118],"title":[42],"are":[44],"dependent":[45],"--":[46,57,137],"because":[47],"venues":[48],"tend":[49],"to":[50,107],"focus":[51],"on":[52],"a":[53,75,77,101,113,119,132,138,144],"few":[54],"areas":[56],"but":[58],"this":[59,70,81],"dependence":[60,71,130],"is":[61],"modeled":[63],"by":[64],"current":[65],"unsupervised":[66,86],"techniques.":[67],"We":[68,125],"call":[69],"between":[72],"fields":[73],"record":[76],"cross-field":[78,96,129],"dependence.":[79,97],"In":[80],"paper,":[82],"we":[83],"present":[84],"an":[85],"generative":[87],"for":[89],"problem":[92],"explicitly":[94],"models":[95],"Our":[98],"uses":[100],"single":[102],"set":[103],"latent":[105],"variables":[106],"control":[108],"two":[109],"disparate":[110],"clustering":[111],"models:":[112],"Dirichlet-multinomial":[114],"over":[116,123,143],"titles,":[117],"non-exchangeable":[120],"string-edit":[121],"venues.":[124],"show":[126],"modeling":[128],"yields":[131],"substantial":[133],"improvement":[134],"performance":[136],"58%":[139],"reduction":[140],"error":[142],"standard":[145],"Dirichlet":[146],"process":[147],"mixture.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}