{"id":"https://openalex.org/W2119320829","doi":"https://doi.org/10.1145/1807167.1807252","title":"On active learning of record matching packages","display_name":"On active learning of record matching packages","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2119320829","doi":"https://doi.org/10.1145/1807167.1807252","mag":"2119320829"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","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/A5026802346","display_name":"Arvind Arasu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Arasu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020288994","display_name":"Michaela G\u00f6tz","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michaela G\u00f6tz","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103280746","display_name":"Raghav Kaushik","orcid":"https://orcid.org/0000-0003-1457-1384"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghav Kaushik","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.4505,"has_fulltext":false,"cited_by_count":185,"citation_normalized_percentile":{"value":0.98928044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"783","last_page":"794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9995999932289124,"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/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9902999997138977,"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/computer-science","display_name":"Computer science","score":0.7928885221481323},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.7365442514419556},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7115734219551086},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6642394065856934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6375331878662109},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6263567805290222},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5597521066665649},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5263967514038086},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.4146004617214203},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07271063327789307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928885221481323},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.7365442514419556},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7115734219551086},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6642394065856934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6375331878662109},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6263567805290222},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5597521066665649},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5263967514038086},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.4146004617214203},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07271063327789307},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1807167.1807252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.8992","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.8992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/%7Egoetz/pdf/sigmodActiveLearningOfRecordMatchings.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.464.7800","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.464.7800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/class/spring2012/cmsc828L/Papers/ArasuSIGMOD2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1489243580","https://openalex.org/W1504694836","https://openalex.org/W1528361845","https://openalex.org/W1545736123","https://openalex.org/W1559390933","https://openalex.org/W1569123402","https://openalex.org/W1573317759","https://openalex.org/W1660390307","https://openalex.org/W1974995373","https://openalex.org/W1977245551","https://openalex.org/W2024605621","https://openalex.org/W2024770506","https://openalex.org/W2028128906","https://openalex.org/W2036216970","https://openalex.org/W2045086034","https://openalex.org/W2046020929","https://openalex.org/W2052581258","https://openalex.org/W2058755145","https://openalex.org/W2067566391","https://openalex.org/W2095644746","https://openalex.org/W2096598900","https://openalex.org/W2097730395","https://openalex.org/W2102350406","https://openalex.org/W2105423800","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2114232233","https://openalex.org/W2114909350","https://openalex.org/W2115404432","https://openalex.org/W2119057313","https://openalex.org/W2121516976","https://openalex.org/W2125055259","https://openalex.org/W2127675794","https://openalex.org/W2133990480","https://openalex.org/W2135892731","https://openalex.org/W2138745909","https://openalex.org/W2139212933","https://openalex.org/W2139945125","https://openalex.org/W2143124645","https://openalex.org/W2143182259","https://openalex.org/W2151023586","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2168190036","https://openalex.org/W2170902582","https://openalex.org/W2221787104","https://openalex.org/W2246671150","https://openalex.org/W2281290965","https://openalex.org/W2426031434","https://openalex.org/W2854975279","https://openalex.org/W2990138404","https://openalex.org/W3193477162","https://openalex.org/W4285719527","https://openalex.org/W6661768467"],"related_works":["https://openalex.org/W184546935","https://openalex.org/W146740654","https://openalex.org/W2131495543","https://openalex.org/W2037866349","https://openalex.org/W2021806873","https://openalex.org/W3179999069","https://openalex.org/W2106701323","https://openalex.org/W4299830350","https://openalex.org/W2909115059","https://openalex.org/W2097814353"],"abstract_inverted_index":{"We":[0,91,125],"consider":[1],"the":[2,19,23,40,82,135],"problem":[3,97,119],"of":[4,25,56,137],"learning":[5,14,20,34,44,66,110],"a":[6,37,53,127],"record":[7,48,68,123],"matching":[8,49,69],"package":[9],"(classifier)":[10],"in":[11],"an":[12],"active":[13,17,65,109],"setting.":[15],"In":[16],"learning,":[18],"algorithm":[21],"picks":[22],"set":[24,55],"examples":[26,58],"to":[27,87,117,122],"be":[28],"labeled,":[29],"unlike":[30],"more":[31],"traditional":[32,108],"passive":[33],"setting":[35],"where":[36],"user":[38],"selects":[39],"labeled":[41,57],"examples.":[42],"Active":[43],"is":[45,59],"important":[46],"for":[47,67,95],"since":[50],"manually":[51],"identifying":[52],"suitable":[54],"difficult.":[60],"Previous":[61],"algorithms":[62,83,94,103],"that":[63,75,98],"use":[64],"have":[70],"serious":[71],"limitations:":[72],"The":[73],"packages":[74],"they":[76],"learn":[77],"lack":[78],"quality":[79],"guarantees":[80],"and":[81,112],"do":[84],"not":[85],"scale":[86],"large":[88],"input":[89],"sizes.":[90],"present":[92],"new":[93],"this":[96],"overcome":[99],"these":[100],"limitations.":[101],"Our":[102],"are":[104,113],"fundamentally":[105],"different":[106],"from":[107],"approaches,":[111],"designed":[114],"ground":[115],"up":[116],"exploit":[118],"characteristics":[120],"specific":[121],"matching.":[124],"include":[126],"detailed":[128],"experimental":[129],"evaluation":[130],"on":[131],"realworld":[132],"data":[133],"demonstrating":[134],"effectiveness":[136],"our":[138],"algorithms.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}