{"id":"https://openalex.org/W2052698082","doi":"https://doi.org/10.1145/2339530.2339707","title":"Active sampling for entity matching","display_name":"Active sampling for entity matching","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2052698082","doi":"https://doi.org/10.1145/2339530.2339707","mag":"2052698082"},"language":"en","primary_location":{"id":"doi:10.1145/2339530.2339707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5090835762","display_name":"Kedar Bellare","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kedar Bellare","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041045187","display_name":"Suresh Iyengar","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Suresh Iyengar","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013608601","display_name":"Aditya Parameswaran","orcid":"https://orcid.org/0000-0002-4538-4752"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya G. Parameswaran","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003599004","display_name":"Vibhor Rastogi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vibhor Rastogi","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090835762"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":12.8307,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":{"value":0.98826338,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1131","last_page":"1139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.998199999332428,"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":0.998199999332428,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9962999820709229,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.979200005531311,"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":0.7652238011360168},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7489701509475708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.608412504196167},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5072309970855713},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4670143723487854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46397122740745544},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4384409487247467},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4345116913318634},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41191136837005615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16000115871429443},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07909157872200012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652238011360168},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7489701509475708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.608412504196167},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5072309970855713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4670143723487854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46397122740745544},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4384409487247467},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4345116913318634},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41191136837005615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16000115871429443},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07909157872200012}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2339530.2339707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.7858","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.7858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ilpubs.stanford.edu:8090/1036/1/main.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W61518770","https://openalex.org/W1518784700","https://openalex.org/W1572210044","https://openalex.org/W1600192391","https://openalex.org/W2005314985","https://openalex.org/W2036216970","https://openalex.org/W2042932437","https://openalex.org/W2056707879","https://openalex.org/W2067566391","https://openalex.org/W2095644746","https://openalex.org/W2099416425","https://openalex.org/W2104511295","https://openalex.org/W2108991785","https://openalex.org/W2114232233","https://openalex.org/W2117756453","https://openalex.org/W2117974736","https://openalex.org/W2119320829","https://openalex.org/W2122689903","https://openalex.org/W2125943921","https://openalex.org/W2128518360","https://openalex.org/W2142021955","https://openalex.org/W2142261479","https://openalex.org/W2143124645","https://openalex.org/W2151023586","https://openalex.org/W2164456230","https://openalex.org/W2165484066","https://openalex.org/W2166886563","https://openalex.org/W2167595980","https://openalex.org/W2170902582","https://openalex.org/W2903158431","https://openalex.org/W2951528191","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W2794488505","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W4286910063","https://openalex.org/W2163707935","https://openalex.org/W83146503","https://openalex.org/W2169074127","https://openalex.org/W202723009","https://openalex.org/W2188612292"],"abstract_inverted_index":{"In":[0],"entity":[1,55],"matching,":[2],"a":[3,8,72,93],"fundamental":[4],"issue":[5],"while":[6],"training":[7,26],"classifier":[9,82],"to":[10,35,58,77],"label":[11],"pairs":[12,65,107],"of":[13,23,46,80,103],"entities":[14],"as":[15],"either":[16],"duplicates":[17],"or":[18],"non-duplicates":[19],"is":[20,50],"the":[21,41,47,81,84,97,101,109],"one":[22],"selecting":[24],"informative":[25],"examples.":[27],"Although":[28],"active":[29],"learning":[30],"presents":[31],"an":[32,51],"attractive":[33],"solution":[34],"this":[36],"problem,":[37],"previous":[38],"approaches":[39],"minimize":[40],"misclassification":[42],"rate":[43],"(0-1":[44],"loss)":[45],"classifier,":[48],"which":[49],"unsuitable":[52],"metric":[53],"for":[54],"matching":[56],"due":[57],"class":[59],"imbalance":[60],"(i.e.,":[61],"many":[62],"more":[63],"non-duplicate":[64],"than":[66,92],"duplicate":[67],"pairs).":[68],"To":[69],"address":[70],"this,":[71],"recent":[73],"paper":[74],"[1]":[75],"proposes":[76],"maximize":[78],"recall":[79],"under":[83],"constraint":[85],"that":[86],"its":[87],"precision":[88],"should":[89],"be":[90],"greater":[91],"specified":[94],"threshold.":[95],"However,":[96],"proposed":[98],"technique":[99],"requires":[100],"labels":[102],"all":[104],"n":[105],"input":[106],"in":[108],"worst-case.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}