{"id":"https://openalex.org/W4205223485","doi":"https://doi.org/10.1145/775085.775087","title":"Interactive deduplication using active learning","display_name":"Interactive deduplication using active learning","publication_year":2002,"publication_date":"2002-01-01","ids":{"openalex":"https://openalex.org/W4205223485","doi":"https://doi.org/10.1145/775085.775087"},"language":"en","primary_location":{"id":"doi:10.1145/775085.775087","doi":"https://doi.org/10.1145/775085.775087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775085.775087","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '02","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616","observed_orcids":["https://orcid.org/0009-0005-9538-6616"]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunita Sarawagi","raw_affiliation_strings":["IIT Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039999123","display_name":"Anuradha Bhamidipaty","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anuradha Bhamidipaty","raw_affiliation_strings":["IIT Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.37311768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":9.999999747378752e-05,"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/T12072","display_name":"Machine Learning and Algorithms","score":9.999999747378752e-05,"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/record-deduplication","display_name":"record deduplication","score":0.8289999961853027},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.7680000066757202},{"id":"https://openalex.org/keywords/entity-resolution","display_name":"entity resolution","score":0.7149999737739563},{"id":"https://openalex.org/keywords/data-integration","display_name":"data integration","score":0.6489999890327454},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"interactive learning","score":0.5440000295639038},{"id":"https://openalex.org/keywords/data-inconsistency","display_name":"data inconsistency","score":0.5509999990463257},{"id":"https://openalex.org/keywords/classifier-training","display_name":"classifier training","score":0.4129999876022339},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6050000190734863}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9685786366462708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8687810301780701},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5645214319229126},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5365533828735352},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5215497016906738},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4704384207725525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46706706285476685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4387013614177704},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4141325354576111},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3961767554283142},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1889713704586029},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/775085.775087","doi":"https://doi.org/10.1145/775085.775087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775085.775087","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '02","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7099058481","https://openalex.org/W42232109","https://openalex.org/W2144348063","https://openalex.org/W3194524707","https://openalex.org/W2287992749","https://openalex.org/W4401979936","https://openalex.org/W2122426698","https://openalex.org/W4411312427","https://openalex.org/W7097120225","https://openalex.org/W25696896"],"abstract_inverted_index":{"Deduplication":[0],"is":[1,17,54,94],"a":[2,19,25,57,77,118,124,165],"key":[3],"operation":[4],"in":[5,14,34,111,163],"integrating":[6],"data":[7,38,103],"from":[8],"multiple":[9],"sources.":[10],"The":[11,65],"main":[12],"challenge":[13],"this":[15,68],"task":[16],"designing":[18],"function":[20],"that":[21,85,122,142,161],"can":[22],"resolve":[23],"when":[24],"pair":[26],"of":[27,36,52,67,82,90,117,127,149],"records":[28,108],"refer":[29],"to":[30,48,55,59,75,152,167],"the":[31,50,88,147],"same":[32],"entity":[33],"spite":[35],"various":[37,102,158],"inconsistencies.":[39],"Most":[40],"existing":[41],"systems":[42],"use":[43],"hand-coded":[44],"functions.":[45],"One":[46],"way":[47],"overcome":[49],"tedium":[51],"hand-coding":[53],"train":[56],"classifier":[58],"distinguish":[60],"between":[61,105],"duplicates":[62],"and":[63,79,173],"non-duplicates.":[64],"success":[66],"method":[69,126],"critically":[70],"hinges":[71],"on":[72,138],"being":[73],"able":[74],"provide":[76,168],"covering":[78],"challenging":[80,130],"set":[81],"training":[83,131],"pairs":[84,132],"bring":[86],"out":[87],"subtlety":[89],"deduplication":[91,120],"function.":[92],"This":[93],"non-trivial":[95],"because":[96],"it":[97],"requires":[98],"manually":[99],"searching":[100],"for":[101],"inconsistencies":[104],"any":[106],"two":[107],"spread":[109],"apart":[110],"large":[112],"lists.We":[113],"present":[114],"our":[115],"design":[116,159],"learning-based":[119],"system":[121,166],"uses":[123],"novel":[125],"interactively":[128],"discovering":[129],"using":[133],"active":[134,143],"learning.":[135],"Our":[136],"experiments":[137],"real-life":[139],"datasets":[140],"show":[141],"learning":[144],"significantly":[145],"reduces":[146],"number":[148],"instances":[150],"needed":[151],"achieve":[153],"high":[154],"accuracy.":[155],"We":[156],"investigate":[157],"issues":[160],"arise":[162],"building":[164],"interactive":[169],"response,":[170],"fast":[171],"convergence,":[172],"interpretable":[174],"output.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2022-01-26T00:00:00"}