{"id":"https://openalex.org/W2767681556","doi":"https://doi.org/10.1145/3132847.3132949","title":"Active Learning for Large-Scale Entity Resolution","display_name":"Active Learning for Large-Scale Entity Resolution","publication_year":2017,"publication_date":"2017-11-06","ids":{"openalex":"https://openalex.org/W2767681556","doi":"https://doi.org/10.1145/3132847.3132949","mag":"2767681556"},"language":"en","primary_location":{"id":"doi:10.1145/3132847.3132949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3132949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","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/A5005099484","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0002-6765-9446"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kun Qian","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041152581","display_name":"Lucian Popa","orcid":"https://orcid.org/0000-0002-0659-9144"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucian Popa","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105422045","display_name":"Prithviraj Sen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prithviraj Sen","raw_affiliation_strings":["IBM Research - Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005099484"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":7.5435,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.97321429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1379","last_page":"1388"},"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/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.989300012588501,"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":0.8114438056945801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.694614052772522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6685369610786438},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.6103301048278809},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5931541323661804},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5916294455528259},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5432272553443909},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.516730010509491},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48947155475616455},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4867801368236542},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4531231224536896},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.42732882499694824},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4143102467060089},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.386833131313324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114438056945801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.694614052772522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6685369610786438},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.6103301048278809},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5931541323661804},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5916294455528259},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5432272553443909},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.516730010509491},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48947155475616455},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4867801368236542},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4531231224536896},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.42732882499694824},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4143102467060089},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.386833131313324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3132847.3132949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3132949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W61518770","https://openalex.org/W1496255159","https://openalex.org/W1507695921","https://openalex.org/W1528361845","https://openalex.org/W1540269031","https://openalex.org/W1835243625","https://openalex.org/W1977970897","https://openalex.org/W1982804187","https://openalex.org/W1995945562","https://openalex.org/W1999483928","https://openalex.org/W2007682403","https://openalex.org/W2024770506","https://openalex.org/W2026910242","https://openalex.org/W2042932437","https://openalex.org/W2046020929","https://openalex.org/W2052698082","https://openalex.org/W2053606499","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2065398649","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2080021732","https://openalex.org/W2090659861","https://openalex.org/W2095708598","https://openalex.org/W2106675345","https://openalex.org/W2111116800","https://openalex.org/W2119320829","https://openalex.org/W2139021951","https://openalex.org/W2139709458","https://openalex.org/W2144461918","https://openalex.org/W2156909104","https://openalex.org/W2170902582","https://openalex.org/W2171450492","https://openalex.org/W2171472464","https://openalex.org/W2244198747","https://openalex.org/W2292361954","https://openalex.org/W2409900585","https://openalex.org/W2535778619","https://openalex.org/W2951528191","https://openalex.org/W3106889297","https://openalex.org/W4230674625"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757","https://openalex.org/W2949848653"],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"(ER)":[2],"is":[3,22,38],"the":[4,11,44,66,70,89,110,120,180,195],"task":[5],"of":[6,10,51,59,122,124,179,182,197,204,209,211,224],"identifying":[7],"different":[8,150],"representations":[9],"same":[12],"real-world":[13,201],"object":[14],"across":[15],"datasets.":[16],"Designing":[17],"and":[18,83,86,229],"tuning":[19],"ER":[20,76,101,117,202],"algorithms":[21,77,102],"an":[23,165],"error-prone,":[24],"labor-intensive":[25],"process,":[26],"which":[27],"can":[28],"significantly":[29],"benefit":[30],"from":[31,151],"data-driven,":[32],"automated":[33],"learning":[34,100,106,133,144,167,216],"methods.":[35],"Our":[36],"focus":[37],"on":[39,99,200,235],"\"big":[40],"data''":[41],"scenarios":[42,203],"where":[43],"primary":[45],"challenges":[46,112],"include":[47],"1)":[48],"identifying,":[49],"out":[50],"a":[52,56,134],"potentially":[53],"massive":[54],"set,":[55],"small":[57],"subset":[58],"informative":[60],"examples":[61,72],"to":[62,73,92,107,115,186,191,207],"be":[63],"labeled":[64,71],"by":[65,113],"user,":[67],"2)":[68],"using":[69],"efficiently":[74],"learn":[75,116,219],"that":[78,147,169,218],"achieve":[79],"both":[80],"high":[81,84,187],"precision":[82,128],"recall,":[85,188],"3)":[87],"executing":[88],"learned":[90],"algorithm":[91],"determine":[93],"duplicates":[94],"at":[95,171],"scale.":[96],"Recent":[97],"work":[98,138],"has":[103,139],"employed":[104],"active":[105,166,215],"partially":[108],"address":[109],"above":[111],"aiming":[114],"rules":[118,146,174,221],"in":[119,132,143,189],"form":[121],"conjunctions":[123],"matching":[125],"predicates,":[126],"under":[127],"guarantees.":[129],"While":[130],"successful":[131,142],"single":[135],"rule,":[136],"prior":[137],"been":[140],"less":[141],"multiple":[145,173],"are":[148],"sufficiently":[149],"each":[152,175],"other,":[153],"thus":[154,184],"missing":[155],"opportunities":[156],"for":[157,227],"improving":[158],"recall.":[159],"In":[160],"this":[161],"paper,":[162],"we":[163],"introduce":[164],"system":[168,199],"learns,":[170],"scale,":[172],"having":[176],"significant":[177],"coverage":[178],"space":[181],"duplicates,":[183],"leading":[185],"addition":[190],"high-precision.":[192],"We":[193],"show":[194],"superiority":[196],"our":[198],"sizes":[205],"up":[206],"tens":[208],"millions":[210],"records,":[212],"over":[213,231],"state-of-the-art":[214],"methods":[217,233],"either":[220],"or":[222],"committees":[223],"statistical":[225],"classifiers":[226],"ER,":[228],"even":[230],"sophisticated":[232],"based":[234],"first-order":[236],"probabilistic":[237],"models.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":6}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}