{"id":"https://openalex.org/W4380433186","doi":"https://doi.org/10.1145/3588712","title":"Ground Truth Inference for Weakly Supervised Entity Matching","display_name":"Ground Truth Inference for Weakly Supervised Entity Matching","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4380433186","doi":"https://doi.org/10.1145/3588712"},"language":"en","primary_location":{"id":"doi:10.1145/3588712","doi":"https://doi.org/10.1145/3588712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588712","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.06975","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009874448","display_name":"Renzhi Wu","orcid":"https://orcid.org/0000-0002-9144-8999","observed_orcids":["https://orcid.org/0000-0002-9144-8999"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renzhi Wu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9144-8999","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009760836","display_name":"Alexander Bendeck","orcid":"https://orcid.org/0000-0002-9799-2194","observed_orcids":["https://orcid.org/0000-0002-9799-2194"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Bendeck","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9799-2194","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430982","display_name":"Xu Chu","orcid":"https://orcid.org/0009-0007-3202-3767","observed_orcids":["https://orcid.org/0009-0007-3202-3767"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Chu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0009-0007-3202-3767","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034908019","display_name":"Yeye He","orcid":"https://orcid.org/0000-0003-2824-5299","observed_orcids":["https://orcid.org/0000-0003-2824-5299"]},"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":"Yeye He","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2824-5299","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0909,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78887903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"1","issue":"1","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0006000000284984708,"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":0.00019999999494757503,"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/entity-resolution","display_name":"entity resolution","score":0.9919999837875366},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.9629999995231628},{"id":"https://openalex.org/keywords/labeling-functions","display_name":"labeling functions","score":0.8360000252723694},{"id":"https://openalex.org/keywords/snorkel","display_name":"snorkel","score":0.7680000066757202},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.6460000276565552},{"id":"https://openalex.org/keywords/data-annotation","display_name":"data annotation","score":0.6320000290870667},{"id":"https://openalex.org/keywords/data-linkage","display_name":"data linkage","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265777587890625},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6303996443748474},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6254889965057373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5451159477233887},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5425539612770081},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.532252311706543},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.5110770463943481},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5022187232971191},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48681947588920593},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4626081883907318},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4464721083641052},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4337017834186554},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4150685667991638},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4125107526779175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34877878427505493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18567952513694763},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3588712","doi":"https://doi.org/10.1145/3588712","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588712","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2211.06975","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.06975","pdf_url":"https://arxiv.org/pdf/2211.06975","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.06975","doi":"https://doi.org/10.48550/arxiv.2211.06975","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.06975","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.06975","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.06975","pdf_url":"https://arxiv.org/pdf/2211.06975","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380433186.pdf","grobid_xml":"https://content.openalex.org/works/W4380433186.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W114565888","https://openalex.org/W1518816191","https://openalex.org/W1593532658","https://openalex.org/W1934084512","https://openalex.org/W1981590391","https://openalex.org/W1982350890","https://openalex.org/W1990028388","https://openalex.org/W2041439319","https://openalex.org/W2067566391","https://openalex.org/W2086413055","https://openalex.org/W2096742765","https://openalex.org/W2113878109","https://openalex.org/W2119320829","https://openalex.org/W2124833832","https://openalex.org/W2139688603","https://openalex.org/W2141649520","https://openalex.org/W2143430537","https://openalex.org/W2148143831","https://openalex.org/W2158703410","https://openalex.org/W2340222647","https://openalex.org/W2398690102","https://openalex.org/W2542998387","https://openalex.org/W2585226541","https://openalex.org/W2604259521","https://openalex.org/W2769041395","https://openalex.org/W2798649495","https://openalex.org/W2798782420","https://openalex.org/W2804269561","https://openalex.org/W2893303656","https://openalex.org/W2895604144","https://openalex.org/W2911424454","https://openalex.org/W2946504770","https://openalex.org/W2952286769","https://openalex.org/W2957824372","https://openalex.org/W2964677000","https://openalex.org/W3014705052","https://openalex.org/W3022333975","https://openalex.org/W3029701880","https://openalex.org/W3030888939","https://openalex.org/W3123518987","https://openalex.org/W3123856223","https://openalex.org/W3158691555","https://openalex.org/W3170190513","https://openalex.org/W3175827219","https://openalex.org/W3198482311","https://openalex.org/W4210546623","https://openalex.org/W4221080699","https://openalex.org/W4226125558","https://openalex.org/W4235216760","https://openalex.org/W4236965008","https://openalex.org/W4242744113","https://openalex.org/W4288723898","https://openalex.org/W4394648760"],"related_works":["https://openalex.org/W7117447904","https://openalex.org/W4393166924","https://openalex.org/W4285077516","https://openalex.org/W4382239817","https://openalex.org/W1742677423","https://openalex.org/W7062198703","https://openalex.org/W7154490638","https://openalex.org/W4293238659","https://openalex.org/W3176788992","https://openalex.org/W3198482311"],"abstract_inverted_index":{"Entity":[0],"matching":[1,37,150],"(EM)":[2],"refers":[3],"to":[4,21,54,60,115,145,190,271],"the":[5,22,26,73,105,118,141,146,153,169,181,193,197,201,245,290],"problem":[6],"of":[7,10,45,102,107,148,160,196,278,280],"identifying":[8],"pairs":[9],"data":[11,62,108],"records":[12],"in":[13,25,205,217,236,294],"one":[14],"or":[15,52],"more":[16],"relational":[17],"tables":[18],"that":[19,89,192,231,252,284],"refer":[20],"same":[23],"entity":[24,149],"real":[27],"world.":[28],"Supervised":[29],"machine":[30],"learning":[31,255],"(ML)":[32],"models":[33],"currently":[34],"achieve":[35],"state-of-the-art":[36],"performance;":[38],"however,":[39],"they":[40],"require":[41],"a":[42,86,100,112,127,237,253],"large":[43],"number":[44],"labeled":[46],"examples,":[47],"which":[48],"are":[49],"often":[50],"expensive":[51],"infeasible":[53],"obtain.":[55],"This":[56],"has":[57],"inspired":[58],"us":[59],"approach":[61,189,268,286],"labeling":[63,74,82,109,113,131,142,162,182,198,233,291],"for":[64,133,184],"EM":[65,227,256],"using":[66,276],"weak":[67,135,176,266],"supervision.":[68],"In":[69,121],"particular,":[70],"we":[71,124,139,186,229],"use":[72],"function":[75,83],"abstraction":[76],"popularized":[77],"by":[78,151],"Snorkel,":[79],"where":[80,211],"each":[81],"(LF)":[84],"is":[85,164,269],"user-provided":[87],"program":[88],"can":[90,287],"generate":[91],"many":[92],"noisy":[93],"match/non-match":[94],"labels":[95,262],"quickly":[96],"and":[97,213,223],"cheaply.":[98],"Given":[99],"set":[101],"user-written":[103],"LFs,":[104],"quality":[106],"depends":[110],"on":[111,242,261],"model":[114,132,143,163,183,199,234,258,274],"accurately":[116],"infer":[117],"ground-truth":[119,281],"labels.":[120],"this":[122],"work,":[123],"first":[125],"propose":[126],"simple":[128,165],"but":[129],"powerful":[130],"general":[134,158,175],"supervision":[136,177,267],"tasks.":[137],"Then,":[138],"tailor":[140,180],"specifically":[144],"task":[147],"considering":[152],"EM-specific":[154],"transitivity":[155,202],"property.":[156],"The":[157],"form":[159],"our":[161,232,265,285],"while":[166],"substantially":[167],"outperforming":[168],"best":[170,246],"existing":[171,247],"method":[172],"across":[173],"ten":[174],"datasets.":[178],"To":[179],"EM,":[185,206],"formulate":[187],"an":[188,208,214,272],"ensure":[191],"final":[194],"predictions":[195],"satisfy":[200],"property":[203],"required":[204,293],"utilizing":[207],"exact":[209],"solution":[210],"possible":[212],"ML-based":[215],"approximation":[216],"remaining":[218],"cases.":[219],"On":[220],"two":[221],"single-table":[222],"nine":[224],"two-table":[225],"real-world":[226],"datasets,":[228],"show":[230,251],"results":[235],"9%":[238],"higher":[239],"F1":[240],"score":[241],"average":[243],"than":[244],"method.":[248],"We":[249],"also":[250],"deep":[254],"end":[257,273],"(DeepMatcher)":[259],"trained":[260,275],"generated":[263],"from":[264],"comparable":[270],"tens":[277],"thousands":[279],"labels,":[282],"demonstrating":[283],"significantly":[288],"reduce":[289],"efforts":[292],"EM.":[295]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-06-14T00:00:00"}