{"id":"https://openalex.org/W3029701880","doi":"https://doi.org/10.1145/3318464.3389743","title":"ZeroER: Entity Resolution using Zero Labeled Examples","display_name":"ZeroER: Entity Resolution using Zero Labeled Examples","publication_year":2020,"publication_date":"2020-05-29","ids":{"openalex":"https://openalex.org/W3029701880","doi":"https://doi.org/10.1145/3318464.3389743","mag":"3029701880"},"language":"en","primary_location":{"id":"doi:10.1145/3318464.3389743","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318464.3389743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.06049","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Renzhi Wu","orcid":null},"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":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sanya Chaba","orcid":null},"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":"Sanya Chaba","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Saurabh Sawlani","orcid":null},"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":"Saurabh Sawlani","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Chu","orcid":null},"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":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":null,"display_name":"Saravanan Thirumuruganathan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138380","display_name":"Qatar Cardiovascular Research Center","ror":"https://ror.org/038vyt185","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210138380"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Saravanan Thirumuruganathan","raw_affiliation_strings":["QCRI, HBKU, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"QCRI, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I4210138380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.4508,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.99214899,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1149","last_page":"1164"},"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":0.9815999865531921,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5813000202178955},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5449000000953674},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48660001158714294},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.48019999265670776},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.41850000619888306},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4178999960422516},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4129999876022339},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3912999927997589},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38359999656677246}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6171000003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5834000110626221},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5813000202178955},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45019999146461487},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.41850000619888306},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4129999876022339},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3273000121116638},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2599000036716461}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3318464.3389743","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318464.3389743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.06049","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.06049","pdf_url":"https://arxiv.org/pdf/1908.06049","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,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.06049","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.06049","pdf_url":"https://arxiv.org/pdf/1908.06049","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1494076862","https://openalex.org/W1598629391","https://openalex.org/W1799378028","https://openalex.org/W1974995373","https://openalex.org/W1981590391","https://openalex.org/W2007682403","https://openalex.org/W2024605621","https://openalex.org/W2041439319","https://openalex.org/W2047846523","https://openalex.org/W2049633694","https://openalex.org/W2053870252","https://openalex.org/W2065259291","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2079649893","https://openalex.org/W2090299879","https://openalex.org/W2096598900","https://openalex.org/W2098034668","https://openalex.org/W2110411158","https://openalex.org/W2117974736","https://openalex.org/W2119320829","https://openalex.org/W2121516976","https://openalex.org/W2143124645","https://openalex.org/W2153174381","https://openalex.org/W2164456230","https://openalex.org/W2218423201","https://openalex.org/W2399361902","https://openalex.org/W2542998387","https://openalex.org/W2798649495","https://openalex.org/W2804269561","https://openalex.org/W2893303656","https://openalex.org/W2997591727","https://openalex.org/W3011807731","https://openalex.org/W3124367822","https://openalex.org/W4238253035","https://openalex.org/W6676495512"],"related_works":[],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"(ER)":[2],"refers":[3],"to":[4,17,43,60,77,198],"the":[5,18,29,86,103,140,157,165,169],"problem":[6,53],"of":[7,37,113,121,159],"matching":[8],"records":[9],"in":[10,85,172,177],"one":[11],"or":[12],"more":[13],"relations":[14],"that":[15,40,54,67,112,155,187],"refer":[16],"same":[19],"real-world":[20],"entity.":[21],"While":[22],"supervised":[23,78,199],"machine":[24],"learning":[25,139],"(ML)":[26],"approaches":[27,193],"achieve":[28,74],"state-of-the-art":[30],"results,":[31],"they":[32],"require":[33],"a":[34,99,119,127,173],"large":[35],"amount":[36],"labeled":[38,70],"examples":[39],"are":[41],"expensive":[42],"obtain":[44],"and":[45,142,194],"often":[46],"times":[47],"infeasible.":[48],"We":[49],"investigate":[50],"an":[51,62,148],"important":[52],"vexes":[55],"practitioners:":[56],"is":[57,96],"it":[58],"possible":[59],"design":[61],"effective":[63],"algorithm":[64],"for":[65,106,138,153],"ER":[66,154,183],"requires":[68,118],"Zero":[69],"examples,":[71],"yet":[72,129],"can":[73],"performance":[75,197],"comparable":[76,196],"approaches?":[79],"In":[80],"this":[81,116],"paper,":[82],"we":[83,125,146,163,185],"answer":[84],"affirmative":[87],"through":[88],"our":[89],"proposed":[90],"approach":[91,95],"dubbed":[92],"ZeroER.":[93],"Our":[94],"based":[97,133],"on":[98,134],"simple":[100,128],"observation":[101],"---":[102],"similarity":[104],"vectors":[105],"matches":[107],"should":[108],"look":[109],"different":[110],"from":[111],"unmatches.":[114],"Operationalizing":[115],"insight":[117],"number":[120],"technical":[122],"innovations.":[123],"First,":[124],"propose":[126,147],"powerful":[130],"generative":[131,170],"model":[132,171],"Gaussian":[135],"Mixture":[136],"Models":[137],"match":[141],"unmatch":[143],"distributions.":[144],"Second,":[145],"adaptive":[149],"regularization":[150],"technique":[151],"customized":[152],"ameliorates":[156],"issue":[158],"feature":[160],"overfitting.":[161],"Finally,":[162],"incorporate":[164],"transitivity":[166],"property":[167],"into":[168],"novel":[174],"way":[175],"resulting":[176],"improved":[178],"accuracy.":[179],"On":[180],"five":[181],"benchmark":[182],"datasets,":[184],"show":[186],"ZeroER":[188],"greatly":[189],"outperforms":[190],"existing":[191],"unsupervised":[192],"achieves":[195],"approaches.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-06-05T00:00:00"}