{"id":"https://openalex.org/W2775696413","doi":"https://doi.org/10.14778/3149193.3149199","title":"Synthesizing entity matching rules by examples","display_name":"Synthesizing entity matching rules by examples","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2775696413","doi":"https://doi.org/10.14778/3149193.3149199","mag":"2775696413"},"language":"en","primary_location":{"id":"doi:10.14778/3149193.3149199","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3149193.3149199","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 VLDB Endowment","raw_type":"journal-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/A5081688191","display_name":"Rohit Singh","orcid":"https://orcid.org/0000-0002-4084-7340"},"institutions":[{"id":"https://openalex.org/I2946016260","display_name":"Uber AI (United States)","ror":"https://ror.org/05vm0ed18","country_code":"US","type":"company","lineage":["https://openalex.org/I2946016260"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rohit Singh","raw_affiliation_strings":["CSAIL and Uber AI Labs"],"affiliations":[{"raw_affiliation_string":"CSAIL and Uber AI Labs","institution_ids":["https://openalex.org/I2946016260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000458112","display_name":"Venkata Vamsikrishna Meduri","orcid":"https://orcid.org/0000-0002-7054-181X"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkata Vamsikrishna Meduri","raw_affiliation_strings":["Arizona State University"],"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089912733","display_name":"Ahmed K. Elmagarmid","orcid":"https://orcid.org/0000-0002-0044-458X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Elmagarmid","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["CSAIL"],"affiliations":[{"raw_affiliation_string":"CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011336242","display_name":"Paolo Papotti","orcid":"https://orcid.org/0000-0003-0651-4128"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paolo Papotti","raw_affiliation_strings":["EURECOM, France"],"affiliations":[{"raw_affiliation_string":"EURECOM, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083942725","display_name":"Jorge-Arnulfo Quian\u00e9-Ruiz","orcid":"https://orcid.org/0000-0002-9001-825X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jorge-Arnulfo Quian\u00e9-Ruiz","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010786661","display_name":"Armando Solar-Lezama","orcid":"https://orcid.org/0000-0001-7604-8252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Armando Solar-Lezama","raw_affiliation_strings":["CSAIL"],"affiliations":[{"raw_affiliation_string":"CSAIL","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Qatar","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5081688191"],"corresponding_institution_ids":["https://openalex.org/I2946016260"],"apc_list":null,"apc_paid":null,"fwci":10.5081,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.98376489,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"11","issue":"2","first_page":"189","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9836999773979187,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.982699990272522,"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":0.6627764105796814},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6453593969345093},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5889779925346375},{"id":"https://openalex.org/keywords/disjunctive-normal-form","display_name":"Disjunctive normal form","score":0.5747330188751221},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5704070329666138},{"id":"https://openalex.org/keywords/negation","display_name":"Negation","score":0.5361032485961914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5314815044403076},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.46212291717529297},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.42903077602386475},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38286158442497253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36861878633499146},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3248540163040161},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2680152654647827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2624731957912445},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15574583411216736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6627764105796814},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6453593969345093},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5889779925346375},{"id":"https://openalex.org/C136726353","wikidata":"https://www.wikidata.org/wiki/Q903789","display_name":"Disjunctive normal form","level":2,"score":0.5747330188751221},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5704070329666138},{"id":"https://openalex.org/C2185349","wikidata":"https://www.wikidata.org/wiki/Q190558","display_name":"Negation","level":2,"score":0.5361032485961914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314815044403076},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.46212291717529297},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.42903077602386475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38286158442497253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36861878633499146},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3248540163040161},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2680152654647827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2624731957912445},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15574583411216736},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3149193.3149199","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3149193.3149199","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:fr.eurecom:5376","is_oa":false,"landing_page_url":"http://www.eurecom.fr/publication/5376","pdf_url":null,"source":{"id":"https://openalex.org/S4377196942","display_name":"Graduate School and Research Center in Digital Science (EURECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1902872","host_organization_name":"EURECOM","host_organization_lineage":["https://openalex.org/I1902872"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"VLDB 2018, 44th International Conference on Very Large Data Bases, 27-31 August 2018, Rio de Janeiro, Brazil / Proceedings of the VLDB Endowment, Vol.11, N\u00b012, August 2018
\\n","raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W13608894","https://openalex.org/W61518770","https://openalex.org/W1489527380","https://openalex.org/W1590649805","https://openalex.org/W1736726159","https://openalex.org/W1870428314","https://openalex.org/W1981590391","https://openalex.org/W2003536960","https://openalex.org/W2014327223","https://openalex.org/W2050789550","https://openalex.org/W2056748234","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2085261163","https://openalex.org/W2101234009","https://openalex.org/W2107391405","https://openalex.org/W2107966677","https://openalex.org/W2108991785","https://openalex.org/W2110711640","https://openalex.org/W2114764731","https://openalex.org/W2139077857","https://openalex.org/W2154785834","https://openalex.org/W2157060173","https://openalex.org/W2164456230","https://openalex.org/W2171472464","https://openalex.org/W2237063244","https://openalex.org/W2367397349","https://openalex.org/W2399923814","https://openalex.org/W2424628474","https://openalex.org/W2440159969","https://openalex.org/W2544486974","https://openalex.org/W2585438896","https://openalex.org/W2604399864","https://openalex.org/W2612177096","https://openalex.org/W2626106541","https://openalex.org/W2912710490","https://openalex.org/W2963233086","https://openalex.org/W2997591727","https://openalex.org/W3192343331","https://openalex.org/W4300601563","https://openalex.org/W6600533884","https://openalex.org/W6629352142","https://openalex.org/W6639283537","https://openalex.org/W6674236629","https://openalex.org/W6733170484","https://openalex.org/W6799746607"],"related_works":["https://openalex.org/W2073883415","https://openalex.org/W3108206494","https://openalex.org/W2739726746","https://openalex.org/W4242380336","https://openalex.org/W4366990902","https://openalex.org/W4317732970","https://openalex.org/W4388550696","https://openalex.org/W4313289487","https://openalex.org/W4321636153","https://openalex.org/W2141272333"],"abstract_inverted_index":{"Entity":[0],"matching":[1,16,20,65],"(EM)":[2],"is":[3,27,77],"a":[4,31,42,47,53,138],"critical":[5],"part":[6],"of":[7,24,99],"data":[8],"integration.":[9],"We":[10,136],"study":[11],"how":[12],"to":[13,34,80,89],"synthesize":[14],"entity":[15],"rules":[17,37,95,107,151,167],"from":[18,84],"positive-negative":[19,145],"examples.":[21],"The":[22,94],"core":[23],"our":[25],"solution":[26],"program":[28],"synthesis":[29,140],",":[30],"powerful":[32],"tool":[33],"automatically":[35],"generate":[36],"(or":[38],"programs)":[39],"that":[40,60,129,152,162],"satisfy":[41],"given":[43,143],"high-level":[44],"specification,":[45],"via":[46],"predefined":[48],"grammar.":[49],"This":[50],"grammar":[51],"describes":[52],"General":[54],"Boolean":[55],"Formula":[56],"(":[57,113],"GBF":[58,100],")":[59],"can":[61],"include":[62],"arbitrary":[63,86],"attribute":[64,87,92],"predicates":[66],"combined":[67],"by":[68],"conjunctions":[69],"(\u2227),":[70],"disjunctions":[71],"(\u2228)":[72],"and":[73,76,124,176,192],"negations":[74],"(\u00ac),":[75],"expressive":[78],"enough":[79],"model":[81],"EM":[82,106,150],"problems,":[83],"capturing":[85],"combinations":[88],"handling":[90],"missing":[91],"values.":[93],"in":[96,109,174],"the":[97,156],"form":[98],"are":[101,118,153,177],"more":[102,119],"concise":[103],"than":[104,121],"traditional":[105],"represented":[108],"Disjunctive":[110],"Normal":[111],"Form":[112],"DNF":[114],").":[115],"Consequently,":[116],"they":[117],"interpretable":[120,166],"decision":[122,169,183],"trees":[123,132,170,184],"other":[125,165],"machine":[126],"learning":[127],"algorithms":[128],"output":[130],"deep":[131],"with":[133,171,179,185],"many":[134],"branches.":[135],"present":[137],"new":[139],"algorithm":[141],"that,":[142],"only":[144],"examples":[146],"as":[147],"input,":[148],"synthesizes":[149],"effective":[154],"over":[155],"entire":[157],"dataset.":[158],"Extensive":[159],"experiments":[160],"show":[161],"we":[163],"outperform":[164],"(e.g.,":[168,182],"low":[172],"depth)":[173],"effectiveness,":[175],"comparable":[178],"non-interpretable":[180],"tools":[181],"high":[186],"depth,":[187],"gradient-boosting":[188],"trees,":[189],"random":[190],"forests":[191],"SVM).":[193]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}