{"id":"https://openalex.org/W2951621897","doi":"https://doi.org/10.1145/3292500.3330993","title":"Sherlock","display_name":"Sherlock","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2951621897","doi":"https://doi.org/10.1145/3292500.3330993","mag":"2951621897"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"preprint","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/A5058441702","display_name":"Madelon Hulsebos","orcid":"https://orcid.org/0000-0002-0949-7290"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Madelon Hulsebos","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006392683","display_name":"Kevin Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Hu","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035791917","display_name":"Michiel A. Bakker","orcid":"https://orcid.org/0000-0003-4474-7109"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bakker","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069672953","display_name":"Emanuel Zgraggen","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emanuel Zgraggen","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077783676","display_name":"Arvind Satyanarayan","orcid":"https://orcid.org/0000-0001-5564-635X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvind Satyanarayan","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027360874","display_name":"\u00c7a\u011fatay Demiralp","orcid":"https://orcid.org/0009-0003-2080-0443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00c7agatay Demiralp","raw_affiliation_strings":["Megagon Labs, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064297795","display_name":"C\u00e9sar A. Hidalgo","orcid":"https://orcid.org/0000-0002-6977-9492"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C\u00e9sar Hidalgo","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5058441702"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":10.115,"has_fulltext":false,"cited_by_count":167,"citation_normalized_percentile":{"value":0.98472185,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1500","last_page":"1508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9937000274658203,"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":0.8458878993988037},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7634534239768982},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.7405855059623718},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.6505630612373352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6036233901977539},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5662946701049805},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5661311745643616},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5221538543701172},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5044845342636108},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4600178897380829},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4398975074291229},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24772092700004578},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.13291692733764648},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11566969752311707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458878993988037},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7634534239768982},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.7405855059623718},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6505630612373352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6036233901977539},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5662946701049805},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5661311745643616},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5221538543701172},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5044845342636108},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4600178897380829},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4398975074291229},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24772092700004578},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.13291692733764648},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11566969752311707},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330993","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292500.3330993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W1501251778","https://openalex.org/W2008896880","https://openalex.org/W2028742638","https://openalex.org/W2064766209","https://openalex.org/W2092364718","https://openalex.org/W2094728533","https://openalex.org/W2101234009","https://openalex.org/W2106895292","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2131744502","https://openalex.org/W2151401338","https://openalex.org/W2187252142","https://openalex.org/W2250539671","https://openalex.org/W2255747889","https://openalex.org/W2275294428","https://openalex.org/W2407487288","https://openalex.org/W2522154031","https://openalex.org/W2604190938","https://openalex.org/W2789111643","https://openalex.org/W2795089200","https://openalex.org/W2795302121","https://openalex.org/W2798546256","https://openalex.org/W2941366772","https://openalex.org/W2993820083","https://openalex.org/W6630077386"],"related_works":["https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W153377533","https://openalex.org/W1571902268","https://openalex.org/W2548028074","https://openalex.org/W2371267901","https://openalex.org/W1528218860","https://openalex.org/W2029826694","https://openalex.org/W2161265250","https://openalex.org/W3206360718"],"abstract_inverted_index":{"Correctly":[0],"detecting":[1,70],"the":[2,82,104,137],"semantic":[3,40,71,88],"type":[4],"of":[5,59,114,123,127,139],"data":[6,11,17,22,25,52,78],"columns":[7,79],"is":[8],"crucial":[9],"for":[10,69],"science":[12],"tasks":[13],"such":[14],"as":[15],"automated":[16],"cleaning,":[18],"schema":[19],"matching,":[20],"and":[21,27,34,53,111,132,136],"discovery.":[23],"Existing":[24],"preparation":[26],"analysis":[28],"systems":[29],"rely":[30],"on":[31,76],"dictionary":[32,131],"lookups":[33],"regular":[35,133],"expression":[36,134],"matching":[37,86],"to":[38,50,92],"detect":[39,55],"types.":[41,60,72],"However,":[42],"these":[43],"matching-based":[44],"approaches":[45],"often":[46],"are":[47],"not":[48],"robust":[49],"dirty":[51],"only":[54],"a":[56,64,119],"limited":[57],"number":[58],"We":[61,73,95],"introduce":[62],"Sherlock,":[63],"multi-input":[65],"deep":[66],"neural":[67],"network":[68],"train":[74],"Sherlock":[75,117],"$686,765$":[77],"retrieved":[80],"from":[81,90],"VizNet":[83],"corpus":[84],"by":[85],"$78$":[87],"types":[89],"DBpedia":[91],"column":[93,99,115],"headers.":[94],"characterize":[96],"each":[97],"matched":[98],"with":[100],"$1,588$":[101],"features":[102],"describing":[103],"statistical":[105],"properties,":[106],"character":[107],"distributions,":[108],"word":[109],"embeddings,":[110],"paragraph":[112],"vectors":[113],"values.":[116],"achieves":[118],"support-weighted":[120],"F$_1$":[121],"score":[122],"$0.89$,":[124],"exceeding":[125],"that":[126],"machine":[128],"learning":[129],"baselines,":[130],"benchmarks,":[135],"consensus":[138],"crowdsourced":[140],"annotations.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2019-06-27T00:00:00"}