{"id":"https://openalex.org/W4387848992","doi":"https://doi.org/10.1145/3583780.3614750","title":"NumJoin: Discovering Numeric Joinable Tables with Semantically Related Columns","display_name":"NumJoin: Discovering Numeric Joinable Tables with Semantically Related Columns","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387848992","doi":"https://doi.org/10.1145/3583780.3614750"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3614750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3614750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International 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/A5087558180","display_name":"Pranav Subramaniam","orcid":"https://orcid.org/0009-0005-4684-0501"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pranav Subramaniam","raw_affiliation_strings":["The University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"The University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013455098","display_name":"Udayan Khurana","orcid":"https://orcid.org/0000-0001-8113-1210"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Udayan Khurana","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085594669","display_name":"Kavitha Srinivas","orcid":"https://orcid.org/0000-0003-4610-967X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kavitha Srinivas","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035277014","display_name":"Horst Samulowitz","orcid":"https://orcid.org/0000-0002-6780-3217"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Horst Samulowitz","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087558180"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":0.7563,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75493262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5096","last_page":"5100"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9948999881744385,"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":0.8227295875549316},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7422188520431519},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.5686672925949097},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.511298418045044},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4987647533416748},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46775293350219727},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4414500892162323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16981661319732666},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16116118431091309}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227295875549316},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7422188520431519},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5686672925949097},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.511298418045044},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4987647533416748},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46775293350219727},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4414500892162323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16981661319732666},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16116118431091309},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3614750","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3614750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2616147950","https://openalex.org/W2795302121","https://openalex.org/W2904530076","https://openalex.org/W2948163032","https://openalex.org/W2963174348","https://openalex.org/W3037852608","https://openalex.org/W3108851861","https://openalex.org/W3170190513","https://openalex.org/W3208057978","https://openalex.org/W4280609432","https://openalex.org/W4285335450","https://openalex.org/W4297950604","https://openalex.org/W4301461621","https://openalex.org/W4303449483","https://openalex.org/W4375928372","https://openalex.org/W4385653220"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W650102067","https://openalex.org/W1550806730","https://openalex.org/W2589740103","https://openalex.org/W2172084996","https://openalex.org/W1966967794","https://openalex.org/W1501284171","https://openalex.org/W2397450670"],"abstract_inverted_index":{"Join":[0],"discovery":[1,54],"is":[2,48],"a":[3,49,70,83,108],"crucial":[4],"part":[5],"of":[6,105],"exploration":[7],"on":[8,107],"data":[9,22,84,110,114],"lakes.":[10],"It":[11],"often":[12,24],"involves":[13],"finding":[14],"joinable":[15,80],"tables":[16,27,47,81,89],"that":[17,73,87,95],"are":[18],"semantically":[19,42],"relevant.":[20],"However,":[21],"lakes":[23],"contain":[25],"numeric":[26,46,63,97],"with":[28],"unreliable":[29],"column":[30],"headers,":[31],"and":[32,93,99,115],"ID":[33],"columns":[34],"whose":[35],"text":[36],"names":[37],"have":[38],"been":[39],"lost.":[40],"Finding":[41],"relevant":[43],"joins":[44],"over":[45],"challenge.":[50],"State-of-the-art":[51],"describes":[52],"join":[53],"using":[55],"semantic":[56],"similarity,":[57],"but":[58],"do":[59],"not":[60],"consider":[61],"purely":[62],"tables.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"describe":[69],"system,":[71],"NumJoin":[72,106],"includes":[74],"two":[75],"novel":[76],"approaches":[77],"for":[78],"discovering":[79],"in":[82],"lake:":[85],"one":[86],"maps":[88],"to":[90],"knowledge":[91],"graphs,":[92],"another":[94],"leverages":[96],"types":[98],"distributions.":[100],"We":[101],"demonstrate":[102],"the":[103],"effectiveness":[104],"large":[109],"lake,":[111],"including":[112],"transportation":[113],"finance":[116],"data.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}