{"id":"https://openalex.org/W4380433117","doi":"https://doi.org/10.1145/3588689","title":"SANTOS: Relationship-based Semantic Table Union Search","display_name":"SANTOS: Relationship-based Semantic Table Union Search","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4380433117","doi":"https://doi.org/10.1145/3588689"},"language":"en","primary_location":{"id":"doi:10.1145/3588689","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588689","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,"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"},"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/A5047161025","display_name":"Aamod Khatiwada","orcid":"https://orcid.org/0000-0001-5720-1207"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aamod Khatiwada","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0001-5720-1207","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049651913","display_name":"Grace Fan","orcid":"https://orcid.org/0000-0001-9020-3642"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Fan","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0001-9020-3642","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002899918","display_name":"Roee Shraga","orcid":"https://orcid.org/0000-0001-8803-8481"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roee Shraga","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0001-8803-8481","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103115509","display_name":"Zixuan Chen","orcid":"https://orcid.org/0000-0003-2872-1865"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zixuan Chen","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0003-2872-1865","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086781628","display_name":"Wolfgang Gatterbauer","orcid":"https://orcid.org/0000-0002-9614-0504"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wolfgang Gatterbauer","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-9614-0504","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ren\u00e9e J. Miller","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-1484-4787","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049802784","display_name":"Mirek Riedewald","orcid":"https://orcid.org/0000-0002-6102-7472"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirek Riedewald","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-6102-7472","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047161025"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":12.3278,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.98931981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"1","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9983999729156494,"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":0.9965999722480774,"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":0.7490905523300171},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7328760623931885},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.642795205116272},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6383228302001953},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5789680480957031},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5597215890884399},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5391630530357361},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.5388926863670349},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47252848744392395},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.430332750082016},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4196779131889343},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3360707759857178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25680702924728394},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.22448348999023438},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1669931411743164},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15358498692512512},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12224686145782471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490905523300171},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7328760623931885},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.642795205116272},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6383228302001953},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5789680480957031},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5597215890884399},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5391630530357361},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5388926863670349},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47252848744392395},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.430332750082016},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4196779131889343},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3360707759857178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25680702924728394},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.22448348999023438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1669931411743164},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15358498692512512},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12224686145782471},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588689","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588689","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,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7379858174","display_name":null,"funder_award_id":"IIS-1956096, IIS-2107248 and IIS-1762268","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1607198972","https://openalex.org/W1969621019","https://openalex.org/W1976022204","https://openalex.org/W1985697096","https://openalex.org/W2020022499","https://openalex.org/W2073414385","https://openalex.org/W2092364718","https://openalex.org/W2111869785","https://openalex.org/W2140116426","https://openalex.org/W2144211451","https://openalex.org/W2341748398","https://openalex.org/W2425316268","https://openalex.org/W2529049456","https://openalex.org/W2563663650","https://openalex.org/W2752618741","https://openalex.org/W2795302121","https://openalex.org/W2798664493","https://openalex.org/W2810954846","https://openalex.org/W2889003264","https://openalex.org/W2904530076","https://openalex.org/W2926805670","https://openalex.org/W2951621897","https://openalex.org/W2963174348","https://openalex.org/W2970992672","https://openalex.org/W2971681342","https://openalex.org/W3010336026","https://openalex.org/W3013008430","https://openalex.org/W3013082216","https://openalex.org/W3014616325","https://openalex.org/W3032215537","https://openalex.org/W3082424964","https://openalex.org/W3094328550","https://openalex.org/W3103177583","https://openalex.org/W3141398051","https://openalex.org/W3145728363","https://openalex.org/W3167537240","https://openalex.org/W3196185722","https://openalex.org/W4205922070","https://openalex.org/W6753529518"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2010935248"],"abstract_inverted_index":{"Existing":[0],"techniques":[1],"for":[2,221],"unionable":[3],"table":[4,27,51],"search":[5,151,159,186],"define":[6],"unionability":[7,67,150],"using":[8,219],"metadata":[9],"(tables":[10],"must":[11],"have":[12],"the":[13,23,32,40,54,57,75,93,109,120,182],"same":[14,33],"or":[15,18],"similar":[16],"schemas)":[17],"column-based":[19,166],"metrics":[20],"(for":[21],"example,":[22],"values":[24],"in":[25,49,79,196],"a":[26,50,63,80,114,156,162,204],"should":[28],"be":[29,194],"drawn":[30],"from":[31,119,211],"domain).":[34],"In":[35],"this":[36],"work,":[37],"we":[38,61,86,112],"introduce":[39,62],"use":[41],"of":[42,47,56,66,77,98,165,184,207],"semantic":[43,94],"relationships":[44,70,95],"between":[45,71,96],"pairs":[46,97],"columns":[48],"to":[52,91],"improve":[53],"accuracy":[55,183],"union":[58,158,185,222],"search.":[59,223],"Consequently,":[60],"new":[64,89,134,149],"notion":[65],"that":[68,137,147,160,177,191],"considers":[69],"columns,":[72,78],"together":[73],"with":[74,214],"semantics":[76,190],"principled":[81],"way.":[82],"To":[83],"do":[84],"so,":[85],"present":[87,133],"two":[88],"methods":[90],"discover":[92],"columns.":[99],"The":[100],"first":[101],"uses":[102,117,161],"an":[103,126,197],"existing":[104,127],"knowledge":[105,118],"base":[106],"(KB),":[107],"and":[108,132,140,171,218],"second":[110],"(which":[111],"call":[113],"\"synthesized":[115],"KB\")":[116],"data":[121,143,212],"lake":[122],"itself.":[123],"We":[124,145,174],"adopt":[125],"Table":[128],"Union":[129],"Search":[130],"benchmark":[131],"(open)":[135],"benchmarks":[136],"represent":[138],"small":[139],"large":[141],"real":[142],"lakes.":[144],"show":[146,175],"our":[148,178],"algorithm,":[152],"called":[153],"SANTOS,":[154],"outperforms":[155],"state-of-the-art":[157],"wide":[163],"variety":[164],"semantics,":[167],"including":[168],"word":[169],"embeddings":[170],"regular":[172],"expressions.":[173],"empirically":[176],"synthesized":[179,209],"KB":[180,216],"improves":[181],"by":[187],"representing":[188],"relationship":[189],"may":[192],"not":[193],"contained":[195],"available":[198],"KB.":[199],"This":[200],"result":[201],"hints":[202],"at":[203],"promising":[205],"future":[206],"creating":[208],"KBs":[210],"lakes":[213],"limited":[215],"coverage":[217],"them":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}