{"id":"https://openalex.org/W4379390735","doi":"https://doi.org/10.1145/3555041.3589409","title":"Table Discovery in Data Lakes: State-of-the-art and Future Directions","display_name":"Table Discovery in Data Lakes: State-of-the-art and Future Directions","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4379390735","doi":"https://doi.org/10.1145/3555041.3589409"},"language":"en","primary_location":{"id":"doi:10.1145/3555041.3589409","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3555041.3589409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","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/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":true,"raw_author_name":"Grace Fan","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346150","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0002-3172-6133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Megagon Labs, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Megagon Labs, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750716","display_name":"Yuliang Li","orcid":"https://orcid.org/0000-0002-0602-149X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuliang Li","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/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, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049651913"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":5.5465,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9602263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"75"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.991599977016449,"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":0.9905999898910522,"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":0.7998015880584717},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.782940685749054},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.6370078325271606},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6121343970298767},{"id":"https://openalex.org/keywords/data-discovery","display_name":"Data discovery","score":0.5640621185302734},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.48450085520744324},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45272165536880493},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42630481719970703},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3602006435394287},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2808476686477661},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.23224413394927979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998015880584717},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.782940685749054},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.6370078325271606},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6121343970298767},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.5640621185302734},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.48450085520744324},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45272165536880493},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42630481719970703},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3602006435394287},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2808476686477661},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.23224413394927979},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3555041.3589409","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3555041.3589409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2023 International Conference on Management of Data","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":42,"referenced_works":["https://openalex.org/W1493773376","https://openalex.org/W1721994796","https://openalex.org/W1969621019","https://openalex.org/W1972545488","https://openalex.org/W1996505782","https://openalex.org/W2066806792","https://openalex.org/W2092364718","https://openalex.org/W2111869785","https://openalex.org/W2128056631","https://openalex.org/W2140116426","https://openalex.org/W2341748398","https://openalex.org/W2440094130","https://openalex.org/W2752618741","https://openalex.org/W2798664493","https://openalex.org/W2810954846","https://openalex.org/W2889003264","https://openalex.org/W2890164255","https://openalex.org/W2941003455","https://openalex.org/W2948163032","https://openalex.org/W2962982640","https://openalex.org/W2963174348","https://openalex.org/W2963469388","https://openalex.org/W2969723769","https://openalex.org/W2970992672","https://openalex.org/W2971681342","https://openalex.org/W2986888662","https://openalex.org/W3013008430","https://openalex.org/W3014616325","https://openalex.org/W3082424964","https://openalex.org/W3094328550","https://openalex.org/W3103177583","https://openalex.org/W3174637548","https://openalex.org/W3196747654","https://openalex.org/W3196867679","https://openalex.org/W3196904276","https://openalex.org/W4205922070","https://openalex.org/W4210558765","https://openalex.org/W4283383705","https://openalex.org/W4289533971","https://openalex.org/W6753529518","https://openalex.org/W6754183483","https://openalex.org/W6774873859"],"related_works":["https://openalex.org/W2740324253","https://openalex.org/W112116702","https://openalex.org/W2910938786","https://openalex.org/W2944900003","https://openalex.org/W1601083748","https://openalex.org/W171190900","https://openalex.org/W2396520550","https://openalex.org/W3123614446","https://openalex.org/W2053529155","https://openalex.org/W2157453101"],"abstract_inverted_index":{"Data":[0],"discovery":[1,43,84,94,120,137],"refers":[2],"to":[3,14],"a":[4,35],"set":[5],"of":[6,22,38,74,136],"tasks":[7,56],"that":[8],"enable":[9],"users":[10],"and":[11,16,63,85,105,126,142],"downstream":[12],"applications":[13,100],"explore":[15],"gain":[17],"insights":[18],"from":[19],"massive":[20],"collections":[21],"data":[23,27,48,69,98],"sources":[24],"such":[25,57,101],"as":[26,58,89,91,102,130,132],"lakes.":[28],"In":[29],"this":[30],"tutorial,":[31],"we":[32,110],"will":[33,52,77,111],"provide":[34],"comprehensive":[36],"overview":[37],"the":[39,47,134],"most":[40],"recent":[41],"table":[42,54,61,64,86,93,119,128],"techniques":[44,80],"developed":[45],"by":[46,122],"management":[49],"community.":[50],"We":[51,76],"cover":[53,79],"understanding":[55],"domain":[59],"discovery,":[60],"annotation,":[62],"representation":[65],"learning":[66,104],"which":[67],"help":[68],"lake":[70],"systems":[71],"capture":[72],"semantics":[73],"tables.":[75],"also":[78],"enabling":[81],"various":[82],"query-driven":[83],"exploration":[87],"tasks,":[88],"well":[90,131],"how":[92],"can":[95],"support":[96],"key":[97],"science":[99],"machine":[103],"knowledge":[106,125],"base":[107],"construction.":[108],"Finally,":[109],"discuss":[112],"future":[113],"research":[114],"directions":[115],"on":[116],"developing":[117],"new":[118],"paradigms":[121],"combining":[123],"structured":[124],"dense":[127],"representations,":[129],"improving":[133],"efficiency":[135],"using":[138],"state-of-the-art":[139],"indexing":[140],"techniques,":[141],"more.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}