{"id":"https://openalex.org/W2092364718","doi":"https://doi.org/10.14778/2002938.2002939","title":"Recovering semantics of tables on the web","display_name":"Recovering semantics of tables on the web","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2092364718","doi":"https://doi.org/10.14778/2002938.2002939","mag":"2092364718"},"language":"en","primary_location":{"id":"doi:10.14778/2002938.2002939","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2002938.2002939","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/A5067988262","display_name":"Petros Venetis","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petros Venetis","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067621853","display_name":"Alon Halevy","orcid":"https://orcid.org/0000-0002-8717-7356"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Halevy","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034699810","display_name":"Jayant Madhavan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayant Madhavan","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103731322","display_name":"Marius Pa\u015fca","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marius Pa\u015fca","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110502431","display_name":"Warren Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren Shen","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008408613","display_name":"Gengxin Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gengxin Miao","raw_affiliation_strings":["UC Santa Barbara","UC, Santa Barbara#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Santa Barbara","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"UC, Santa Barbara#TAB#","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109488110","display_name":"Chung Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung Wu","raw_affiliation_strings":["Google Inc","GOOGLE INC "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":98.1128,"has_fulltext":false,"cited_by_count":342,"citation_normalized_percentile":{"value":0.99930841,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"4","issue":"9","first_page":"528","last_page":"538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7802819609642029},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6019432544708252},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.5764127373695374},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5269116759300232},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5142406821250916},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4939456582069397},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.4695205092430115},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45708417892456055},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45079994201660156},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.4505194425582886},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3917301893234253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35826927423477173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34936538338661194},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2377447485923767}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802819609642029},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6019432544708252},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.5764127373695374},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5269116759300232},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5142406821250916},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4939456582069397},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.4695205092430115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45708417892456055},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45079994201660156},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.4505194425582886},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3917301893234253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35826927423477173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34936538338661194},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2377447485923767},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2002938.2002939","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2002938.2002939","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:CiteSeerX.psu:10.1.1.228.830","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/vol4/p528-venetis.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W32369653","https://openalex.org/W157725869","https://openalex.org/W1493490255","https://openalex.org/W1553019137","https://openalex.org/W1572864191","https://openalex.org/W1732744741","https://openalex.org/W1965893683","https://openalex.org/W2008375984","https://openalex.org/W2022166150","https://openalex.org/W2057052429","https://openalex.org/W2068737686","https://openalex.org/W2087347434","https://openalex.org/W2088762045","https://openalex.org/W2104987630","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2116429057","https://openalex.org/W2124067180","https://openalex.org/W2126539437","https://openalex.org/W2127761948","https://openalex.org/W2135767707","https://openalex.org/W2135843243","https://openalex.org/W2137023796","https://openalex.org/W2140116426","https://openalex.org/W2140602286","https://openalex.org/W2142305207","https://openalex.org/W2144108169","https://openalex.org/W2145007893","https://openalex.org/W2168596788","https://openalex.org/W6629638141","https://openalex.org/W6633154970","https://openalex.org/W6680646450","https://openalex.org/W6680720543","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W3007479582","https://openalex.org/W3121299875","https://openalex.org/W1566754092","https://openalex.org/W3123744736","https://openalex.org/W1505848319","https://openalex.org/W953130165","https://openalex.org/W4214886263","https://openalex.org/W1992086467","https://openalex.org/W2144839430","https://openalex.org/W2368939071"],"abstract_inverted_index":{"The":[0,92],"Web":[1,206],"offers":[2],"a":[3,43,80,108,112,115,142,155,165,171],"corpus":[4],"of":[5,14,51,76,82,94,118,132,173,179,202],"over":[6],"100":[7],"million":[8],"tables":[9,52,68,203],"[6],":[10],"but":[11,102],"the":[12,21,35,49,55,90,119,122,130,177,180,205],"meaning":[13],"each":[15],"table":[16,22,56,184],"is":[17,103],"rarely":[18],"explicit":[19],"from":[20,89],"itself.":[23],"Header":[24],"rows":[25],"exist":[26],"in":[27,121,129],"few":[28],"cases":[29],"and":[30,69,85,96,135,157,186],"even":[31],"when":[32,148],"they":[33],"do,":[34],"attribute":[36],"names":[37],"are":[38,124],"typically":[39],"useless.":[40],"We":[41,106,140,169],"describe":[42,141,170],"system":[44],"that":[45,127,159,175,188],"attempts":[46],"to":[47,111],"recover":[48,74],"semantics":[50,75,182],"by":[53],"enriching":[54],"with":[57,126],"additional":[58],"annotations.":[59],"Our":[60],"annotations":[61],"facilitate":[62],"operations":[63],"such":[64],"as":[65],"searching":[66],"for":[67,137,145,154,183],"finding":[70],"related":[71],"tables.":[72],"To":[73],"tables,":[77],"we":[78,149,198],"leverage":[79],"database":[81,93,131],"class":[83,109,133],"labels":[84],"relationships":[86,97],"automatically":[87],"extracted":[88],"Web.":[91],"classes":[95],"has":[98],"very":[99],"wide":[100],"coverage,":[101],"also":[104],"noisy.":[105],"attach":[107],"label":[110,128],"column":[113,123],"if":[114],"sufficient":[116,152],"number":[117],"values":[120],"identified":[125],"labels,":[134],"analogously":[136],"binary":[138],"relationships.":[139],"formal":[143],"model":[144],"reasoning":[146],"about":[147],"have":[150],"seen":[151],"evidence":[153],"label,":[156],"show":[158,187],"it":[160,189],"performs":[161,190],"substantially":[162,191],"better":[163,192],"than":[164,193],"simple":[166],"majority":[167],"scheme.":[168],"set":[172],"experiments":[174],"illustrate":[176],"utility":[178],"recovered":[181],"search":[185],"previous":[194],"approaches.":[195],"In":[196],"addition,":[197],"characterize":[199],"what":[200],"fraction":[201],"on":[204],"can":[207],"be":[208],"annotated":[209],"using":[210],"our":[211],"approach.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":35},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":30},{"year":2015,"cited_by_count":37},{"year":2014,"cited_by_count":30},{"year":2013,"cited_by_count":31},{"year":2012,"cited_by_count":19}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}