{"id":"https://openalex.org/W2108223890","doi":"https://doi.org/10.14778/1453856.1453916","title":"WebTables","display_name":"WebTables","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2108223890","doi":"https://doi.org/10.14778/1453856.1453916","mag":"2108223890"},"language":"en","primary_location":{"id":"doi:10.14778/1453856.1453916","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453916","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/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Cafarella","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"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., Mountain View, CA","Google Inc., Mountain View, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountain View, CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003464266","display_name":"Daisy Zhe Wang","orcid":"https://orcid.org/0009-0003-8234-5482"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daisy Zhe Wang","raw_affiliation_strings":["UC Berkeley, Berkeley, CA","UC Berkeley, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]},{"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":"Eugene Wu","raw_affiliation_strings":["MIT, Cambridge, MA","MIT, Cambridge, Ma.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT, Cambridge, Ma.#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100354667","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-3111-1534"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]},{"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":"Yang Zhang","raw_affiliation_strings":["MIT, Cambridge, MA","MIT, Cambridge, Ma.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT, Cambridge, Ma.#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":110.3388,"has_fulltext":false,"cited_by_count":634,"citation_normalized_percentile":{"value":0.99950971,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"1","issue":"1","first_page":"538","last_page":"549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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/T11719","display_name":"Data Quality and Management","score":0.9987000226974487,"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":0.9983000159263611,"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":0.8280775547027588},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7058329582214355},{"id":"https://openalex.org/keywords/information-schema","display_name":"Information schema","score":0.6461541056632996},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.6099634766578674},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5388611555099487},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.5157385468482971},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3985927700996399},{"id":"https://openalex.org/keywords/semi-structured-model","display_name":"Semi-structured model","score":0.36694324016571045},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.3422292470932007},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.1166205108165741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280775547027588},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7058329582214355},{"id":"https://openalex.org/C150012506","wikidata":"https://www.wikidata.org/wiki/Q6031185","display_name":"Information schema","level":5,"score":0.6461541056632996},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.6099634766578674},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5388611555099487},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.5157385468482971},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3985927700996399},{"id":"https://openalex.org/C56310702","wikidata":"https://www.wikidata.org/wiki/Q2269281","display_name":"Semi-structured model","level":4,"score":0.36694324016571045},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.3422292470932007},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.1166205108165741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1453856.1453916","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1453856.1453916","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W58719989","https://openalex.org/W72943092","https://openalex.org/W147286453","https://openalex.org/W204601728","https://openalex.org/W1489949474","https://openalex.org/W1567365482","https://openalex.org/W1570448133","https://openalex.org/W1574901103","https://openalex.org/W1593045043","https://openalex.org/W1595439448","https://openalex.org/W1965605789","https://openalex.org/W1971684273","https://openalex.org/W1984477806","https://openalex.org/W1988217119","https://openalex.org/W2008896880","https://openalex.org/W2044515729","https://openalex.org/W2053414435","https://openalex.org/W2078206655","https://openalex.org/W2085498649","https://openalex.org/W2092772700","https://openalex.org/W2098388305","https://openalex.org/W2102189859","https://openalex.org/W2108126629","https://openalex.org/W2108267498","https://openalex.org/W2109664771","https://openalex.org/W2110686900","https://openalex.org/W2115461474","https://openalex.org/W2117510361","https://openalex.org/W2121350579","https://openalex.org/W2124576009","https://openalex.org/W2139135093","https://openalex.org/W2140602286","https://openalex.org/W2150365753","https://openalex.org/W2159637323","https://openalex.org/W2161344493","https://openalex.org/W2294859229","https://openalex.org/W2966207845","https://openalex.org/W6602439768","https://openalex.org/W6605996862","https://openalex.org/W6635635861","https://openalex.org/W6676373471","https://openalex.org/W6680506379","https://openalex.org/W6680646450"],"related_works":["https://openalex.org/W2090626944","https://openalex.org/W2007556552","https://openalex.org/W2153455914","https://openalex.org/W2121229754","https://openalex.org/W2766698234","https://openalex.org/W2911768431","https://openalex.org/W1995017804","https://openalex.org/W1905261690","https://openalex.org/W945629821","https://openalex.org/W2460926837"],"abstract_inverted_index":{"The":[0,72],"World-Wide":[1],"Web":[2],"consists":[3],"of":[4,8,20,57,75,92,107,146,188],"a":[5,68,132,144,161,168,209,235],"huge":[6,133],"number":[7],"unstructured":[9],"documents,":[10],"but":[11],"it":[12],"also":[13],"contains":[14],"structured":[15,70,117],"data":[16,118],"in":[17],"the":[18,41,96,173,176,197],"form":[19],"HTML":[21,27],"tables.":[22],"We":[23,94],"extracted":[24,240],"14.1":[25],"billion":[26],"tables":[28],"from":[29,172],"Google's":[30],"general-purpose":[31],"web":[32],"crawl,":[33],"and":[34,59,148,229],"used":[35],"statistical":[36],"classification":[37],"techniques":[38,113,139],"to":[39,99,193,212,237],"find":[40],"estimated":[42],"154M":[43],"that":[44,150,182],"contain":[45],"high-quality":[46],"relational":[47,51],"data.":[48],"Because":[49],"each":[50,62],"table":[52,64],"has":[53],"its":[54],"own":[55],"\"schema\"":[56],"labeled":[58],"typed":[60],"columns,":[61],"such":[63,131],"can":[65,126,152],"be":[66,127],"considered":[67],"small":[69],"database.":[71],"resulting":[73],"corpus":[74,82,145],"databases":[76],"is":[77],"larger":[78],"than":[79,157],"any":[80],"other":[81],"we":[83,136,166],"are":[84,111],"aware":[85],"of,":[86],"by":[87,129],"at":[88,119],"least":[89],"five":[90],"orders":[91],"magnitude.":[93],"describe":[95],"WEBTABLES":[97],"system":[98],"explore":[100],"two":[101],"fundamental":[102],"questions":[103],"about":[104],"this":[105],"collection":[106],"databases.":[108],"First,":[109,135],"what":[110,123],"effective":[112],"for":[114,116,140,226],"searching":[115],"search-engine":[120],"scales?":[121],"Second,":[122,165],"additional":[124],"power":[125],"derived":[128,171],"analyzing":[130],"corpus?":[134],"develop":[137],"new":[138,169],"keyword":[141],"search":[142,163,195],"over":[143],"tables,":[147],"show":[149],"they":[151],"achieve":[153],"substantially":[154],"higher":[155],"relevance":[156],"solutions":[158],"based":[159],"on":[160,186],"traditional":[162],"engine.":[164],"introduce":[167],"object":[170],"database":[174,180,210],"corpus:":[175],"attribute":[177,216,223],"correlation":[178],"statistics":[179,185],"(AcsDB)":[181],"records":[183],"corpus-wide":[184],"co-occurrences":[187],"schema":[189,204,214,227],"elements.":[190],"In":[191],"addition":[192],"improving":[194],"relevance,":[196],"AcsDB":[198],"makes":[199],"possible":[200],"several":[201],"novel":[202],"applications:":[203],"auto-complete":[205],",":[206,219,232],"which":[207,220,233],"helps":[208],"designer":[211],"choose":[213],"elements;":[215],"synonym":[217,224],"finding":[218],"automatically":[221],"computes":[222],"pairs":[225],"matching;":[228],"join-graph":[230],"traversal":[231],"allows":[234],"user":[236],"navigate":[238],"between":[239],"schemas":[241],"using":[242],"automatically-generated":[243],"join":[244],"links.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":44},{"year":2018,"cited_by_count":44},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":43},{"year":2015,"cited_by_count":51},{"year":2014,"cited_by_count":40},{"year":2013,"cited_by_count":57},{"year":2012,"cited_by_count":34}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}