{"id":"https://openalex.org/W2135767707","doi":"https://doi.org/10.14778/1687627.1687749","title":"Harvesting relational tables from lists on the web","display_name":"Harvesting relational tables from lists on the web","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2135767707","doi":"https://doi.org/10.14778/1687627.1687749","mag":"2135767707"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687749","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687749","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/A5074464488","display_name":"Hazem Elmeleegy","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hazem Elmeleegy","raw_affiliation_strings":["Purdue University"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"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 "],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]},{"author_position":"last","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 "],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"GOOGLE INC ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074464488"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":31.8284,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":{"value":0.99583727,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"1078","last_page":"1089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":0.9768999814987183,"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/T11719","display_name":"Data Quality and Management","score":0.9699000120162964,"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":0.8252911567687988},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.734678328037262},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6890396475791931},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5913932919502258},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.5650781989097595},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5265771746635437},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5042814016342163},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4669521749019623},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.45264390110969543},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.4385654032230377},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.26634350419044495},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2035377025604248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252911567687988},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.734678328037262},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6890396475791931},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5913932919502258},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5650781989097595},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5265771746635437},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5042814016342163},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4669521749019623},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45264390110969543},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.4385654032230377},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26634350419044495},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2035377025604248},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1687627.1687749","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687749","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:10.1.1.151.3809","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.3809","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/2/vldb09-325.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W936010977","https://openalex.org/W969384404","https://openalex.org/W1480054672","https://openalex.org/W1526421387","https://openalex.org/W1527979595","https://openalex.org/W1533571181","https://openalex.org/W1553019137","https://openalex.org/W1553704664","https://openalex.org/W1631144012","https://openalex.org/W1677189912","https://openalex.org/W1763978250","https://openalex.org/W1922751452","https://openalex.org/W1927338256","https://openalex.org/W1927863387","https://openalex.org/W1955270353","https://openalex.org/W1975946664","https://openalex.org/W1992994083","https://openalex.org/W2027864253","https://openalex.org/W2029873015","https://openalex.org/W2033339460","https://openalex.org/W2057052429","https://openalex.org/W2069388662","https://openalex.org/W2074231493","https://openalex.org/W2093189534","https://openalex.org/W2093559286","https://openalex.org/W2096496923","https://openalex.org/W2104086170","https://openalex.org/W2108223890","https://openalex.org/W2109664771","https://openalex.org/W2111408050","https://openalex.org/W2128613007","https://openalex.org/W2140116426","https://openalex.org/W2140602286","https://openalex.org/W2143309843","https://openalex.org/W2145007893","https://openalex.org/W2148738951","https://openalex.org/W2150721933","https://openalex.org/W2156147750","https://openalex.org/W2159874616","https://openalex.org/W2160196229","https://openalex.org/W2166407869","https://openalex.org/W2171364811","https://openalex.org/W2200414440","https://openalex.org/W2201579119","https://openalex.org/W2207914665","https://openalex.org/W2209211805","https://openalex.org/W2231551935","https://openalex.org/W2265995408","https://openalex.org/W2278153051","https://openalex.org/W2295751658","https://openalex.org/W2299467510","https://openalex.org/W4233527139","https://openalex.org/W4285719527","https://openalex.org/W6633154970","https://openalex.org/W6676373471","https://openalex.org/W6680646450"],"related_works":["https://openalex.org/W4281971614","https://openalex.org/W3007479582","https://openalex.org/W3121299875","https://openalex.org/W1566754092","https://openalex.org/W3123744736","https://openalex.org/W4226523698","https://openalex.org/W2131131934","https://openalex.org/W1519332147","https://openalex.org/W2070384782","https://openalex.org/W3123448197"],"abstract_inverted_index":{"A":[0],"large":[1,202],"number":[2],"of":[3,12,97,129,185,204,214,230,232],"web":[4,170],"pages":[5],"contain":[6],"data":[7],"structured":[8],"in":[9,29,87,157],"the":[10,109,135,158,178,183,210,215,242],"form":[11],"\"lists\".":[13],"Many":[14],"such":[15,39],"lists":[16,40,47,171,173,207,240],"can":[17,25,41],"be":[18,27,42,228],"further":[19],"split":[20,100],"into":[21,103],"multi-column":[22],"tables,":[23,131],"which":[24],"then":[26,107],"used":[28],"more":[30],"semantically":[31],"meaningful":[32],"tasks.":[33],"However,":[34],"harvesting":[35],"relational":[36,236],"tables":[37,78,176,190,217,237],"from":[38,79,134,175,209,239],"a":[43,73,88,127,201],"challenging":[44],"task.":[45],"The":[46,81,180,212],"are":[48,225],"manually":[49],"generated":[50],"and":[51,66,85,106,116,120,141,172,234],"hence":[52],"need":[53],"not":[54],"have":[55,61,68,218],"well":[56],"defined":[57],"templates":[58],"--":[59],"they":[60],"inconsistent":[62],"delimiters":[63],"(if":[64],"any)":[65],"often":[67],"missing":[69],"information.":[70],"We":[71,92,161],"propose":[72],"novel":[74],"technique":[75,82,187,199],"for":[76],"extracting":[77],"lists.":[80],"is":[83],"domain-independent":[84],"operates":[86],"fully":[89],"unsupervised":[90],"manner.":[91],"first":[93],"use":[94],"multiple":[95,104,112],"sources":[96],"information":[98],"to":[99,114,137,188,221,227],"individual":[101],"lines":[102,113],"fields,":[105],"compare":[108],"splits":[110,119],"across":[111],"identify":[115,138],"fix":[117],"incorrect":[118],"bad":[121],"alignments.":[122,143],"In":[123,194],"particular,":[124],"we":[125,148,196],"exploit":[126],"corpus":[128],"HTML":[130],"also":[132],"extracted":[133,146,216],"Web,":[136],"likely":[139,226],"fields":[140],"good":[142],"For":[144],"each":[145],"table,":[147],"compute":[149],"an":[150,163],"extraction":[151],"score":[152],"that":[153,223],"reflects":[154],"our":[155,186,198],"confidence":[156],"table's":[159],"quality.":[160],"conducted":[162],"extensive":[164],"experimental":[165],"study":[166],"using":[167],"both":[168],"real":[169],"derived":[174],"on":[177,200,241],"Web.":[179,211,243],"experiments":[181],"demonstrate":[182],"ability":[184],"extract":[189],"with":[191],"high":[192],"accuracy.":[193],"addition,":[195],"applied":[197],"sample":[203],"about":[205],"100,000":[206],"crawled":[208],"analysis":[213],"led":[219],"us":[220],"believe":[222],"there":[224],"tens":[229],"millions":[231],"useful":[233],"query-able":[235],"extractable":[238]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":15}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
