{"id":"https://openalex.org/W2166983036","doi":"https://doi.org/10.1145/1519103.1519112","title":"Web-scale extraction of structured data","display_name":"Web-scale extraction of structured data","publication_year":2009,"publication_date":"2009-03-20","ids":{"openalex":"https://openalex.org/W2166983036","doi":"https://doi.org/10.1145/1519103.1519112","mag":"2166983036"},"language":"en","primary_location":{"id":"doi:10.1145/1519103.1519112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1519103.1519112","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"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":"ACM SIGMOD Record","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"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"],"raw_orcid":null,"affiliations":[{"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":19.4108,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.99106186,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":"4","first_page":"55","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9936000108718872,"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":0.9927999973297119,"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":0.8974672555923462},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6528485417366028},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6435185670852661},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.578399121761322},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5602124929428101},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.5503180623054504},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5460451245307922},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4901638925075531},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48542484641075134},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.45665302872657776},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4504663348197937},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4418785572052002},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4241119623184204},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3598174452781677},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12851229310035706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8974672555923462},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6528485417366028},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6435185670852661},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.578399121761322},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5602124929428101},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.5503180623054504},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5460451245307922},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4901638925075531},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48542484641075134},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.45665302872657776},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4504663348197937},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4418785572052002},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4241119623184204},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3598174452781677},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12851229310035706},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1519103.1519112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1519103.1519112","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"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":"ACM SIGMOD Record","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.211.3686","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.211.3686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sigmod.org/sigmod/record/issues/0812/p055.special.cafarella.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W343945789","https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1986828474","https://openalex.org/W2013970953","https://openalex.org/W2022166150","https://openalex.org/W2057052429","https://openalex.org/W2068737686","https://openalex.org/W2081948558","https://openalex.org/W2108223890","https://openalex.org/W2108267498","https://openalex.org/W2108489852","https://openalex.org/W2115461474","https://openalex.org/W2117058208","https://openalex.org/W2118356300","https://openalex.org/W2125969310","https://openalex.org/W2131006463","https://openalex.org/W2140602286","https://openalex.org/W2146304342","https://openalex.org/W2148738951","https://openalex.org/W2161344493","https://openalex.org/W2171262729","https://openalex.org/W3184666341","https://openalex.org/W6629638141","https://openalex.org/W6678605463","https://openalex.org/W6680646450","https://openalex.org/W6902931378"],"related_works":["https://openalex.org/W1495666889","https://openalex.org/W2963140294","https://openalex.org/W2100071482","https://openalex.org/W2729360854","https://openalex.org/W2780890200","https://openalex.org/W2165565716","https://openalex.org/W4249203355","https://openalex.org/W3088578348","https://openalex.org/W2121592681","https://openalex.org/W2184421161"],"abstract_inverted_index":{"A":[0],"long-standing":[1],"goal":[2],"of":[3,54,90,106,118,123],"Web":[4,12,23,52],"research":[5],"has":[6],"been":[7,127],"to":[8],"construct":[9],"a":[10,116],"unified":[11],"knowledge":[13],"base.":[14],"Information":[15],"extraction":[16,43],"techniques":[17],"have":[18,125],"shown":[19],"good":[20],"results":[21],"on":[22,49,64,73,82,96],"inputs,":[24],"but":[25],"even":[26],"most":[27],"domain-independent":[28],"ones":[29],"are":[30,130],"not":[31],"appropriate":[32],"for":[33],"Web-scale":[34],"operation.":[35],"In":[36],"this":[37],"paper":[38],"we":[39,100,114],"describe":[40,101],"three":[41,111],"recent":[42],"systems":[44],"that":[45,129],"can":[46,93],"be":[47],"operated":[48],"the":[50,69,77,104,110],"entire":[51],"(two":[53],"which":[55,124],"come":[56],"from":[57],"Google":[58],"Research).":[59],"The":[60,85],"TextRunner":[61],"system":[62,71,80],"focuses":[63,72,81],"raw":[65],"natural":[66],"language":[67],"text,":[68],"WebTables":[70],"HTML-embedded":[74],"tables,":[75],"and":[76,88],"deep-web":[78],"surfacing":[79],"\"hidden\"":[83],"databases.":[84],"domain,":[86],"expressiveness,":[87],"accuracy":[89],"extracted":[91],"data":[92,107,120],"depend":[94],"strongly":[95],"its":[97],"source":[98],"extractor;":[99],"differences":[102],"in":[103],"characteristics":[105],"produced":[108],"by":[109,132],"extractors.":[112],"Finally,":[113],"discuss":[115],"series":[117],"unique":[119],"applications":[121],"(some":[122],"already":[126],"prototyped)":[128],"enabled":[131],"aggregating":[133],"extractedWeb":[134],"information.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}