{"id":"https://openalex.org/W2296164608","doi":"https://doi.org/10.14778/2733085.2733091","title":"DIADEM","display_name":"DIADEM","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2296164608","doi":"https://doi.org/10.14778/2733085.2733091","mag":"2296164608"},"language":"en","primary_location":{"id":"doi:10.14778/2733085.2733091","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2733085.2733091","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/A5113511969","display_name":"Tim Furche","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Furche","raw_affiliation_strings":["Oxford University, Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050151740","display_name":"Georg Gottlob","orcid":"https://orcid.org/0000-0002-2353-5230"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georg Gottlob","raw_affiliation_strings":["Oxford University, Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036346128","display_name":"Giovanni Grasso","orcid":"https://orcid.org/0000-0002-4350-0115"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giovanni Grasso","raw_affiliation_strings":["Oxford University, Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013956365","display_name":"Xiaonan Guo","orcid":"https://orcid.org/0000-0002-5001-5636"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaonan Guo","raw_affiliation_strings":["Oxford University, Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008165294","display_name":"Giorgio Orsi","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giorgio Orsi","raw_affiliation_strings":["Oxford University, Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051365299","display_name":"Christian Schallhart","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christian Schallhart","raw_affiliation_strings":["Oxford University, Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101782462","display_name":"Cheng Wang","orcid":"https://orcid.org/0000-0003-0101-3949"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cheng Wang","raw_affiliation_strings":["Oxford University, Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":28.8813,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.99446792,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"7","issue":"14","first_page":"1845","last_page":"1856"},"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/T11719","display_name":"Data Quality and Management","score":0.9865000247955322,"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/T13976","display_name":"Web visibility and informetrics","score":0.9811999797821045,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8158928155899048},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5406380295753479},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4954124689102173},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.48508420586586},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4595332443714142},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40411972999572754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.401699960231781},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3897300362586975},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2867688834667206},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.19707822799682617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158928155899048},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5406380295753479},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4954124689102173},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.48508420586586},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4595332443714142},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40411972999572754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.401699960231781},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3897300362586975},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2867688834667206},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.19707822799682617},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2733085.2733091","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2733085.2733091","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":45,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1501945960","https://openalex.org/W1971415141","https://openalex.org/W1976055110","https://openalex.org/W1976258225","https://openalex.org/W1987947616","https://openalex.org/W2002956097","https://openalex.org/W2011539648","https://openalex.org/W2015551056","https://openalex.org/W2022166150","https://openalex.org/W2029591641","https://openalex.org/W2029593518","https://openalex.org/W2035302703","https://openalex.org/W2040757233","https://openalex.org/W2044515729","https://openalex.org/W2049020147","https://openalex.org/W2051141368","https://openalex.org/W2069388662","https://openalex.org/W2079594573","https://openalex.org/W2080132606","https://openalex.org/W2083413555","https://openalex.org/W2097874932","https://openalex.org/W2100164132","https://openalex.org/W2101997700","https://openalex.org/W2108223890","https://openalex.org/W2111278149","https://openalex.org/W2114541504","https://openalex.org/W2116595366","https://openalex.org/W2117312440","https://openalex.org/W2127978399","https://openalex.org/W2128341918","https://openalex.org/W2131552526","https://openalex.org/W2133669904","https://openalex.org/W2135479443","https://openalex.org/W2139259611","https://openalex.org/W2148210463","https://openalex.org/W2148738951","https://openalex.org/W2154444297","https://openalex.org/W2160189941","https://openalex.org/W2163072729","https://openalex.org/W2168320385","https://openalex.org/W2168358004","https://openalex.org/W2169753664","https://openalex.org/W6681973738","https://openalex.org/W6684943652"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W187246281","https://openalex.org/W2565703248","https://openalex.org/W2143548620"],"abstract_inverted_index":{"The":[0],"web":[1,60],"is":[2,74,81,89,120,137],"overflowing":[3],"with":[4,189],"implicitly":[5],"structured":[6,31,93],"data,":[7,111],"spread":[8],"over":[9,58],"hundreds":[10],"of":[11,13,30,36,38,51,106,109,114,149,160,174],"thousands":[12,37],"sites,":[14],"hidden":[15],"deep":[16],"behind":[17],"search":[18],"forms,":[19],"or":[20],"siloed":[21],"in":[22,48],"marketplaces,":[23],"only":[24],"accessible":[25],"as":[26],"HTML.":[27],"Automatic":[28],"extraction":[29,73,86],"data":[32,94,188],"at":[33,98],"the":[34,49,82,121,138],"scale":[35],"websites":[39],"has":[40],"long":[41],"proven":[42],"elusive,":[43],"despite":[44],"its":[45,200],"central":[46],"role":[47],"\"web":[50],"data\".":[52],"Through":[53],"an":[54,181],"extensive":[55,163],"evaluation":[56,167],"spanning":[57],"10000":[59],"sites":[61,175],"from":[62,95,176],"multiple":[63],"application":[64],"domains,":[65,178],"we":[66],"show":[67],"that":[68,88,152,184],"automatic,":[69],"yet":[70],"accurate":[71],"full-site":[72,85],"no":[75],"longer":[76],"a":[77,146,157],"distant":[78],"dream.":[79],"diadem":[80,124,141,179,193],"first":[83,122],"automatic":[84],"system":[87],"able":[90],"to":[91],"extract":[92],"different":[96],"domains":[97],"very":[99],"high":[100],"accuracy.":[101],"It":[102],"combines":[103],"automated":[104],"exploration":[105],"websites,":[107],"identification":[108],"relevant":[110,187],"and":[112,131,164,199],"induction":[113],"exhaustive":[115],"wrappers.":[116],"Automating":[117],"these":[118,135],"components":[119,136,201],"challenge.":[123,140],"overcomes":[125,142],"this":[126,143],"challenge":[127,144],"by":[128],"combining":[129],"phenomenological":[130],"ontological":[132],"knowledge.":[133],"Integrating":[134],"second":[139],"through":[145],"self-adaptive":[147],"network":[148],"relational":[150],"transducers":[151],"produces":[153],"effective":[154,182],"wrappers":[155],"for":[156,170],"wide":[158],"variety":[159],"websites.":[161],"Our":[162],"publicly":[165],"available":[166],"shows":[168],"that,":[169],"more":[171],"than":[172],"90%":[173],"three":[177],"obtains":[180],"wrapper":[183],"extracts":[185],"all":[186],"97%":[190],"average":[191],"precision.":[192],"also":[194],"tolerates":[195],"noisy":[196],"entity":[197],"recognisers,":[198],"individually":[202],"outperform":[203],"comparable":[204],"approaches.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2016-06-24T00:00:00"}