{"id":"https://openalex.org/W2216972693","doi":"https://doi.org/10.14778/2824032.2824120","title":"WADaR","display_name":"WADaR","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2216972693","doi":"https://doi.org/10.14778/2824032.2824120","mag":"2216972693"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824120","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824120","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":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3454705","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057963374","display_name":"Stefano Ortona","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":true,"raw_author_name":"Stefano Ortona","raw_affiliation_strings":["Oxford University, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, United Kingdom","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, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032860819","display_name":"Marcello Buoncristiano","orcid":"https://orcid.org/0000-0003-2022-7475"},"institutions":[{"id":"https://openalex.org/I20272500","display_name":"University of Basilicata","ror":"https://ror.org/03tc05689","country_code":"IT","type":"education","lineage":["https://openalex.org/I20272500"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Buoncristiano","raw_affiliation_strings":["Universit\u00e0 della Basilicata, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 della Basilicata, Italy","institution_ids":["https://openalex.org/I20272500"]}]},{"author_position":"last","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, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Oxford University, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057963374"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":7.4112,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97021991,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"12","first_page":"1996","last_page":"1999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980000257492065,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9836999773979187,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8441293239593506},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7586969137191772},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4772988557815552},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43553340435028076},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.42291516065597534},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3001081943511963},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28682196140289307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441293239593506},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7586969137191772},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4772988557815552},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43553340435028076},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.42291516065597534},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3001081943511963},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28682196140289307}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/2824032.2824120","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824120","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:iris.unibas.it:11563/113857","is_oa":false,"landing_page_url":"http://hdl.handle.net/11563/113857","pdf_url":null,"source":{"id":"https://openalex.org/S4377196360","display_name":"CINECA IRIS Institutional Research Information System (University of Basilicata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20272500","host_organization_name":"University of Basilicata","host_organization_lineage":["https://openalex.org/I20272500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unibas.it:11563/154066","is_oa":false,"landing_page_url":"http://hdl.handle.net/11563/154066","pdf_url":null,"source":{"id":"https://openalex.org/S4377196360","display_name":"CINECA IRIS Institutional Research Information System (University of Basilicata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20272500","host_organization_name":"University of Basilicata","host_organization_lineage":["https://openalex.org/I20272500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:zenodo.org:3454705","is_oa":true,"landing_page_url":"https://zenodo.org/record/3454705","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3454705","is_oa":true,"landing_page_url":"https://zenodo.org/record/3454705","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.550000011920929,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1494141893","https://openalex.org/W1972495172","https://openalex.org/W2097874932","https://openalex.org/W2104086170","https://openalex.org/W2108126629","https://openalex.org/W2114541504","https://openalex.org/W2117312440","https://openalex.org/W2128341918","https://openalex.org/W2143309843","https://openalex.org/W2151234409","https://openalex.org/W2161861392","https://openalex.org/W2296164608","https://openalex.org/W6681480118"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2757182831","https://openalex.org/W2095886385","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W3151146928"],"abstract_inverted_index":{"Web":[0],"scraping":[1],"(or":[2],"wrapping)":[3],"is":[4,102],"a":[5,52],"popular":[6],"means":[7],"for":[8,58,91],"acquiring":[9],"data":[10,23,62,94],"from":[11],"the":[12,93,106,119,126,134],"web.":[13],"Recent":[14],"advancements":[15],"have":[16],"made":[17],"scalable":[18,42,53],"wrapper-generation":[19],"possible":[20],"and":[21,34,38,54,61,95,113,115],"enabled":[22],"acquisition":[24],"processes":[25],"involving":[26],"thousands":[27],"of":[28,108,125,133],"sources.":[29],"This":[30],"makes":[31],"wrapper":[32,60,121],"analysis":[33],"maintenance":[35],"both":[36,92],"needed":[37],"challenging":[39],"as":[40],"no":[41],"tools":[43],"exists":[44],"that":[45,84,100],"support":[46],"these":[47],"tasks.":[48],"We":[49,98],"demonstrate":[50],"WADaR,":[51],"highly":[55],"automated":[56],"tool":[57],"joint":[59],"repair.":[63],"WADaR":[64,101],"uses":[65],"off-the-shelf":[66],"entity":[67],"recognisers":[68],"to":[69,80,104,116],"locate":[70],"target":[71],"entities":[72],"in":[73,129],"wrapper-generated":[74,109],"data.":[75],"Markov":[76],"chains":[77],"are":[78,85],"used":[79],"determine":[81],"structural":[82],"repairs,":[83],"then":[86],"encoded":[87],"into":[88],"suitable":[89],"repairs":[90],"corresponding":[96,120],"wrappers.":[97],"show":[99],"able":[103],"increase":[105],"quality":[107],"relations":[110],"between":[111],"15%":[112],"60%,":[114],"fully":[117],"repair":[118],"without":[122],"any":[123],"knowledge":[124],"original":[127],"website":[128],"more":[130],"than":[131],"50%":[132],"cases.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2016-06-24T00:00:00"}
