{"id":"https://openalex.org/W2439475996","doi":"https://doi.org/10.1109/icde.2016.7498320","title":"Joint repairs for web wrappers","display_name":"Joint repairs for web wrappers","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2439475996","doi":"https://doi.org/10.1109/icde.2016.7498320","mag":"2439475996"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2016.7498320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2016.7498320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 32nd International Conference on Data Engineering (ICDE)","raw_type":"proceedings-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/A5057963374","display_name":"Stefano Ortona","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]},{"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":["Department of Computer Science, Oxford University, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Oxford University, United Kingdom","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008165294","display_name":"Giorgio Orsi","orcid":null},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giorgio Orsi","raw_affiliation_strings":["School of Computer Science, University of Birmingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham, United Kingdom","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Furche","raw_affiliation_strings":["Department of Computer Science, Oxford University, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Oxford University, United Kingdom","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]}]},{"author_position":"last","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":["Dipartimento di Matematica, Informatica ed Economia, Universita della Basilicata, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica, Informatica ed Economia, Universita della Basilicata, Italy","institution_ids":["https://openalex.org/I20272500"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057963374"],"corresponding_institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"],"apc_list":null,"apc_paid":null,"fwci":5.5429,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.95843889,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"10","issue":null,"first_page":"1146","last_page":"1157"},"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":0.9993000030517578,"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":0.992900013923645,"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":0.8163034319877625},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.7490801811218262},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.690516471862793},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6101179718971252},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5084351897239685},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46794217824935913},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.45551034808158875},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41999661922454834},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3473513722419739},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29448258876800537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29106903076171875},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.22632476687431335},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18298745155334473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163034319877625},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.7490801811218262},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.690516471862793},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6101179718971252},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5084351897239685},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46794217824935913},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.45551034808158875},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41999661922454834},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3473513722419739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29448258876800537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29106903076171875},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.22632476687431335},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18298745155334473},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icde.2016.7498320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2016.7498320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 32nd International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:84ccdc92-cf32-4ab4-a052-1d33ada23dbd","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:84ccdc92-cf32-4ab4-a052-1d33ada23dbd","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements at Oxford","raw_type":"Conference"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/ecb62da0-0fc5-44ec-b2f1-0438602e15ef","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/portal/en/publications/joint-repairs-for-web-wrappers(ecb62da0-0fc5-44ec-b2f1-0438602e15ef).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ortona, S, Orsi, G, Furche, T & Buoncristiano, M 2016, Joint Repairs for Web Wrappers. in Proceedings of the 32nd IEEE International Conference on Data Engineering (ICDE) . Institute of Electrical and Electronics Engineers (IEEE), 32nd IEEE International Conference on Data Engineering (ICDE) , Helsinki, Finland, 16/05/16. https://doi.org/10.1109/ICDE.2016.7498320","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/ecb62da0-0fc5-44ec-b2f1-0438602e15ef","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/ecb62da0-0fc5-44ec-b2f1-0438602e15ef","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ortona , S , Orsi , G , Furche , T & Buoncristiano , M 2016 , Joint Repairs for Web Wrappers . in Proceedings of the 32nd IEEE International Conference on Data Engineering (ICDE) . Institute of Electrical and Electronics Engineers (IEEE) , 32nd IEEE International Conference on Data Engineering (ICDE) , Helsinki , Finland , 16/05/16 . https://doi.org/10.1109/ICDE.2016.7498320","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G8400180575","display_name":null,"funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W236085609","https://openalex.org/W279841946","https://openalex.org/W1494141893","https://openalex.org/W1972495172","https://openalex.org/W1992479406","https://openalex.org/W1992994083","https://openalex.org/W1993141752","https://openalex.org/W2001104490","https://openalex.org/W2027864253","https://openalex.org/W2044520606","https://openalex.org/W2045968013","https://openalex.org/W2067367118","https://openalex.org/W2080132606","https://openalex.org/W2081186682","https://openalex.org/W2084801987","https://openalex.org/W2089206172","https://openalex.org/W2089363549","https://openalex.org/W2092364718","https://openalex.org/W2093752301","https://openalex.org/W2097874932","https://openalex.org/W2108126629","https://openalex.org/W2110219039","https://openalex.org/W2115770258","https://openalex.org/W2116548113","https://openalex.org/W2117312440","https://openalex.org/W2128341918","https://openalex.org/W2135767707","https://openalex.org/W2143309843","https://openalex.org/W2147805208","https://openalex.org/W2151234409","https://openalex.org/W2161861392","https://openalex.org/W2166817967","https://openalex.org/W2167333415","https://openalex.org/W2169262681","https://openalex.org/W2183774130","https://openalex.org/W2296164608","https://openalex.org/W2504831212","https://openalex.org/W2753933954","https://openalex.org/W4240555197","https://openalex.org/W6610184536","https://openalex.org/W6629420277","https://openalex.org/W6676342170","https://openalex.org/W6677288352"],"related_works":["https://openalex.org/W1542110834","https://openalex.org/W2611888112","https://openalex.org/W2121120069","https://openalex.org/W562932586","https://openalex.org/W2124793519","https://openalex.org/W2398280235","https://openalex.org/W2162899405","https://openalex.org/W2184735843","https://openalex.org/W3113091479","https://openalex.org/W2355446901"],"abstract_inverted_index":{"Automated":[0],"web":[1,164],"scraping":[2],"is":[3,45,58,104],"a":[4,47,63,112,139,171],"popular":[5],"means":[6],"for":[7,81,92],"acquiring":[8],"data":[9,44,57,65,77,82],"from":[10,18,166],"the":[11,42,55,60,75,86,102,120,185,195,207],"web.":[12],"Scrapers":[13],"(or":[14],"wrappers)":[15],"are":[16,122,181],"derived":[17],"either":[19],"manually":[20],"or":[21,34],"automatically":[22],"annotated":[23],"examples,":[24],"often":[25,59],"resulting":[26],"in":[27,106,202],"under/over":[28],"segmented":[29],"data,":[30],"together":[31,73],"with":[32,74],"missing":[33],"spurious":[35],"content.":[36],"Automatic":[37],"repair":[38],"and":[39,68,95,144,191],"maintenance":[40],"of":[41,62,88,142,170,174,187,194,206],"extracted":[43,56,97],"thus":[46,69],"necessary":[48],"complement":[49],"to":[50,119,183],"automatic":[51],"wrapper":[52,196],"generation.":[53],"Moreover,":[54],"result":[61],"long-term":[64],"acquisition":[66],"effort":[67],"jointly":[70],"repairing":[71],"wrappers":[72,94,188],"generated":[76],"reduces":[78],"future":[79],"needs":[80],"cleaning.":[83],"We":[84,99],"study":[85],"problem":[87,103,121],"computing":[89],"joint":[90,179],"repairs":[91,180],"XPath-based":[93],"their":[96],"data.":[98],"show":[100],"that":[101,135,178],"NP-complete":[105],"general":[107],"but":[108,129,153],"becomes":[109],"tractable":[110,117],"under":[111],"few":[113],"natural":[114],"assumptions.":[115],"Even":[116],"solutions":[118],"still":[123],"impractical":[124],"on":[125,149],"very":[126],"large":[127],"datasets,":[128],"we":[130],"propose":[131],"an":[132],"optimal":[133],"approximation":[134],"proves":[136],"effective":[137],"across":[138],"wide":[140,172],"variety":[141,173],"domains":[143],"sources.":[145],"Our":[146],"approach":[147],"relies":[148],"encoded":[150],"domain":[151],"knowledge,":[152],"require":[154],"no":[155],"per-source":[156],"supervision.":[157],"An":[158],"evaluation":[159],"spanning":[160],"more":[161,203],"than":[162,204],"100k":[163],"pages":[165],"100":[167],"different":[168],"sites":[169],"application":[175],"domains,":[176],"shows":[177],"able":[182],"increase":[184],"quality":[186],"between":[189],"15%":[190],"60%":[192],"independently":[193],"generation":[197],"system,":[198],"eliminating":[199],"all":[200],"errors":[201],"50%":[205],"cases.":[208]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}