{"id":"https://openalex.org/W2067367118","doi":"https://doi.org/10.1145/2479832.2479845","title":"Unsupervised wrapper induction using linked data","display_name":"Unsupervised wrapper induction using linked data","publication_year":2013,"publication_date":"2013-06-23","ids":{"openalex":"https://openalex.org/W2067367118","doi":"https://doi.org/10.1145/2479832.2479845","mag":"2067367118"},"language":"en","primary_location":{"id":"doi:10.1145/2479832.2479845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2479832.2479845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2479832.2479845","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh international conference on Knowledge capture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2479832.2479845","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045091443","display_name":"Anna Lisa Gentile","orcid":"https://orcid.org/0000-0002-6401-4175"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anna Lisa Gentile","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404392","display_name":"Ziqi Zhang","orcid":"https://orcid.org/0000-0002-8587-8618"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ziqi Zhang","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018976680","display_name":"Isabelle Augenstein","orcid":"https://orcid.org/0000-0003-1562-7909"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Isabelle Augenstein","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052671966","display_name":"Fabio Ciravegna","orcid":"https://orcid.org/0000-0001-5817-4810"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fabio Ciravegna","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045091443"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":16.7114,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.98818332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"48"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9851999878883362,"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":0.8471510410308838},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7101446390151978},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5430997014045715},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5240483283996582},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5094895958900452},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5011205673217773},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4972250759601593},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49021512269973755},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.48500916361808777},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38344648480415344},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33234554529190063},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33146774768829346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8471510410308838},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7101446390151978},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5430997014045715},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5240483283996582},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5094895958900452},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5011205673217773},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4972250759601593},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49021512269973755},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.48500916361808777},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38344648480415344},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33234554529190063},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33146774768829346},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/2479832.2479845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2479832.2479845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2479832.2479845","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh international conference on Knowledge capture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.705.8947","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.705.8947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staffwww.dcs.shef.ac.uk/people/I.Augenstein/KCAP2013-Unsupervised.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.870.2530","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.870.2530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Anna_Gentile/publication/255979956_Unsupervised_Wrapper_Induction_using_Linked_Data/links/0deec521378579278d000000.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1547793","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1547793/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In:       (2013)     ","raw_type":"Proceedings paper"},{"id":"pmh:oai:irep.ntu.ac.uk:28566","is_oa":false,"landing_page_url":"http://irep.ntu.ac.uk/id/eprint/28566/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400559","display_name":"Nottingham Trent University's Institutional Repository (Nottingham Trent Repository)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I52590639","host_organization_name":"Nottingham Trent University","host_organization_lineage":["https://openalex.org/I52590639"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":{"id":"doi:10.1145/2479832.2479845","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2479832.2479845","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2479832.2479845","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh international conference on Knowledge capture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1132554097","display_name":null,"funder_award_id":"EP/J019488/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G466780314","display_name":"Lodie,Web Scale Information Extraction via Linked Open Data","funder_award_id":"EP/J019488/1","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2067367118.pdf","grobid_xml":"https://content.openalex.org/works/W2067367118.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W11658723","https://openalex.org/W64481094","https://openalex.org/W279841946","https://openalex.org/W1510085999","https://openalex.org/W1515300998","https://openalex.org/W1553019137","https://openalex.org/W1616576116","https://openalex.org/W1708151696","https://openalex.org/W1795600436","https://openalex.org/W1885838195","https://openalex.org/W1993977866","https://openalex.org/W2002956097","https://openalex.org/W2036383017","https://openalex.org/W2080132606","https://openalex.org/W2101649195","https://openalex.org/W2140421087","https://openalex.org/W2150721933","https://openalex.org/W2154444297","https://openalex.org/W2161861392","https://openalex.org/W2162340487","https://openalex.org/W2163072729","https://openalex.org/W2181790738","https://openalex.org/W2522338500","https://openalex.org/W2912486915","https://openalex.org/W4210962885","https://openalex.org/W6602554808","https://openalex.org/W6610184536","https://openalex.org/W6633154970"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W2016355461","https://openalex.org/W2386938185","https://openalex.org/W2068844411","https://openalex.org/W1986386500","https://openalex.org/W2793744252","https://openalex.org/W1516746680","https://openalex.org/W2072284316"],"abstract_inverted_index":{"This":[0],"work":[1,66],"explores":[2],"the":[3,18,100,146],"usage":[4],"of":[5,20,64,70,145],"Linked":[6,50,72,111],"Data":[7,51,73,112],"for":[8,106,119],"Web":[9,88],"scale":[10,89],"Information":[11,90,120],"Extraction":[12,91],"and":[13,40,78,95,98],"shows":[14],"encouraging":[15],"results":[16,140],"on":[17,123,151],"task":[19],"Wrapper":[21],"Induction.":[22],"We":[23,103],"propose":[24],"a":[25,68,115,124],"simple":[26,134],"knowledge":[27,54,80,117],"based":[28],"method":[29],"which":[30],"is":[31,67],"(i)":[32],"highly":[33],"flexible":[34],"with":[35],"respect":[36],"to":[37,56,86],"different":[38],"domains":[39,107],"(ii)":[41],"does":[42],"not":[43],"require":[44],"any":[45],"training":[46,152],"material,":[47],"but":[48],"exploits":[49],"as":[52,114],"background":[53],"source":[55],"build":[57],"essential":[58],"learning":[59],"resources.":[60],"The":[61],"major":[62],"contribution":[63],"this":[65,133],"study":[69],"how":[71],"-":[74,82],"an":[75,93],"imprecise,":[76],"redundant":[77],"large-scale":[79],"resource":[81,118],"can":[83,137],"be":[84],"used":[85],"support":[87],"in":[92],"effective":[94],"efficient":[96],"way":[97],"identify":[99],"challenges":[101],"involved.":[102],"show":[104],"that,":[105,129],"that":[108,148],"are":[109],"covered,":[110],"serve":[113],"powerful":[116],"Extraction.":[121],"Experiments":[122],"publicly":[125],"available":[126],"dataset":[127],"demonstrate":[128],"under":[130],"certain":[131],"conditions,":[132],"unsupervised":[135],"approach":[136],"achieve":[138],"competitive":[139],"against":[141],"some":[142],"complex":[143],"state":[144],"art":[147],"always":[149],"depends":[150],"data.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}