{"id":"https://openalex.org/W950074402","doi":"https://doi.org/10.3233/sw-150180","title":"Distantly supervised Web relation extraction for knowledge base population","display_name":"Distantly supervised Web relation extraction for knowledge base population","publication_year":2016,"publication_date":"2016-05-27","ids":{"openalex":"https://openalex.org/W950074402","doi":"https://doi.org/10.3233/sw-150180","mag":"950074402"},"language":"en","primary_location":{"id":"doi:10.3233/sw-150180","is_oa":true,"landing_page_url":"https://doi.org/10.3233/sw-150180","pdf_url":"https://content.iospress.com:443/download/semantic-web/sw180?id=semantic-web%2Fsw180","source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://content.iospress.com:443/download/semantic-web/sw180?id=semantic-web%2Fsw180","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Isabelle Augenstein","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Regent Court, 211 Portobello, Sheffield, S1 4DP, United Kingdom. E-mails:\u00a0i.augenstein@sheffield.ac.uk,\u00a0d.maynard@sheffield.ac.uk,\u00a0f.ciravegna@sheffield.ac.uk"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Regent Court, 211 Portobello, Sheffield, S1 4DP, United Kingdom. E-mails:\u00a0i.augenstein@sheffield.ac.uk,\u00a0d.maynard@sheffield.ac.uk,\u00a0f.ciravegna@sheffield.ac.uk","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089236260","display_name":"Diana Maynard","orcid":"https://orcid.org/0000-0002-1773-7020"},"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":"Diana Maynard","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Regent Court, 211 Portobello, Sheffield, S1 4DP, United Kingdom. E-mails:\u00a0i.augenstein@sheffield.ac.uk,\u00a0d.maynard@sheffield.ac.uk,\u00a0f.ciravegna@sheffield.ac.uk"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Regent Court, 211 Portobello, Sheffield, S1 4DP, United Kingdom. E-mails:\u00a0i.augenstein@sheffield.ac.uk,\u00a0d.maynard@sheffield.ac.uk,\u00a0f.ciravegna@sheffield.ac.uk","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":["Department of Computer Science, The University of Sheffield, Regent Court, 211 Portobello, Sheffield, S1 4DP, United Kingdom. E-mails:\u00a0i.augenstein@sheffield.ac.uk,\u00a0d.maynard@sheffield.ac.uk,\u00a0f.ciravegna@sheffield.ac.uk"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Regent Court, 211 Portobello, Sheffield, S1 4DP, United Kingdom. E-mails:\u00a0i.augenstein@sheffield.ac.uk,\u00a0d.maynard@sheffield.ac.uk,\u00a0f.ciravegna@sheffield.ac.uk","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018976680"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":9.7179,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.97958154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"7","issue":"4","first_page":"335","last_page":"349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9984999895095825,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9955000281333923,"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/relationship-extraction","display_name":"Relationship extraction","score":0.728805422782898},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5637195110321045},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5359175205230713},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5353349447250366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4828341603279114},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4629557728767395},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45319899916648865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3593292236328125},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35587939620018005},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34396836161613464},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23146525025367737},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14735546708106995},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.07341983914375305},{"id":"https://openalex.org/keywords/demography","display_name":"Demography","score":0.050631821155548096}],"concepts":[{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.728805422782898},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5637195110321045},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5359175205230713},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5353349447250366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4828341603279114},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4629557728767395},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45319899916648865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3593292236328125},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35587939620018005},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34396836161613464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23146525025367737},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14735546708106995},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.07341983914375305},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.050631821155548096},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/sw-150180","is_oa":true,"landing_page_url":"https://doi.org/10.3233/sw-150180","pdf_url":"https://content.iospress.com:443/download/semantic-web/sw180?id=semantic-web%2Fsw180","source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","raw_type":"journal-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:98763","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1547797","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1547797/","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":"   Semantic Web Journal , 7  (4)   pp. 335-349.   (2016)      ","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.3233/sw-150180","is_oa":true,"landing_page_url":"https://doi.org/10.3233/sw-150180","pdf_url":"https://content.iospress.com:443/download/semantic-web/sw180?id=semantic-web%2Fsw180","source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W950074402.pdf","grobid_xml":"https://content.openalex.org/works/W950074402.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W56435837","https://openalex.org/W97146189","https://openalex.org/W152228199","https://openalex.org/W171009253","https://openalex.org/W174427690","https://openalex.org/W1512387364","https://openalex.org/W1529731474","https://openalex.org/W1593580292","https://openalex.org/W1604644367","https://openalex.org/W1852412531","https://openalex.org/W1954715867","https://openalex.org/W2009591769","https://openalex.org/W2023352384","https://openalex.org/W2038721957","https://openalex.org/W2045495924","https://openalex.org/W2067367118","https://openalex.org/W2080133951","https://openalex.org/W2094728533","https://openalex.org/W2096765155","https://openalex.org/W2099115159","https://openalex.org/W2107598941","https://openalex.org/W2114544510","https://openalex.org/W2115461474","https://openalex.org/W2117173982","https://openalex.org/W2128407051","https://openalex.org/W2129629757","https://openalex.org/W2129842875","https://openalex.org/W2132679783","https://openalex.org/W2145453687","https://openalex.org/W2146304342","https://openalex.org/W2149713870","https://openalex.org/W2150102617","https://openalex.org/W2150588363","https://openalex.org/W2151149636","https://openalex.org/W2158981854","https://openalex.org/W2161494021","https://openalex.org/W2167187514","https://openalex.org/W2250265269","https://openalex.org/W2251419334","https://openalex.org/W2251851831","https://openalex.org/W2251887685","https://openalex.org/W2251960799","https://openalex.org/W2252115292","https://openalex.org/W2345859682","https://openalex.org/W4235505822","https://openalex.org/W6609612681","https://openalex.org/W6621631081","https://openalex.org/W6629054345","https://openalex.org/W6633568089","https://openalex.org/W6681875376","https://openalex.org/W6725824694","https://openalex.org/W6727875242"],"related_works":["https://openalex.org/W2976808399","https://openalex.org/W2609844752","https://openalex.org/W2981341912","https://openalex.org/W4385734297","https://openalex.org/W4221160509","https://openalex.org/W4285246823","https://openalex.org/W4226278302","https://openalex.org/W2547211086","https://openalex.org/W3114142812","https://openalex.org/W4380551175"],"abstract_inverted_index":{"Extracting":[0],"information":[1,36,53,73,183,197],"from":[2,38,74,106,126,185,206],"Web":[3,40,121],"pages":[4],"for":[5,90,103,120,188],"populating":[6,189],"large,":[7],"cross-domain":[8],"knowledge":[9,47,190],"bases":[10,48,191],"requires":[11],"methods":[12,175],"which":[13,70],"are":[14,28,116],"suitable":[15,119],"across":[16,151,156],"domains,":[17,27],"do":[18],"not":[19,118],"require":[20],"manual":[21],"effort":[22],"to":[23,25,30,49,51,80,86,176],"adapt":[24],"new":[26],"able":[29],"deal":[31],"with":[32,54,84],"noise,":[33],"and":[34,133,153,194,200],"integrate":[35],"extracted":[37,184,210],"different":[39],"pages.":[41],"Recent":[42],"approaches":[43,60,115],"have":[44],"used":[45],"existing":[46,114],"learn":[50],"extract":[52],"promising":[55],"results,":[56],"one":[57],"of":[58,100,141],"those":[59,203],"being":[61],"distant":[62,101],"supervision.":[63],"Distant":[64],"supervision":[65,102],"is":[66,112],"an":[67],"unsupervised":[68,160],"method":[69,111],"uses":[71],"background":[72],"the":[75,98,107,110,139,166],"Linking":[76],"Open":[77],"Data":[78],"cloud":[79],"automatically":[81],"label":[82],"sentences":[83],"relations":[85,155],"create":[87],"training":[88,179,224],"data":[89,130,142,225],"relation":[91,104,208],"classifiers.":[92],"In":[93],"this":[94],"paper":[95],"we":[96,192],"propose":[97],"use":[99],"extraction":[105,122],"Web.":[108],"Although":[109],"promising,":[113],"still":[117],"as":[123],"they":[124],"suffer":[125],"three":[127],"main":[128],"issues:":[129],"sparsity,":[131],"noise":[132,167],"lexical":[134,170],"ambiguity.":[135],"Our":[136],"approach":[137],"reduces":[138],"impact":[140],"sparsity":[143],"by":[144,169,172,216,229],"making":[145],"entity":[146],"recognition":[147],"tools":[148],"more":[149],"robust":[150],"domains":[152],"extracting":[154],"sentence":[157],"boundaries":[158],"using":[159,211],"coreference":[161],"resolution":[162],"methods.":[163],"We":[164,218],"reduce":[165],"caused":[168],"ambiguity":[171],"employing":[173],"statistical":[174],"strategically":[177,222],"select":[178],"data.":[180],"To":[181],"combine":[182],"multiple":[186],"sources":[187],"present":[193],"evaluate":[195],"several":[196],"integration":[198],"strategies":[199],"show":[201,220],"that":[202,221],"benefit":[204],"immensely":[205],"additional":[207],"mentions":[209],"co-reference":[212],"resolution,":[213],"increasing":[214],"precision":[215,228],"8%.":[217],"further":[219,231],"selecting":[223],"can":[226],"increase":[227],"a":[230],"3%.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}