{"id":"https://openalex.org/W2045926622","doi":"https://doi.org/10.1145/2767109.2767114","title":"Addressing Instance Ambiguity in Web Harvesting","display_name":"Addressing Instance Ambiguity in Web Harvesting","publication_year":2015,"publication_date":"2015-05-31","ids":{"openalex":"https://openalex.org/W2045926622","doi":"https://doi.org/10.1145/2767109.2767114","mag":"2045926622"},"language":"en","primary_location":{"id":"doi:10.1145/2767109.2767114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2767109.2767114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Workshop on Web and Databases","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/A5065529268","display_name":"Zhixu Li","orcid":"https://orcid.org/0000-0003-2355-288X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhixu Li","raw_affiliation_strings":["The School of Computer Science and Technology, Soochow University, China","The School of Computer Science and Technology, Soochow University, China#TAB#"],"affiliations":[{"raw_affiliation_string":"The School of Computer Science and Technology, Soochow University, China","institution_ids":["https://openalex.org/I3923682"]},{"raw_affiliation_string":"The School of Computer Science and Technology, Soochow University, China#TAB#","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000755750","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0002-3574-5665"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"XiangLiang Zhang","raw_affiliation_strings":["KAUST, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019011143","display_name":"Hai Huang","orcid":"https://orcid.org/0000-0002-2376-0462"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hai Huang","raw_affiliation_strings":["Griffith University, Gold Coast, Australia","[Griffith University, Gold Coast, Australia]"],"affiliations":[{"raw_affiliation_string":"Griffith University, Gold Coast, Australia","institution_ids":["https://openalex.org/I11701301"]},{"raw_affiliation_string":"[Griffith University, Gold Coast, Australia]","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013657140","display_name":"Qing Xie","orcid":"https://orcid.org/0000-0003-4530-588X"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Qing Xie","raw_affiliation_strings":["KAUST, Jeddah, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031653957","display_name":"Jia Zhu","orcid":"https://orcid.org/0000-0002-5959-390X"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zhu","raw_affiliation_strings":["South China Normal University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China Normal University, Guangzhou, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011384237","display_name":"Xiaofang Zhou","orcid":"https://orcid.org/0000-0001-6343-1455"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]},{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Xiaofang Zhou","raw_affiliation_strings":["The School of Computer Science and Technology, Soochow University, China and The University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"The School of Computer Science and Technology, Soochow University, China and The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I3923682","https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065529268"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07650336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"6","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9976000189781189,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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/ambiguity","display_name":"Ambiguity","score":0.8948414325714111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8247388601303101},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5988878011703491},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5817192196846008},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.43331533670425415},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35791507363319397},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33040812611579895}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.8948414325714111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8247388601303101},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5988878011703491},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5817192196846008},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.43331533670425415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35791507363319397},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33040812611579895},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2767109.2767114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2767109.2767114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Workshop on Web and Databases","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-108221","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-108221","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:382737","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-108221","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-108221","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2604341855","display_name":null,"funder_award_id":"DP140103171","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G6347735047","display_name":null,"funder_award_id":"61472263, 61402313, 61303019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W86887328","https://openalex.org/W141513725","https://openalex.org/W197097210","https://openalex.org/W1482214997","https://openalex.org/W1536465844","https://openalex.org/W1794858913","https://openalex.org/W1996505782","https://openalex.org/W2017360628","https://openalex.org/W2032584215","https://openalex.org/W2053239431","https://openalex.org/W2064522604","https://openalex.org/W2072475455","https://openalex.org/W2085337304","https://openalex.org/W2093903870","https://openalex.org/W2103296194","https://openalex.org/W2103931177","https://openalex.org/W2127761948","https://openalex.org/W2136542423","https://openalex.org/W2139253079","https://openalex.org/W2145007893","https://openalex.org/W2152444902","https://openalex.org/W2154439800","https://openalex.org/W2166279853","https://openalex.org/W2169213601","https://openalex.org/W2171960770","https://openalex.org/W2436001372","https://openalex.org/W2462998714","https://openalex.org/W2604516091","https://openalex.org/W3127908038","https://openalex.org/W4240913316","https://openalex.org/W4246858749","https://openalex.org/W6628905179","https://openalex.org/W6682656196","https://openalex.org/W7006778996"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W2389866386"],"abstract_inverted_index":{"Web":[0,79,91,159],"Harvesting":[1,92,160],"enables":[2],"the":[3,14,17,24,27,35,48,61,74,100,125,137,144,151,168,171],"enrichment":[4],"of":[5,19,26,52,68,102,117,153,170],"incomplete":[6],"data":[7,37],"sets":[8],"by":[9,99],"retrieving":[10],"required":[11],"information":[12],"from":[13],"Web.":[15,49,145],"However,":[16],"ambiguity":[18,62,76],"instances":[20,123,135],"may":[21,39],"greatly":[22],"decrease":[23],"quality":[25],"harvested":[28,172],"data,":[29],"given":[30],"that":[31,128,164],"any":[32],"instance":[33,75,88],"in":[34,64,78,90,115,124],"local":[36],"set":[38],"become":[40],"ambiguous":[41,141],"when":[42],"attempting":[43],"to":[44,58,72,86,110],"identify":[45],"it":[46,165],"on":[47,143],"Although":[50],"plenty":[51],"disambiguation":[53,89,96,155],"methods":[54],"have":[55],"been":[56],"proposed":[57],"deal":[59],"with":[60,93],"problems":[63],"various":[65],"settings,":[66],"none":[67],"them":[69],"are":[70],"able":[71],"handle":[73],"problem":[77],"Harvesting.":[80],"In":[81,106],"this":[82],"paper,":[83],"we":[84,108],"propose":[85],"do":[87],"a":[94,157],"novel":[95],"method":[97],"inspired":[98],"idea":[101],"collaborative":[103,154],"identity":[104],"recognition.":[105],"particular,":[107],"expect":[109],"find":[111],"some":[112],"common":[113],"properties":[114],"forms":[116],"latent":[118],"shared":[119,130],"attribute":[120,131],"values":[121,132],"among":[122],"list,":[126],"such":[127],"these":[129],"can":[133],"differentiate":[134],"within":[136],"list":[138],"against":[139],"those":[140],"ones":[142],"Our":[146],"extensive":[147],"experimental":[148],"evaluation":[149],"illustrates":[150],"utility":[152],"for":[156],"popular":[158],"application,":[161],"and":[162],"shows":[163],"substantially":[166],"improves":[167],"accuracy":[169],"data.":[173]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
