{"id":"https://openalex.org/W1998587816","doi":"https://doi.org/10.1145/1772690.1772885","title":"Efficient web pages identification for entity resolution","display_name":"Efficient web pages identification for entity resolution","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W1998587816","doi":"https://doi.org/10.1145/1772690.1772885","mag":"1998587816"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","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/A5031653957","display_name":"Jia Zhu","orcid":"https://orcid.org/0000-0002-5959-390X"},"institutions":[{"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"],"is_corresponding":true,"raw_author_name":"Jia Zhu","raw_affiliation_strings":["University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491411","display_name":"Gabriel Pui Cheong Fung","orcid":"https://orcid.org/0000-0002-7408-795X"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Gabriel Fung","raw_affiliation_strings":["University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"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/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaofang Zhou","raw_affiliation_strings":["University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031653957"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":0.8058,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76730529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1223","last_page":"1224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9979000091552734,"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":0.9721999764442444,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8452029228210449},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.8268985748291016},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7338573336601257},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6492531299591064},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5989008545875549},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.5410072207450867},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.45833900570869446},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4523800015449524},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44365644454956055},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.44329798221588135},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44126856327056885},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11988621950149536},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0587688684463501},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05628514289855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8452029228210449},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.8268985748291016},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7338573336601257},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6492531299591064},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5989008545875549},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.5410072207450867},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.45833900570869446},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4523800015449524},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44365644454956055},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.44329798221588135},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44126856327056885},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11988621950149536},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0587688684463501},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05628514289855957},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1772690.1772885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:316291","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:1783.1-108415","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2010&rft.spage=1223&rft.aulast=Zhu&rft.aufirst=&rft.atitle=Efficient+web+pages+identification+for+entity+resolution&rft.title=Proceedings+of+the+19th+International+Conference+on+World+Wide+Web%2C+WWW+%2710","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2137408040","https://openalex.org/W2542557639","https://openalex.org/W4254373586","https://openalex.org/W6729312850"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2319837024","https://openalex.org/W2343500026","https://openalex.org/W2390627310","https://openalex.org/W2413664130","https://openalex.org/W2051731675","https://openalex.org/W2033159440"],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"(ER)":[2],"is":[3,106,112],"a":[4,17,52,72,85],"problem":[5,76],"that":[6,19,102],"arises":[7],"in":[8],"many":[9],"areas.":[10],"In":[11,47],"most":[12],"of":[13,87,95],"cases,":[14],"it":[15],"represents":[16],"task":[18],"multiple":[20],"entities":[21,60,64],"from":[22],"different":[23,36],"sources":[24],"require":[25],"to":[26,32,58,66],"be":[27],"identified":[28],"if":[29],"they":[30],"refer":[31,65],"the":[33,92,115],"same":[34],"or":[35],"objects":[37],"because":[38],"there":[39],"are":[40],"not":[41],"unique":[42],"identifiers":[43],"associated":[44],"with":[45],"them.":[46],"this":[48],"paper,":[49],"we":[50],"propose":[51],"model":[53,83],"using":[54],"web":[55],"pages":[56],"identification":[57],"identify":[59],"and":[61,80],"merge":[62],"those":[63],"one":[67],"object":[68],"together.":[69],"We":[70],"use":[71],"classical":[73],"name":[74],"disambiguation":[75],"as":[77,91],"case":[78],"study":[79],"examine":[81],"our":[82,96,103],"on":[84],"subset":[86],"digital":[88],"library":[89],"records":[90],"first":[93],"stage":[94],"work.":[97],"The":[98],"favorable":[99],"results":[100],"indicated":[101],"proposed":[104],"approach":[105],"highly":[107],"effective.":[108],"\u00a9":[109],"2010":[110],"Copyright":[111],"held":[113],"by":[114],"author/owner(s).":[116]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
