{"id":"https://openalex.org/W1995116392","doi":"https://doi.org/10.1145/1352793.1352853","title":"Canonicalization of graph database records using similarity measures","display_name":"Canonicalization of graph database records using similarity measures","publication_year":2008,"publication_date":"2008-01-31","ids":{"openalex":"https://openalex.org/W1995116392","doi":"https://doi.org/10.1145/1352793.1352853","mag":"1995116392"},"language":"en","primary_location":{"id":"doi:10.1145/1352793.1352853","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1352793.1352853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd international conference on Ubiquitous information management and communication","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/A5100368052","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9739-8964"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Na Li","raw_affiliation_strings":["City University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["City University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402281","display_name":"Liping Wang","orcid":"https://orcid.org/0000-0003-3049-9917"},"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":"Liping Wang","raw_affiliation_strings":["The University of Queensland","The University Of Queensland;"],"affiliations":[{"raw_affiliation_string":"The University of Queensland","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"The University Of Queensland;","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100368052"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12496585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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":0.9984999895095825,"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/T11106","display_name":"Data Management and Algorithms","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8237645626068115},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.6700729727745056},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6155068278312683},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5654611587524414},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.5426157116889954},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49910974502563477},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47520169615745544},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35553646087646484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21916282176971436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237645626068115},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.6700729727745056},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6155068278312683},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5654611587524414},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5426157116889954},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49910974502563477},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47520169615745544},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35553646087646484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21916282176971436},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1352793.1352853","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1352793.1352853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd international conference on Ubiquitous information management and communication","raw_type":"proceedings-article"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:316251","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G6303879699","display_name":null,"funder_award_id":"7002212","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W335144045","https://openalex.org/W1483108372","https://openalex.org/W1493596129","https://openalex.org/W1506285740","https://openalex.org/W1519468639","https://openalex.org/W1604765824","https://openalex.org/W1610496399","https://openalex.org/W1612155886","https://openalex.org/W1641749581","https://openalex.org/W2020191321","https://openalex.org/W2035143052","https://openalex.org/W2096725584","https://openalex.org/W2136593687","https://openalex.org/W2142250121","https://openalex.org/W2168892477"],"related_works":["https://openalex.org/W4393220254","https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W2385015894","https://openalex.org/W3115442681","https://openalex.org/W2007838763","https://openalex.org/W2391000461","https://openalex.org/W2972311463"],"abstract_inverted_index":{"Information":[0],"extraction":[1],"and":[2,17,55,73,79,96],"crawling":[3],"from":[4,42],"the":[5,43,56,69,77,90,106,122],"Web":[6],"have":[7],"been":[8],"increasingly":[9],"common,":[10],"yet":[11],"raw":[12],"data":[13],"are":[14],"often":[15],"noisy":[16],"redundant":[18],"due":[19],"to":[20,45,50,60,115],"heterogeneous":[21],"sources.":[22],"Although":[23],"much":[24],"work":[25],"has":[26],"focused":[27],"on":[28,68,76],"duplicate":[29,74],"records":[30,94],"detection,":[31],"there":[32],"is":[33,58],"little":[34],"investigation":[35],"in":[36,103,132],"providing":[37],"a":[38,52,81,117],"uniform,":[39],"standard":[40],"result":[41],"duplicates":[44],"users,":[46],"which":[47,113],"we":[48,66,98,108],"refer":[49],"as":[51],"canonical":[53,118],"result,":[54],"process":[57],"referred":[59],"record":[61],"canonicalization.":[62,86],"In":[63],"this":[64],"paper,":[65],"focus":[67],"situation":[70],"of":[71,84,92],"imperfect":[72],"documents":[75],"Web,":[78],"propose":[80,99],"preprocessing":[82],"method":[83],"graph":[85,93,110,119,124],"We":[87],"first":[88],"formalize":[89],"problem":[91],"canonicalization,":[95,112],"then":[97],"three":[100],"possible":[101],"solutions":[102],"order.":[104],"Upon":[105],"framework,":[107],"implement":[109],"selection":[111],"aims":[114],"construct":[116],"by":[120],"selecting":[121],"central":[123],"among":[125],"records.":[126],"Experiment":[127],"results":[128],"demonstrate":[129],"its":[130],"performance":[131],"representing":[133],"real":[134],"world":[135],"entities.":[136]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
