{"id":"https://openalex.org/W2424113438","doi":"https://doi.org/10.1109/icde.2016.7498378","title":"Semantic-aware blocking for entity resolution","display_name":"Semantic-aware blocking for entity resolution","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2424113438","doi":"https://doi.org/10.1109/icde.2016.7498378","mag":"2424113438"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2016.7498378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2016.7498378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 32nd International Conference on Data Engineering (ICDE)","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/A5100691702","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0001-9504-4273"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Research School of Computer Science, The Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, The Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113086668","display_name":"Mingyuan Cui","orcid":"https://orcid.org/0009-0007-0421-8268"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingyuan Cui","raw_affiliation_strings":["Research School of Computer Science, The Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, The Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075528828","display_name":"Huizhi Liang","orcid":"https://orcid.org/0000-0003-4408-4528"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huizhi Liang","raw_affiliation_strings":["Department of Computing and Information Systems, The University of Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100691702"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":1.1157,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81877986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"549","issue":null,"first_page":"1468","last_page":"1469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991999864578247,"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":0.9991999864578247,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9872000217437744,"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/T11363","display_name":"Dental Radiography and Imaging","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/3504","display_name":"Oral Surgery"},"field":{"id":"https://openalex.org/fields/35","display_name":"Dentistry"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8071801662445068},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7328348159790039},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6873193383216858},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6576663851737976},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.47206953167915344},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.4336249530315399},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4308794140815735},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4181225597858429},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4159456491470337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3922993242740631},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.07906785607337952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071801662445068},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7328348159790039},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6873193383216858},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6576663851737976},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.47206953167915344},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.4336249530315399},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4308794140815735},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4181225597858429},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4159456491470337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3922993242740631},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.07906785607337952},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2016.7498378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2016.7498378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 32nd International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/733797412","is_oa":false,"landing_page_url":"https://hdl.handle.net/1885/733797412","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W299839057","https://openalex.org/W788126153","https://openalex.org/W1502916507","https://openalex.org/W2031250218","https://openalex.org/W2038276547","https://openalex.org/W2061162567","https://openalex.org/W2147717514","https://openalex.org/W2182703380","https://openalex.org/W2424113438","https://openalex.org/W4230502578","https://openalex.org/W4242744113","https://openalex.org/W6629956336"],"related_works":["https://openalex.org/W3134365128","https://openalex.org/W1965623300","https://openalex.org/W2541135911","https://openalex.org/W2359259132","https://openalex.org/W4387489691","https://openalex.org/W2103835134","https://openalex.org/W3028298263","https://openalex.org/W3016822073","https://openalex.org/W2133831373","https://openalex.org/W2807098362"],"abstract_inverted_index":{"In":[0,36],"this":[1,134],"work":[2],"we":[3,50],"propose":[4],"a":[5,112,153],"semantic-aware":[6,135],"blocking":[7,34,104,136,146],"framework":[8,15,92,137],"for":[9,147],"entity":[10,149],"resolution":[11,150],"(ER).":[12],"The":[13,106],"proposed":[14,91],"is":[16],"built":[17],"using":[18,111],"locality-sensitive":[19],"hashing":[20],"(LSH)":[21],"techniques":[22,82],"to":[23,38,128,141],"efficiently":[24],"unify":[25],"both":[26],"textual":[27,118],"and":[28,57,78,98,117,144],"semantic":[29,70,115],"features":[30,116,119],"into":[31],"an":[32],"ER":[33,48],"process.":[35],"order":[37],"understand":[39],"how":[40,68],"similarity":[41,55,71,85],"metrics":[42,56],"may":[43],"affect":[44],"the":[45,52,69,102,123,129],"effectiveness":[46],"of":[47,54,62,72,114,125,132],"blocking,":[49],"study":[51,108],"robustness":[53],"their":[58],"properties":[59],"in":[60,152],"terms":[61],"LSH":[63,81],"families.":[64],"We":[65,87],"further":[66],"discuss":[67],"records":[73],"can":[74,120],"be":[75],"captured,":[76],"measured,":[77],"integrated":[79],"with":[80,101],"over":[83,93],"multiple":[84],"spaces.":[86],"have":[88],"evaluated":[89],"our":[90],"two":[94],"real-world":[95],"data":[96,155],"sets,":[97],"compared":[99],"it":[100],"state-of-the-art":[103],"techniques.":[105],"experimental":[107],"shows":[109],"that":[110],"combination":[113],"considerably":[121],"improve":[122],"quality":[124],"blocking.":[126],"Due":[127],"probabilistic":[130],"nature":[131],"LSH,":[133],"also":[138],"enables":[139],"us":[140],"build":[142],"fast":[143],"reliable":[145],"performing":[148],"tasks":[151],"large-scale":[154],"environment.":[156]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-16T09:10:04.655348","created_date":"2025-10-10T00:00:00"}