{"id":"https://openalex.org/W2891808172","doi":"https://doi.org/10.1109/access.2018.2871168","title":"Learning Distance Metrics for Entity Resolution","display_name":"Learning Distance Metrics for Entity Resolution","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2891808172","doi":"https://doi.org/10.1109/access.2018.2871168","mag":"2891808172"},"language":"en","primary_location":{"id":"doi:10.1109/access.2018.2871168","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2871168","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2018.2871168","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100731288","display_name":"Lingli Li","orcid":"https://orcid.org/0000-0001-8898-5817"},"institutions":[{"id":"https://openalex.org/I1300757298","display_name":"Heilongjiang University of Science and Technology","ror":"https://ror.org/030xwyx96","country_code":"CN","type":"education","lineage":["https://openalex.org/I1300757298"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingli Li","raw_affiliation_strings":["Department of Computer Science and Technology, Heilongjiang University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-8898-5817","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Heilongjiang University, Harbin, China","institution_ids":["https://openalex.org/I1300757298"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103045128","display_name":"Xiaodan Shang","orcid":"https://orcid.org/0000-0002-5332-5242"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Shang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-5332-5242","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665543","display_name":"Jinbao Li","orcid":"https://orcid.org/0000-0002-8478-3983"},"institutions":[{"id":"https://openalex.org/I1300757298","display_name":"Heilongjiang University of Science and Technology","ror":"https://ror.org/030xwyx96","country_code":"CN","type":"education","lineage":["https://openalex.org/I1300757298"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinbao Li","raw_affiliation_strings":["Department of Computer Science and Technology, Heilongjiang University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Heilongjiang University, Harbin, China","institution_ids":["https://openalex.org/I1300757298"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081724582","display_name":"Jin Hu","orcid":"https://orcid.org/0000-0002-7563-4716"},"institutions":[{"id":"https://openalex.org/I1300757298","display_name":"Heilongjiang University of Science and Technology","ror":"https://ror.org/030xwyx96","country_code":"CN","type":"education","lineage":["https://openalex.org/I1300757298"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Hu","raw_affiliation_strings":["Department of Computer Science and Technology, Heilongjiang University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Heilongjiang University, Harbin, China","institution_ids":["https://openalex.org/I1300757298"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.4246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69101532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"54900","last_page":"54909"},"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9747999906539917,"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/computer-science","display_name":"Computer science","score":0.7629424333572388},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.613440990447998},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.608428418636322},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5760059356689453},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.565572202205658},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5555235147476196},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5549055337905884},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5542850494384766},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5314344763755798},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4804479777812958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47389426827430725},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4697929620742798},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4498922526836395},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.42503345012664795},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3786477744579315},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.30729812383651733},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.2713353931903839},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2535296678543091},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14480909705162048},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10246306657791138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629424333572388},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.613440990447998},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.608428418636322},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5760059356689453},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.565572202205658},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5555235147476196},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5549055337905884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5542850494384766},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5314344763755798},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4804479777812958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47389426827430725},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4697929620742798},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4498922526836395},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.42503345012664795},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3786477744579315},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.30729812383651733},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2713353931903839},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2535296678543091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14480909705162048},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10246306657791138},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2018.2871168","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2871168","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2c8d9ee8d698457d852437c053ae3691","is_oa":true,"landing_page_url":"https://doaj.org/article/2c8d9ee8d698457d852437c053ae3691","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 6, Pp 54900-54909 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2018.2871168","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2871168","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1981590391","https://openalex.org/W1990578345","https://openalex.org/W2001496424","https://openalex.org/W2007682403","https://openalex.org/W2010595692","https://openalex.org/W2034190452","https://openalex.org/W2042454345","https://openalex.org/W2052390074","https://openalex.org/W2105929850","https://openalex.org/W2108991785","https://openalex.org/W2129598390","https://openalex.org/W2150698190","https://openalex.org/W2164456230","https://openalex.org/W2171313960","https://openalex.org/W2278012135","https://openalex.org/W2535778619","https://openalex.org/W2555454054","https://openalex.org/W2587896339","https://openalex.org/W2588943408","https://openalex.org/W2606436201","https://openalex.org/W2610135452","https://openalex.org/W2612526608","https://openalex.org/W2612964472","https://openalex.org/W2616120155","https://openalex.org/W2666784499","https://openalex.org/W2740924709","https://openalex.org/W2750620035","https://openalex.org/W2753663361","https://openalex.org/W2756567726","https://openalex.org/W2767681556","https://openalex.org/W2781570638","https://openalex.org/W2790117078","https://openalex.org/W2964226158","https://openalex.org/W3146259567","https://openalex.org/W6660960606","https://openalex.org/W6682056454"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W4246757943","https://openalex.org/W2368606575","https://openalex.org/W2986277685","https://openalex.org/W2519145296","https://openalex.org/W2132753198","https://openalex.org/W2369874856","https://openalex.org/W2182477562","https://openalex.org/W2792185758"],"abstract_inverted_index":{"Entity":[0],"resolution":[1,102],"(ER)":[2],"is":[3,20],"to":[4,10,21,32,45],"find":[5],"database":[6,30],"records":[7],"that":[8,96],"refer":[9],"the":[11,34,76,81],"same":[12],"real-world":[13],"entity.":[14],"A":[15],"key":[16],"component":[17,78],"for":[18,28,68,87],"ER":[19,40,72],"choose":[22],"a":[23,47],"proper":[24,48],"distance":[25,56,66],"(similarity)":[26],"function":[27],"each":[29],"field":[31],"quantify":[33],"similarity":[35],"of":[36,71],"records.":[37],"Most":[38],"existing":[39],"approaches":[41,98],"focus":[42],"on":[43,52,91],"how":[44],"define":[46],"matching":[49],"rule":[50],"based":[51],"generic":[53],"or":[54],"hand-crafted":[55],"metrics.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"explore":[62],"two":[63,69],"learnable":[64],"string":[65],"metrics":[67],"kinds":[70],"problems":[73],"by":[74],"employing":[75],"principle":[77],"analysis":[79],"and":[80],"largest":[82],"margin":[83],"nearest":[84],"neighbor":[85],"algorithm":[86],"training.":[88],"Experimental":[89],"results":[90],"real":[92],"data":[93],"sets":[94],"show":[95],"our":[97],"can":[99],"improve":[100],"entity":[101],"accuracy":[103],"over":[104],"traditional":[105],"techniques.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}