{"id":"https://openalex.org/W3006253294","doi":"https://doi.org/10.3233/fi-2020-1906","title":"Time and Space Efficient Large Scale Link Discovery using String Similarities","display_name":"Time and Space Efficient Large Scale Link Discovery using String Similarities","publication_year":2020,"publication_date":"2020-02-08","ids":{"openalex":"https://openalex.org/W3006253294","doi":"https://doi.org/10.3233/fi-2020-1906","mag":"3006253294"},"language":"en","primary_location":{"id":"doi:10.3233/fi-2020-1906","is_oa":false,"landing_page_url":"https://doi.org/10.3233/fi-2020-1906","pdf_url":null,"source":{"id":"https://openalex.org/S39012697","display_name":"Fundamenta Informaticae","issn_l":"0169-2968","issn":["0169-2968","1875-8681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fundamenta Informaticae","raw_type":"journal-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/A5087271389","display_name":"\u0391\u03bd\u03b4\u03c1\u03ad\u03b1\u03c2 \u039a\u03b1\u03c1\u03ac\u03bc\u03c0\u03b5\u03bb\u03b1\u03c2","orcid":null},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Andreas Karampelas","raw_affiliation_strings":["Digital Systems Department, University of Piraeus, Piraeus, Greece. akar@unipi.gr, georgev@unipi.gr"],"affiliations":[{"raw_affiliation_string":"Digital Systems Department, University of Piraeus, Piraeus, Greece. akar@unipi.gr, georgev@unipi.gr","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040575826","display_name":"George A. Vouros","orcid":"https://orcid.org/0000-0001-5451-622X"},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"George A. Vouros","raw_affiliation_strings":["Digital Systems Department, University of Piraeus, Piraeus, Greece. akar@unipi.gr, georgev@unipi.gr"],"affiliations":[{"raw_affiliation_string":"Digital Systems Department, University of Piraeus, Piraeus, Greece. akar@unipi.gr, georgev@unipi.gr","institution_ids":["https://openalex.org/I154757721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040575826"],"corresponding_institution_ids":["https://openalex.org/I154757721"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02209813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"172","issue":"3","first_page":"299","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9970999956130981,"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":0.9970999956130981,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9853000044822693,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.7584964632987976},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7485169768333435},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7063572406768799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5759204030036926},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5708129405975342},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5564650297164917},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5296133756637573},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5145260691642761},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5082611441612244},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43657371401786804},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.42929619550704956},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4177863895893097},{"id":"https://openalex.org/keywords/subsequence","display_name":"Subsequence","score":0.41549721360206604},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.3999844491481781},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3894079923629761},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3836548328399658},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3820331394672394},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3790418803691864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34008657932281494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3382762670516968},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08161604404449463}],"concepts":[{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.7584964632987976},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7485169768333435},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7063572406768799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5759204030036926},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5708129405975342},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5564650297164917},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5296133756637573},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5145260691642761},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5082611441612244},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43657371401786804},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.42929619550704956},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4177863895893097},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.41549721360206604},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3999844491481781},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3894079923629761},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3836548328399658},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3820331394672394},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3790418803691864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34008657932281494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382762670516968},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08161604404449463},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/fi-2020-1906","is_oa":false,"landing_page_url":"https://doi.org/10.3233/fi-2020-1906","pdf_url":null,"source":{"id":"https://openalex.org/S39012697","display_name":"Fundamenta Informaticae","issn_l":"0169-2968","issn":["0169-2968","1875-8681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Fundamenta Informaticae","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2298204719","https://openalex.org/W1859666549","https://openalex.org/W2399644331","https://openalex.org/W2187092961","https://openalex.org/W2549495077","https://openalex.org/W52396946","https://openalex.org/W1564013439","https://openalex.org/W2119057313","https://openalex.org/W2405436873","https://openalex.org/W3112977702"],"abstract_inverted_index":{"This":[0],"paper":[1,36],"proposes":[2,37],"and":[3,6,38,73,81,149],"evaluates":[4],"time":[5],"space":[7],"efficient":[8,58],"methods":[9,42,66,136],"for":[10,158],"matching":[11,96,106,115,123,144],"entities":[12,80],"in":[13,69,91,117,139,147],"large":[14,159],"data":[15,55],"sets":[16],"based":[17],"on":[18,45],"effectively":[19],"pruning":[20,59,130],"the":[21,53,76,83,87,94,104,109,113,120,129,133,142,155],"candidate":[22],"pairs":[23],"to":[24,51,93,119,141],"be":[25],"matched,":[26],"using":[27,86],"edit":[28],"distance":[29],"as":[30],"a":[31,46],"string":[32,88,143],"similarity":[33,89],"metric.":[34],"The":[35,63,99],"compares":[39],"three":[40],"filtering":[41,65,97,124,135],"that":[43],"build":[44],"basi":[47],"c":[48],"blocking":[49],"technique":[50],"organize":[52],"target":[54],"set,":[56],"facilitating":[57],"of":[60,71,132,154],"dissimilar":[61],"pairs.":[62],"proposed":[64],"are":[67,152],"compared":[68],"terms":[70],"runtime":[72],"memory":[74],"usage:":[75],"first":[77],"method":[78,101,111],"clusters":[79],"exploits":[82],"triangle":[84],"inequality":[85],"metric,":[90],"conjunction":[92,118],"substring":[95,105,114],"rule.":[98,125],"second":[100],"uses":[102,112],"only":[103],"rule,":[107],"while":[108],"third":[110],"rule":[116],"character":[121],"frequency":[122],"Evaluation":[126],"results":[127],"show":[128],"power":[131],"different":[134],"used,":[137],"also":[138],"comparison":[140],"functionality":[145],"provided":[146],"LIMES":[148],"SILK,":[150],"which":[151],"state":[153],"art":[156],"frameworks":[157],"scale":[160],"link":[161],"discovery.":[162]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}