{"id":"https://openalex.org/W2813885120","doi":"https://doi.org/10.1145/3227609.3227657","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":2018,"publication_date":"2018-06-25","ids":{"openalex":"https://openalex.org/W2813885120","doi":"https://doi.org/10.1145/3227609.3227657","mag":"2813885120"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3227609.3227657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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":"A. Karampelas","raw_affiliation_strings":["University of Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus, Greece","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":false,"raw_author_name":"G. A. Vouros","raw_affiliation_strings":["University of Piraeus, Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus, Greece","institution_ids":["https://openalex.org/I154757721"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":62},"biblio":{"volume":"2006","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality Assessment and Improvement","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 Assessment and Improvement","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/T10215","display_name":"Semantic Web and Ontology Development","score":0.9881,"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/T10317","display_name":"Data Stream Management Systems and Techniques","score":0.9828,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/pruning","display_name":"Pruning","score":0.776196},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7223568},{"id":"https://openalex.org/keywords/string-similarity","display_name":"String Similarity","score":0.615376},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema Matching","score":0.602331},{"id":"https://openalex.org/keywords/duplicate-detection","display_name":"Duplicate Detection","score":0.563217},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5544255},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5413655},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query Optimization","score":0.525269},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"Data Cleaning","score":0.517223},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4279705}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.776196},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7223568},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.7191853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70735395},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.59410906},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5733168},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5544255},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5413655},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.53050655},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5082073},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.45654798},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.43211138},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4279705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41947865},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41767526},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41615698},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39717966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35472792},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23132262},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3227609.3227657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W192652968","https://openalex.org/W1970026646","https://openalex.org/W1973001156","https://openalex.org/W1998901603","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2100548092","https://openalex.org/W2150916025","https://openalex.org/W2152502401","https://openalex.org/W2166400748","https://openalex.org/W2167331726","https://openalex.org/W2239873446","https://openalex.org/W2328277245","https://openalex.org/W2397994241"],"related_works":["https://openalex.org/W52396946","https://openalex.org/W3175353343","https://openalex.org/W2748704845","https://openalex.org/W2549495077","https://openalex.org/W2405436873","https://openalex.org/W2399644331","https://openalex.org/W2298204719","https://openalex.org/W2187092961","https://openalex.org/W2119057313","https://openalex.org/W1564013439"],"abstract_inverted_index":{"This":[0],"paper":[1,36],"proposes":[2,37],"and":[3,6,38,71,135],"evaluates":[4],"time":[5],"space":[7],"efficient":[8,56],"methods":[9,25,42,64],"for":[10,26,141],"discovering":[11],"links":[12],"between":[13],"matching":[14,130],"entities":[15],"in":[16,67,85,107,125,133],"large":[17],"data":[18],"sets,":[19],"using":[20,81],"state":[21],"of":[22,58,69,119],"the":[23,52,78,82,88,96,100,104,110,116,120,128],"art":[24],"measuring":[27],"edit":[28],"distance":[29],"as":[30],"a":[31,46],"string":[32,129],"similarity":[33],"metric.":[34],"The":[35,61,74,91],"compares":[39],"three":[40],"filtering":[41,63],"that":[43],"build":[44],"on":[45],"basic":[47],"blocking":[48,79],"technique":[49],"to":[50,87,109,127],"organize":[51],"target":[53],"dataset,":[54],"facilitating":[55],"pruning":[57,117],"dissimilar":[59],"pairs.":[60],"proposed":[62],"are":[65,138],"compared":[66],"terms":[68],"runtime":[70],"memory":[72],"usage:":[73],"first":[75],"method":[76,93,102],"exploits":[77],"structure":[80],"triangle":[83],"inequality":[84],"conjunction":[86,108],"substring-matching":[89,97,105],"criterion.":[90,112],"second":[92],"uses":[94,103],"only":[95],"criterion,":[98],"while":[99],"third":[101],"criterion":[106],"frequency-matching":[111],"Evaluation":[113],"results":[114],"show":[115],"power":[118],"different":[121],"criteria":[122],"used,":[123],"also":[124],"comparison":[126],"functionality":[131],"provided":[132],"LIMES":[134],"SILK,":[136],"which":[137],"state-of-the-art":[139],"tools":[140],"large-scale":[142],"link":[143],"discovery.":[144]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2813885120","counts_by_year":[],"updated_date":"2024-10-07T13:25:10.768667","created_date":"2018-07-19"}
