{"id":"https://openalex.org/W4386026606","doi":"https://doi.org/10.1007/s00778-023-00806-z","title":"MinJoin++: a fast algorithm for string similarity joins under edit distance","display_name":"MinJoin++: a fast algorithm for string similarity joins under edit distance","publication_year":2023,"publication_date":"2023-08-21","ids":{"openalex":"https://openalex.org/W4386026606","doi":"https://doi.org/10.1007/s00778-023-00806-z"},"language":"en","primary_location":{"id":"doi:10.1007/s00778-023-00806-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00778-023-00806-z","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","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/A5033647227","display_name":"Nikolai Karpov","orcid":"https://orcid.org/0000-0002-4962-3925"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nikolai Karpov","raw_affiliation_strings":["Indiana University, Bloomington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425888","display_name":"Haoyu Zhang","orcid":"https://orcid.org/0000-0002-6049-153X"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["Meta Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418224","display_name":"Qin Zhang","orcid":"https://orcid.org/0000-0002-6851-3115"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["Indiana University, Bloomington, USA"],"raw_orcid":"https://orcid.org/0000-0002-6851-3115","affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033647227"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.7397,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74492195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"33","issue":"2","first_page":"281","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9896000027656555,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9733999967575073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.9470764398574829},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.8711640238761902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7639284133911133},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6641960144042969},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6089967489242554},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5455011129379272},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5025420188903809},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47421860694885254},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.4692290723323822},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3986092209815979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21307173371315002},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.21053731441497803},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15830811858177185}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9470764398574829},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.8711640238761902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639284133911133},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6641960144042969},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6089967489242554},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5455011129379272},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5025420188903809},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47421860694885254},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.4692290723323822},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3986092209815979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21307173371315002},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.21053731441497803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15830811858177185},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00778-023-00806-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00778-023-00806-z","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The VLDB Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4474361506","display_name":null,"funder_award_id":"CCF-1844234","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W344138311","https://openalex.org/W1987562803","https://openalex.org/W2011632873","https://openalex.org/W2019412213","https://openalex.org/W2021283827","https://openalex.org/W2067789269","https://openalex.org/W2097776316","https://openalex.org/W2100548092","https://openalex.org/W2108378253","https://openalex.org/W2121269638","https://openalex.org/W2167847032","https://openalex.org/W2585199909","https://openalex.org/W2964953836","https://openalex.org/W3016766662","https://openalex.org/W4231539689"],"related_works":["https://openalex.org/W2399644331","https://openalex.org/W2187092961","https://openalex.org/W2405436873","https://openalex.org/W2131677984","https://openalex.org/W4386026606","https://openalex.org/W52396946","https://openalex.org/W1973578339","https://openalex.org/W1824878879","https://openalex.org/W1998140328","https://openalex.org/W2462428821"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
