{"id":"https://openalex.org/W2898694032","doi":"https://doi.org/10.1007/978-3-030-00006-6_60","title":"MLS-Join: An Efficient MapReduce-Based Algorithm for String Similarity Self-joins with Edit Distance Constraint","display_name":"MLS-Join: An Efficient MapReduce-Based Algorithm for String Similarity Self-joins with Edit Distance Constraint","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2898694032","doi":"https://doi.org/10.1007/978-3-030-00006-6_60","mag":"2898694032"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-00006-6_60","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-00006-6_60","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5101072907","display_name":"Decai Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]},{"id":"https://openalex.org/I97009856","display_name":"Bohai University","ror":"https://ror.org/01kdzej58","country_code":"CN","type":"education","lineage":["https://openalex.org/I97009856"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Decai Sun","raw_affiliation_strings":["College of Information Science and Technology, Bohai University, Jinzhou, 121007, China","Key Laboratory of Big Data in Digital Publishing, SAPPRFT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Bohai University, Jinzhou, 121007, China","institution_ids":["https://openalex.org/I97009856"]},{"raw_affiliation_string":"Key Laboratory of Big Data in Digital Publishing, SAPPRFT, Beijing, China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100360046","display_name":"Xiaoxia Wang","orcid":"https://orcid.org/0000-0003-2625-6816"},"institutions":[{"id":"https://openalex.org/I97009856","display_name":"Bohai University","ror":"https://ror.org/01kdzej58","country_code":"CN","type":"education","lineage":["https://openalex.org/I97009856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxia Wang","raw_affiliation_strings":["Research and Teaching Institute of College Basics, Bohai University, Jinzhou, 121007, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Teaching Institute of College Basics, Bohai University, Jinzhou, 121007, China","institution_ids":["https://openalex.org/I97009856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101072907"],"corresponding_institution_ids":["https://openalex.org/I4210096250","https://openalex.org/I97009856"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17997174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"662","last_page":"674"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9894000291824341,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9779999852180481,"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/joins","display_name":"Joins","score":0.9487262964248657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8257467746734619},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7093477845191956},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6463930606842041},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6306353807449341},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6252486109733582},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5755102038383484},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5729871392250061},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5262883305549622},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4674343168735504},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.44772887229919434},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43906164169311523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.432911217212677},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4282175302505493},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.4208378195762634},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30623623728752136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22437942028045654},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.20189815759658813},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.17988425493240356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10510987043380737},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09190738201141357}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.9487262964248657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257467746734619},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7093477845191956},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6463930606842041},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6306353807449341},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6252486109733582},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5755102038383484},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5729871392250061},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5262883305549622},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4674343168735504},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.44772887229919434},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43906164169311523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.432911217212677},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4282175302505493},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.4208378195762634},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30623623728752136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22437942028045654},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.20189815759658813},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.17988425493240356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10510987043380737},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09190738201141357},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-00006-6_60","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-00006-6_60","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W82384364","https://openalex.org/W1647671624","https://openalex.org/W1950295237","https://openalex.org/W1973001156","https://openalex.org/W2001700730","https://openalex.org/W2007933321","https://openalex.org/W2019412213","https://openalex.org/W2065259291","https://openalex.org/W2096598900","https://openalex.org/W2104599107","https://openalex.org/W2150916025","https://openalex.org/W2151930506","https://openalex.org/W2161687051","https://openalex.org/W2169387919","https://openalex.org/W2241860760","https://openalex.org/W2286724461","https://openalex.org/W2344811709","https://openalex.org/W2490265015","https://openalex.org/W2555648367","https://openalex.org/W2611264129"],"related_works":["https://openalex.org/W2298204719","https://openalex.org/W2399644331","https://openalex.org/W2187092961","https://openalex.org/W2549495077","https://openalex.org/W52396946","https://openalex.org/W2748704845","https://openalex.org/W1564013439","https://openalex.org/W3175353343","https://openalex.org/W2119057313","https://openalex.org/W2405436873"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}