{"id":"https://openalex.org/W2766530067","doi":"https://doi.org/10.14778/3151113.3151118","title":"Approximate string joins with abbreviations","display_name":"Approximate string joins with abbreviations","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2766530067","doi":"https://doi.org/10.14778/3151113.3151118","mag":"2766530067"},"language":"en","primary_location":{"id":"doi:10.14778/3151113.3151118","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3151113.3151118","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/118039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018442175","display_name":"Wenbo Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Wenbo Tao","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103237059","display_name":"Dong Deng","orcid":"https://orcid.org/0000-0002-4596-3850"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dong Deng","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074724644","display_name":"Michael Stonebraker","orcid":"https://orcid.org/0000-0001-9184-9058"},"institutions":[{"id":"https://openalex.org/I4210109586","display_name":"Moscow Institute of Thermal Technology","ror":"https://ror.org/021es5e59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210109586"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Michael Stonebraker","raw_affiliation_strings":["MIT"],"affiliations":[{"raw_affiliation_string":"MIT","institution_ids":["https://openalex.org/I4210109586"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018442175"],"corresponding_institution_ids":["https://openalex.org/I4210109586"],"apc_list":null,"apc_paid":null,"fwci":5.1191,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95361545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"11","issue":"1","first_page":"53","last_page":"65"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9921000003814697,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.987500011920929,"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":0.8498377203941345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8093286752700806},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7766108512878418},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7016322612762451},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6691499352455139},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5423901677131653},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5126256346702576},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47660961747169495},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.45766785740852356},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45675310492515564},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.44167160987854004},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3682623505592346},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.35921138525009155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3106071949005127},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2437623143196106},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.11324262619018555},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10112527012825012},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08869624137878418}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8498377203941345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8093286752700806},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7766108512878418},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7016322612762451},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6691499352455139},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5423901677131653},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5126256346702576},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47660961747169495},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.45766785740852356},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45675310492515564},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.44167160987854004},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3682623505592346},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.35921138525009155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3106071949005127},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2437623143196106},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.11324262619018555},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10112527012825012},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08869624137878418},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3151113.3151118","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3151113.3151118","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/118039","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/118039","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/118039","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/118039","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W95925839","https://openalex.org/W176238691","https://openalex.org/W178298440","https://openalex.org/W1933390880","https://openalex.org/W1973001156","https://openalex.org/W1991154713","https://openalex.org/W2003979824","https://openalex.org/W2016995838","https://openalex.org/W2019412213","https://openalex.org/W2037594241","https://openalex.org/W2044163187","https://openalex.org/W2065259291","https://openalex.org/W2072173758","https://openalex.org/W2088772188","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2100548092","https://openalex.org/W2105785161","https://openalex.org/W2115214414","https://openalex.org/W2118658201","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2134189109","https://openalex.org/W2150916025","https://openalex.org/W2161936973","https://openalex.org/W2162006472","https://openalex.org/W2166400748","https://openalex.org/W2406430107","https://openalex.org/W6677601337"],"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/W1985051577","https://openalex.org/W2952544458"],"abstract_inverted_index":{"String":[0],"joins":[1,31],"have":[2,52,63],"wide":[3],"applications":[4],"in":[5,73,120,192],"data":[6,13,16],"integration":[7],"and":[8,20,149,172,187,195],"cleaning.":[9],"The":[10],"inconsistency":[11],"of":[12,46,59,76,158],"caused":[14],"by":[15],"errors,":[17],"term":[18,47],"variations":[19],"missing":[21],"values":[22],"has":[23],"led":[24],"to":[25,90,111,154],"the":[26,74,91,96,121,146],"need":[27],"for":[28],"approximate":[29],"string":[30],"(ASJ).":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"study":[37],"ASJ":[38,54],"with":[39],"abbreviations,":[40],"which":[41],"are":[42,86,103,116],"a":[43,56,124,156],"frequent":[44],"type":[45],"variation.":[48],"Although":[49],"prior":[50],"works":[51],"studied":[53],"given":[55],"user-inputted":[57],"dictionary":[58,97,157],"synonym":[60],"rules,":[61],"they":[62,68],"three":[64,117],"common":[65],"limitations.":[66,114],"First,":[67],"suffer":[69],"from":[70,161],"low":[71],"precision":[72],"presence":[75],"abbreviations":[77,102,129,135],"having":[78,136],"multiple":[79,137],"full":[80,138],"forms.":[81],"Second,":[82],"their":[83],"join":[84,143,179],"algorithms":[85],"not":[87,99],"scalable":[88],"due":[89],"exponential":[92],"time":[93],"complexity.":[94],"Third,":[95],"may":[98],"exist":[100],"since":[101],"highly":[104],"domain-dependent.":[105],"We":[106,164],"propose":[107],"an":[108,141,151],"end-to-end":[109],"workflow":[110,167,176],"address":[112],"these":[113],"There":[115],"main":[118],"components":[119],"workflow:":[122],"(1)":[123],"new":[125],"similarity":[126],"measure":[127],"taking":[128],"into":[130],"account":[131],"that":[132,174],"can":[133],"handle":[134],"forms,":[139],"(2)":[140],"efficient":[142],"algorithm":[144],"following":[145],"filter-verification":[147],"framework":[148],"(3)":[150],"unsupervised":[152],"approach":[153],"learn":[155],"abbreviation":[159],"rules":[160],"input":[162,184],"strings.":[163],"evaluate":[165],"our":[166,175],"on":[168],"four":[169],"real-world":[170],"datasets":[171],"show":[173],"outputs":[177],"accurate":[178],"results,":[180],"scales":[181],"well":[182],"as":[183],"size":[185],"grows":[186],"greatly":[188],"outperforms":[189],"state-of-the-art":[190],"approaches":[191],"both":[193],"accuracy":[194],"efficiency.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}