{"id":"https://openalex.org/W2236116266","doi":"https://doi.org/10.14778/2876473.2876478","title":"Repairing data through regular expressions","display_name":"Repairing data through regular expressions","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2236116266","doi":"https://doi.org/10.14778/2876473.2876478","mag":"2236116266"},"language":"en","primary_location":{"id":"doi:10.14778/2876473.2876478","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2876473.2876478","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100455061","display_name":"Zeyu Li","orcid":"https://orcid.org/0000-0001-9568-3315"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zeyu Li","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396652","display_name":"Hongzhi Wang","orcid":"https://orcid.org/0000-0002-7521-2871"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Wang","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083384987","display_name":"Wei Shao","orcid":"https://orcid.org/0000-0002-2401-009X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Shao","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387065","display_name":"Jianzhong Li","orcid":"https://orcid.org/0000-0002-4119-0571"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Li","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070851627","display_name":"Hong Gao","orcid":"https://orcid.org/0000-0002-2000-6683"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Gao","raw_affiliation_strings":["Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100455061"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":2.5227,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88151213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"5","first_page":"432","last_page":"443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.9965999722480774,"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/T11567","display_name":"semigroups and automata theory","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/regular-expression","display_name":"Regular expression","score":0.8657033443450928},{"id":"https://openalex.org/keywords/nondeterministic-algorithm","display_name":"Nondeterministic algorithm","score":0.6818095445632935},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6596246361732483},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6470491290092468},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6429372429847717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6419345736503601},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.5879100561141968},{"id":"https://openalex.org/keywords/nondeterministic-finite-automaton","display_name":"Nondeterministic finite automaton","score":0.5815597772598267},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5462450981140137},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5254995822906494},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.47142189741134644},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4650152325630188},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4544054865837097},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.42497286200523376},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3580820858478546},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.34518158435821533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2666212320327759},{"id":"https://openalex.org/keywords/automata-theory","display_name":"Automata theory","score":0.2471904754638672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11826074123382568},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08679080009460449}],"concepts":[{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.8657033443450928},{"id":"https://openalex.org/C176181172","wikidata":"https://www.wikidata.org/wiki/Q3490301","display_name":"Nondeterministic algorithm","level":2,"score":0.6818095445632935},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6596246361732483},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6470491290092468},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6429372429847717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6419345736503601},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5879100561141968},{"id":"https://openalex.org/C158008952","wikidata":"https://www.wikidata.org/wiki/Q617295","display_name":"Nondeterministic finite automaton","level":4,"score":0.5815597772598267},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5462450981140137},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5254995822906494},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.47142189741134644},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4650152325630188},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4544054865837097},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.42497286200523376},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3580820858478546},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.34518158435821533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2666212320327759},{"id":"https://openalex.org/C116248031","wikidata":"https://www.wikidata.org/wiki/Q214526","display_name":"Automata theory","level":3,"score":0.2471904754638672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11826074123382568},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08679080009460449},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2876473.2876478","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2876473.2876478","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W186914685","https://openalex.org/W1251444851","https://openalex.org/W1506285740","https://openalex.org/W1967167578","https://openalex.org/W1970026646","https://openalex.org/W1980706971","https://openalex.org/W1990058661","https://openalex.org/W2003684739","https://openalex.org/W2047805825","https://openalex.org/W2055693471","https://openalex.org/W2073329022","https://openalex.org/W2073545563","https://openalex.org/W2081186682","https://openalex.org/W2106895292","https://openalex.org/W2153531471","https://openalex.org/W2159296364","https://openalex.org/W2164187405","https://openalex.org/W2166559705","https://openalex.org/W2166858912","https://openalex.org/W2616737215"],"related_works":["https://openalex.org/W4249650827","https://openalex.org/W2090734721","https://openalex.org/W2154040222","https://openalex.org/W2089404966","https://openalex.org/W3094387502","https://openalex.org/W2170160673","https://openalex.org/W2115419634","https://openalex.org/W3143588635","https://openalex.org/W2089302579","https://openalex.org/W2157549685"],"abstract_inverted_index":{"Since":[0],"regular":[1,36,47,107],"expressions":[2],"are":[3],"often":[4],"used":[5],"to":[6,19,38,91,147],"detect":[7],"errors":[8],"in":[9,75],"sequences":[10],"such":[11],"as":[12],"strings":[13],"or":[14],"date,":[15],"it":[16],"is":[17,80,128,136],"natural":[18],"use":[20],"them":[21],"for":[22,151,170],"data":[23,31,43,184,193],"repair.":[24,64],"Motivated":[25],"by":[26,166],"this,":[27],"we":[28,68,158],"propose":[29,69],"a":[30,81,97,104,167],"repair":[32,60,191],"method":[33,55,162,189],"based":[34],"on":[35,179],"expression":[37,48,108],"make":[39],"the":[40,45,70,93,100,129,137,160,171,174,187,192],"input":[41,101,138],"sequence":[42,59,66],"obey":[44],"given":[46],"with":[49,109],"minimal":[50],"revision":[51],"cost.":[52],"The":[53],"proposed":[54,188],"contains":[56],"two":[57],"steps,":[58],"and":[61,103,118,134,163,182,195],"token":[62,155],"value":[63,156],"For":[65,154],"repair,":[67,157],"Regular-expression-based":[71],"Structural":[72],"Repair":[73],"(RSR":[74],"short)":[76],"algorithm.":[77],"RSR":[78],"algorithm":[79,84],"dynamic":[82],"programming":[83],"that":[85,186],"utilizes":[86],"Nondeterministic":[87],"Finite":[88],"Automata":[89],"(NFA)":[90],"calculate":[92],"edit":[94],"distance":[95],"between":[96],"prefix":[98],"of":[99,112,121,132,173],"string":[102,139],"partial":[105],"pattern":[106],"time":[110],"complexity":[111,120],"O":[113,122],"(":[114,123],"nm":[115],"2":[116],")":[117,125],"space":[119],"mn":[124],"where":[126],"m":[127],"edge":[130],"number":[131],"NFA":[133],"n":[135],"length.":[140],"We":[141],"also":[142],"develop":[143],"an":[144],"optimization":[145],"strategy":[146],"achieve":[148],"higher":[149],"performance":[150],"long":[152],"strings.":[153],"combine":[159],"edit-distance-based":[161],"associate":[164],"rules":[165],"unified":[168],"argument":[169],"selection":[172],"proper":[175],"method.":[176],"Experimental":[177],"results":[178],"both":[180],"real":[181],"synthetic":[183],"show":[185],"could":[190],"effectively":[194],"efficiently.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
