{"id":"https://openalex.org/W4385270289","doi":"https://doi.org/10.1109/icde55515.2023.00356","title":"Efficient Regular Expression Matching Based on Positional Inverted Index : (Extended Abstract)","display_name":"Efficient Regular Expression Matching Based on Positional Inverted Index : (Extended Abstract)","publication_year":2023,"publication_date":"2023-04-01","ids":{"openalex":"https://openalex.org/W4385270289","doi":"https://doi.org/10.1109/icde55515.2023.00356"},"language":"en","primary_location":{"id":"doi:10.1109/icde55515.2023.00356","doi":"https://doi.org/10.1109/icde55515.2023.00356","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icde55515.2023.00356","pdf_url":null,"source":{"id":"https://openalex.org/S4210210321","display_name":"IEEE International Conference on Data Engineering (ICDE)","issn_l":"1084-4627","issn":["1084-4627","2375-0286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 39th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},"volume":null,"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/A5007388157","display_name":"Tao Qiu","orcid":"https://orcid.org/0000-0002-1410-7795","observed_orcids":["https://orcid.org/0000-0002-1410-7795"]},"institutions":[{"id":"https://openalex.org/I125904092","display_name":"Shenyang Aerospace University","ror":"https://ror.org/02423gm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I125904092"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qiu","raw_affiliation_strings":["Shenyang Aerospace University,School of Computer Science,China","School of Computer Science, Shenyang Aerospace University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenyang Aerospace University,School of Computer Science,China","institution_ids":["https://openalex.org/I125904092"]},{"raw_affiliation_string":"School of Computer Science, Shenyang Aerospace University, China","institution_ids":["https://openalex.org/I125904092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079763362","display_name":"Xiaochun Yang","orcid":"https://orcid.org/0000-0002-6184-4771","observed_orcids":["https://orcid.org/0000-0002-6184-4771"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Yang","raw_affiliation_strings":["Northeastern University,Liaoning,China,110819"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Liaoning,China,110819","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372342","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-2694-1023","observed_orcids":["https://orcid.org/0000-0002-2694-1023"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Northeastern University,Liaoning,China,110819"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,Liaoning,China,110819","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wei Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), China","institution_ids":["https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06962808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"3859","last_page":"3860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9901999831199646,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9901999831199646,"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":"Advanced Database Systems and Queries","score":0.008100000210106373,"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"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0006000000284984708,"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/regular-expression-matching","display_name":"regular expression matching","score":0.996999979019165},{"id":"https://openalex.org/keywords/query-plan-generation","display_name":"query plan generation","score":0.5360000133514404},{"id":"https://openalex.org/keywords/position-constraints","display_name":"position constraints","score":0.8740000128746033},{"id":"https://openalex.org/keywords/text-retrieval","display_name":"text retrieval","score":0.3779999911785126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.9026925563812256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229203224182129},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.644867479801178},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5633662343025208},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.5627210140228271},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.43193376064300537},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4229891896247864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4074220359325409},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37763863801956177},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34536850452423096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2507212162017822},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.12992647290229797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11398234963417053},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde55515.2023.00356","doi":"https://doi.org/10.1109/icde55515.2023.00356","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icde55515.2023.00356","pdf_url":null,"source":{"id":"https://openalex.org/S4210210321","display_name":"IEEE International Conference on Data Engineering (ICDE)","issn_l":"1084-4627","issn":["1084-4627","2375-0286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 39th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-130299","doi":null,"is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1084-4627&rft.volume=2023-April&rft.issue=&rft.date=2023&rft.spage=3859&rft.aulast=Qiu&rft.aufirst=Tao&rft.atitle=Efficient+Regular+Expression+Matching+Based+on+Positional+Inverted+Index+%3A+%28Extended+Abstract%29&rft.title=Proceedings+-+International+Conference+on+Data+Engineering","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2003683276","https://openalex.org/W2168160104","https://openalex.org/W2302109632"],"related_works":["https://openalex.org/W3025471711","https://openalex.org/W4406249870","https://openalex.org/W4366572714","https://openalex.org/W7100632674","https://openalex.org/W1886913647","https://openalex.org/W4237643769","https://openalex.org/W1599747842","https://openalex.org/W4381326842","https://openalex.org/W2049793868","https://openalex.org/W2168160104"],"abstract_inverted_index":{"We":[0,104],"study":[1],"the":[2,22,55,111,146,149,157,162],"efficient":[3],"regular":[4],"expression":[5],"(regex)":[6],"matching":[7,90,120],"problem.":[8],"Existing":[9],"algorithms":[10,13],"are":[11,69],"scanning-based":[12,56],"that":[14,132,185],"typically":[15],"use":[16],"an":[17,194],"equivalent":[18],"automaton":[19],"compiled":[20],"from":[21],"regex":[23,94,115,119],"query":[24,46,95,142,147,158,168,199],"to":[25,35,38,53,58,75,86,109,144,155,164,193],"verify":[26,59],"a":[27,42,45,83,93,99,106,114,166,173],"document.":[28],"Although":[29],"some":[30],"works":[31],"propose":[32,82,105,139],"various":[33],"strategies":[34],"quickly":[36],"jump":[37],"candidate":[39,61,72],"locations":[40,73,121],"in":[41,198],"document":[43],"where":[44],"result":[47],"may":[48],"appear,":[49],"they":[50],"still":[51,70],"need":[52],"utilize":[54],"method":[57,187],"these":[60],"locations.":[62],"These":[63],"methods":[64,190],"become":[65],"inefficient":[66],"when":[67],"there":[68],"many":[71],"needed":[74],"be":[76,123],"verified.":[77],"In":[78,153],"this":[79],"paper,":[80],"we":[81,138,160],"novel":[84],"approach":[85],"efficiently":[87],"compute":[88],"all":[89,118],"positions":[91,127],"for":[92,176],"purely":[96],"based":[97],"on":[98,128,181],"positional":[100,135,150,177],"q-gram":[101],"inverted":[102,151],"index.":[103,152],"gram-driven":[107],"NFA":[108],"represent":[110],"language":[112],"of":[113,130,196],"and":[116],"show":[117,184],"can":[122],"obtained":[124],"by":[125,170,191],"finding":[126],"q-grams":[129],"GNFA":[131],"satisfy":[133],"certain":[134],"constraints.":[136,178],"Then":[137],"several":[140],"GNFA-based":[141],"plans":[143],"answer":[145],"using":[148],"order":[154,175,195],"improve":[156],"efficiency,":[159],"design":[161],"algorithm":[163],"build":[165],"tree-based":[167],"plan":[169],"carefully":[171],"choosing":[172],"checking":[174],"Experimental":[179],"results":[180],"real-world":[182],"datasets":[183],"our":[186],"outperforms":[188],"state-of-the-art":[189],"up":[192],"magnitude":[197],"efficiency.":[200]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-07-27T00:00:00"}