{"id":"https://openalex.org/W2053208677","doi":"https://doi.org/10.1145/2213556.2213566","title":"Deterministic regular expressions in linear time","display_name":"Deterministic regular expressions in linear time","publication_year":2012,"publication_date":"2012-05-21","ids":{"openalex":"https://openalex.org/W2053208677","doi":"https://doi.org/10.1145/2213556.2213566","mag":"2053208677"},"language":"en","primary_location":{"id":"doi:10.1145/2213556.2213566","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213556.2213566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGMOD-SIGACT-SIGAI symposium on Principles of Database Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00618451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035780800","display_name":"Benot\u00eet Groz","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Benot\u00eet Groz","raw_affiliation_strings":["INRIA and University of Lille, Lille, France"],"affiliations":[{"raw_affiliation_string":"INRIA and University of Lille, Lille, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010785818","display_name":"Sebastian Maneth","orcid":"https://orcid.org/0000-0001-8667-5436"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sebastian Maneth","raw_affiliation_strings":["NICTA and UNSW, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"NICTA and UNSW, Sydney, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038280683","display_name":"S\u0142awek Staworko","orcid":"https://orcid.org/0000-0003-3684-3395"},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Slawek Staworko","raw_affiliation_strings":["INRIA and University of Lille, Lille, France"],"affiliations":[{"raw_affiliation_string":"INRIA and University of Lille, Lille, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035780800"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I2279609970"],"apc_list":null,"apc_paid":null,"fwci":3.9791,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93678445,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/regular-expression","display_name":"Regular expression","score":0.7219095826148987},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6831373572349548},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6762086749076843},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.6722182035446167},{"id":"https://openalex.org/keywords/decidability","display_name":"Decidability","score":0.56265789270401},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5122713446617126},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5092722177505493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47319361567497253},{"id":"https://openalex.org/keywords/regular-language","display_name":"Regular language","score":0.4247582256793976},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.42399877309799194},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.4139830470085144},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40454190969467163},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39388400316238403},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.34423911571502686},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2715511620044708}],"concepts":[{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.7219095826148987},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6831373572349548},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6762086749076843},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.6722182035446167},{"id":"https://openalex.org/C153269930","wikidata":"https://www.wikidata.org/wiki/Q430001","display_name":"Decidability","level":2,"score":0.56265789270401},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5122713446617126},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5092722177505493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47319361567497253},{"id":"https://openalex.org/C52370388","wikidata":"https://www.wikidata.org/wiki/Q752532","display_name":"Regular language","level":3,"score":0.4247582256793976},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.42399877309799194},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.4139830470085144},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40454190969467163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39388400316238403},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.34423911571502686},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2715511620044708},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/2213556.2213566","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213556.2213566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGMOD-SIGACT-SIGAI symposium on Principles of Database Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.9828","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.9828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/61/84/51/PDF/1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.659.7579","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.659.7579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/inria-00618451/document/","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.728.3360","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.728.3360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://researchers.lille.inria.fr/%7Estaworko/papers/groz-pods12.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00618451v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00618451","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PODS-31th ACM Symposium on Principles of Database Systems, 2012, Scottsdale, United States. pp.12","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00618451v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00618451","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PODS-31th ACM Symposium on Principles of Database Systems, 2012, Scottsdale, United States. pp.12","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W81175699","https://openalex.org/W92484003","https://openalex.org/W421997344","https://openalex.org/W1517365704","https://openalex.org/W1548501023","https://openalex.org/W1571991326","https://openalex.org/W1572916762","https://openalex.org/W1600029487","https://openalex.org/W1963838724","https://openalex.org/W1966773178","https://openalex.org/W1968420454","https://openalex.org/W2002089154","https://openalex.org/W2011999472","https://openalex.org/W2014571800","https://openalex.org/W2022532439","https://openalex.org/W2022626404","https://openalex.org/W2057185776","https://openalex.org/W2059078591","https://openalex.org/W2063985934","https://openalex.org/W2065394462","https://openalex.org/W2077450865","https://openalex.org/W2092860912","https://openalex.org/W2099540492","https://openalex.org/W2109486375","https://openalex.org/W2131239155","https://openalex.org/W2136238707","https://openalex.org/W2138917091","https://openalex.org/W2569219525","https://openalex.org/W2971427543","https://openalex.org/W3140808638","https://openalex.org/W6631061626"],"related_works":["https://openalex.org/W2604580999","https://openalex.org/W2160667301","https://openalex.org/W2950141706","https://openalex.org/W3157903927","https://openalex.org/W1607287758","https://openalex.org/W2510632068","https://openalex.org/W2204191597","https://openalex.org/W1972592804","https://openalex.org/W2240836793","https://openalex.org/W252108735"],"abstract_inverted_index":{"Deterministic":[0],"regular":[1,12,33,90,149],"expressions":[2,13,101,117,150],"are":[3,19],"widely":[4],"used":[5],"in":[6,14,39,62,79,102,118],"XML":[7,17],"processing.":[8],"For":[9,145],"instance,":[10],"all":[11],"DTDs":[15],"and":[16,112,127],"Schemas":[18],"required":[20],"to":[21],"be":[22,37,77],"deterministic.":[23],"In":[24],"this":[25],"paper":[26],"we":[27,151],"show":[28,66],"that":[29,67],"determinism":[30],"of":[31,59,88,110,123,139,143],"a":[32,69,85,107,135],"expression":[34,74],"e":[35,75],"can":[36,76],"tested":[38],"linear":[40,81],"time.":[41],"The":[42],"best":[43],"known":[44],"algorithms,":[45],"based":[46],"on":[47],"the":[48,57,120,140],"Glushkov":[49],"automaton,":[50],"require":[51],"O(\u03c3|e|)":[52],"time,":[53],"where":[54],"\u03c3":[55],"is":[56,130],"number":[58,109],"distinct":[60],"symbols":[61,129],"e.":[63,144],"We":[64],"further":[65],"matching":[68,146],"word":[70],"w":[71],"against":[72],"an":[73,153],"achieved":[78],"combined":[80],"time":[82,158],"O(|e|+|w|),":[83],"for":[84],"wide":[86],"range":[87],"deterministic":[89,148],"expressions:":[91],"(i)":[92],"star-free":[93],"(for":[94],"multiple":[95],"input":[96],"words),":[97],"(ii)":[98],"bounded-occurrence,":[99],"i.e.,":[100,116],"which":[103,119],"each":[104],"symbol":[105],"appears":[106],"bounded":[108,114],"times,":[111],"(iii)":[113],"plus-depth,":[115],"nesting":[121],"depth":[122],"alternating":[124],"plus":[125],"(union)":[126],"concatenation":[128],"bounded.":[131],"Our":[132],"algorithms":[133],"use":[134],"new":[136],"structural":[137],"decomposition":[138],"parse":[141],"tree":[142],"arbitrary":[147],"present":[152],"O(|e|":[154],"+":[155],"|w|log":[156],"log|e|)":[157],"algorithm.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
