{"id":"https://openalex.org/W3007878418","doi":"https://doi.org/10.46298/lmcs-19(3:12)2023","title":"The Complexity of Aggregates over Extractions by Regular Expressions","display_name":"The Complexity of Aggregates over Extractions by Regular Expressions","publication_year":2023,"publication_date":"2023-08-09","ids":{"openalex":"https://openalex.org/W3007878418","doi":"https://doi.org/10.46298/lmcs-19(3:12)2023","mag":"3007878418"},"language":"en","primary_location":{"id":"doi:10.46298/lmcs-19(3:12)2023","is_oa":true,"landing_page_url":"https://doi.org/10.46298/lmcs-19(3:12)2023","pdf_url":"https://lmcs.episciences.org/11712/pdf","source":{"id":"https://openalex.org/S114379355","display_name":"Logical Methods in Computer Science","issn_l":"1860-5974","issn":["1860-5974"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313916","host_organization_name":"Logical Methods in Computer Science e.V.","host_organization_lineage":["https://openalex.org/P4310313916"],"host_organization_lineage_names":["Logical Methods in Computer Science e.V."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Logical Methods in Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://lmcs.episciences.org/11712/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082548231","display_name":"Johannes Doleschal","orcid":null},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]},{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]}],"countries":["BE","DE"],"is_corresponding":false,"raw_author_name":"Johannes Doleschal","raw_affiliation_strings":["Hasselt University, Belgium","University of Bayreuth, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasselt University, Belgium","institution_ids":["https://openalex.org/I878454856"]},{"raw_affiliation_string":"University of Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006706357","display_name":"Benny Kimelfeld","orcid":"https://orcid.org/0000-0002-7156-1572"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Benny Kimelfeld","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016412428","display_name":"Wim Martens","orcid":"https://orcid.org/0000-0001-9480-3522"},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wim Martens","raw_affiliation_strings":["University of Bayreuth, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3931,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66301642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"Volume 19, Issue 3","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987000226974487,"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":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.6403672695159912},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6274470686912537},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6043500900268555},{"id":"https://openalex.org/keywords/closure","display_name":"Closure (psychology)","score":0.5842940807342529},{"id":"https://openalex.org/keywords/complexity-class","display_name":"Complexity class","score":0.553463339805603},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5293774604797363},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5100250840187073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5043627023696899},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5036823153495789},{"id":"https://openalex.org/keywords/regular-language","display_name":"Regular language","score":0.47943681478500366},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.47032082080841064},{"id":"https://openalex.org/keywords/relational-algebra","display_name":"Relational algebra","score":0.4435688853263855},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.4330664277076721},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37989455461502075},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33683598041534424},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3268775939941406},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26855796575546265},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.16708657145500183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12875506281852722},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.10540568828582764}],"concepts":[{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.6403672695159912},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6274470686912537},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6043500900268555},{"id":"https://openalex.org/C146834321","wikidata":"https://www.wikidata.org/wiki/Q2979672","display_name":"Closure (psychology)","level":2,"score":0.5842940807342529},{"id":"https://openalex.org/C39637292","wikidata":"https://www.wikidata.org/wiki/Q908207","display_name":"Complexity class","level":3,"score":0.553463339805603},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5293774604797363},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5100250840187073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5043627023696899},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5036823153495789},{"id":"https://openalex.org/C52370388","wikidata":"https://www.wikidata.org/wiki/Q752532","display_name":"Regular language","level":3,"score":0.47943681478500366},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.47032082080841064},{"id":"https://openalex.org/C95916125","wikidata":"https://www.wikidata.org/wiki/Q840540","display_name":"Relational algebra","level":3,"score":0.4435688853263855},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.4330664277076721},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37989455461502075},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33683598041534424},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3268775939941406},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26855796575546265},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.16708657145500183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12875506281852722},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.10540568828582764},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.46298/lmcs-19(3:12)2023","is_oa":true,"landing_page_url":"https://doi.org/10.46298/lmcs-19(3:12)2023","pdf_url":"https://lmcs.episciences.org/11712/pdf","source":{"id":"https://openalex.org/S114379355","display_name":"Logical Methods in Computer Science","issn_l":"1860-5974","issn":["1860-5974"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313916","host_organization_name":"Logical Methods in Computer Science e.V.","host_organization_lineage":["https://openalex.org/P4310313916"],"host_organization_lineage_names":["Logical Methods in Computer Science e.V."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Logical Methods in Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2002.08828","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.08828","pdf_url":"https://arxiv.org/pdf/2002.08828","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:documentserver.uhasselt.be:1942/43193","is_oa":true,"landing_page_url":"http://hdl.handle.net/1942/43193","pdf_url":"https://documentserver.uhasselt.be//bitstream/1942/43193/1/The%20Complexity%20of%20Aggregates%20over%20Extractions%20by%20Regular%20Expressions.pdf","source":{"id":"https://openalex.org/S4306401926","display_name":"Document Server@UHasselt (UHasselt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I878454856","host_organization_name":"Hasselt University","host_organization_lineage":["https://openalex.org/I878454856"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:e355b4bc644d4efe8ca731b87a322f1a","is_oa":true,"landing_page_url":"https://doaj.org/article/e355b4bc644d4efe8ca731b87a322f1a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Logical Methods in Computer Science, Vol Volume 19, Issue 3 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.46298/lmcs-19(3:12)2023","is_oa":true,"landing_page_url":"https://doi.org/10.46298/lmcs-19(3:12)2023","pdf_url":"https://lmcs.episciences.org/11712/pdf","source":{"id":"https://openalex.org/S114379355","display_name":"Logical Methods in Computer Science","issn_l":"1860-5974","issn":["1860-5974"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313916","host_organization_name":"Logical Methods in Computer Science e.V.","host_organization_lineage":["https://openalex.org/P4310313916"],"host_organization_lineage_names":["Logical Methods in Computer Science e.V."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Logical Methods in Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1247588296","display_name":"Quantitative Analyse von Datenbankanfragen","funder_award_id":"412400621","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3881880258","display_name":null,"funder_award_id":"1295/15","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G4323302766","display_name":"Anfrage und Spezifikationssprachen f\u00fcr Graph und GridStrukturierte Daten","funder_award_id":"369116833","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5753352471","display_name":null,"funder_award_id":"768/19","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320947","display_name":"German-Israeli Foundation for Scientific Research and Development","ror":"https://ror.org/00tntzp09"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007878418.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1599188306","https://openalex.org/W1608462205","https://openalex.org/W1643571618","https://openalex.org/W1934084512","https://openalex.org/W1975501803","https://openalex.org/W1986891954","https://openalex.org/W1987679716","https://openalex.org/W1994118705","https://openalex.org/W2015174807","https://openalex.org/W2020147322","https://openalex.org/W2028660080","https://openalex.org/W2036095420","https://openalex.org/W2036667662","https://openalex.org/W2064257849","https://openalex.org/W2064838169","https://openalex.org/W2072181151","https://openalex.org/W2072242455","https://openalex.org/W2078003433","https://openalex.org/W2106691851","https://openalex.org/W2110367654","https://openalex.org/W2129999749","https://openalex.org/W2135779000","https://openalex.org/W2141456009","https://openalex.org/W2143658255","https://openalex.org/W2177243619","https://openalex.org/W2293299776","https://openalex.org/W2363785281","https://openalex.org/W2421547754","https://openalex.org/W2604165918","https://openalex.org/W2748837517","https://openalex.org/W2769041395","https://openalex.org/W2770406504","https://openalex.org/W2883227679","https://openalex.org/W2888585419","https://openalex.org/W2890631112","https://openalex.org/W2895689912","https://openalex.org/W2904220453","https://openalex.org/W2923538364","https://openalex.org/W2948686875","https://openalex.org/W2959716049","https://openalex.org/W2962679309","https://openalex.org/W2963125544","https://openalex.org/W2963170321","https://openalex.org/W2963265283","https://openalex.org/W2963383248","https://openalex.org/W2963560792","https://openalex.org/W3013294921","https://openalex.org/W3014011840","https://openalex.org/W3138379487","https://openalex.org/W3198906529","https://openalex.org/W4210412562","https://openalex.org/W4285719527","https://openalex.org/W4288560456","https://openalex.org/W4322760930"],"related_works":["https://openalex.org/W2603910788","https://openalex.org/W1582705003","https://openalex.org/W2280368318","https://openalex.org/W2105843429","https://openalex.org/W2613180196","https://openalex.org/W2067443406","https://openalex.org/W2057841333","https://openalex.org/W2998389348","https://openalex.org/W4386081251","https://openalex.org/W2964091527"],"abstract_inverted_index":{"Regular":[0],"expressions":[1],"with":[2,121],"capture":[3],"variables,":[4],"also":[5],"known":[6],"as":[7,54],"regex-formulas,":[8],"extract":[9],"relations":[10],"of":[11,27,34,47,61,82],"spans":[12],"(intervals":[13],"identified":[14],"by":[15,50],"their":[16],"start":[17],"and":[18,57,77,84],"end":[19],"indices)":[20],"from":[21],"text.":[22],"In":[23,106],"turn,":[24],"the":[25,32,35,39,44,79],"class":[26],"regular":[28,62,74],"document":[29,63,75],"spanners":[30,76],"is":[31,113],"closure":[33],"regex":[36],"formulas":[37],"under":[38],"Relational":[40],"Algebra.":[41],"We":[42],"investigate":[43],"computational":[45,80],"complexity":[46,81],"querying":[48],"text":[49],"aggregate":[51,71,98],"functions,":[52],"such":[53],"sum,":[55],"average,":[56],"quantile,":[58],"on":[59],"top":[60],"spanners.":[64],"To":[65],"this":[66],"end,":[67],"we":[68,89],"formally":[69],"define":[70],"functions":[72,99],"over":[73],"analyze":[78],"exact":[83,111],"approximate":[85],"computation.":[86],"More":[87],"precisely,":[88],"show":[90],"that":[91],"in":[92,103],"a":[93],"restricted":[94],"case,":[95],"all":[96],"studied":[97],"can":[100,117],"be":[101,119],"computed":[102],"polynomial":[104],"time.":[105],"general,":[107],"however,":[108],"even":[109],"though":[110],"computation":[112],"intractable,":[114],"some":[115],"aggregates":[116],"still":[118],"approximated":[120],"fully":[122],"polynomial-time":[123],"randomized":[124],"approximation":[125],"schemes":[126],"(FPRAS).":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}