{"id":"https://openalex.org/W2604165918","doi":"https://doi.org/10.1145/3196959.3196967","title":"Joining Extractions of Regular Expressions","display_name":"Joining Extractions of Regular Expressions","publication_year":2018,"publication_date":"2018-05-15","ids":{"openalex":"https://openalex.org/W2604165918","doi":"https://doi.org/10.1145/3196959.3196967","mag":"2604165918"},"language":"en","primary_location":{"id":"doi:10.1145/3196959.3196967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3196959.3196967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.lboro.ac.uk/2134/26421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078139232","display_name":"Dominik D. Freydenberger","orcid":"https://orcid.org/0000-0001-5088-0067"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dominik D. Freydenberger","raw_affiliation_strings":["Loughborough University, Loughborough, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University, Loughborough, United Kingdom","institution_ids":["https://openalex.org/I143804889"]}]},{"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/A5077872338","display_name":"Liat Peterfreund","orcid":"https://orcid.org/0000-0002-4788-0944"},"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":"Liat Peterfreund","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"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":0.9980000257492065,"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/conjunctive-query","display_name":"Conjunctive query","score":0.7918405532836914},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7647888660430908},{"id":"https://openalex.org/keywords/relational-algebra","display_name":"Relational algebra","score":0.5212879180908203},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.47496339678764343},{"id":"https://openalex.org/keywords/exponential-time-hypothesis","display_name":"Exponential time hypothesis","score":0.47077223658561707},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46694767475128174},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.4662999212741852},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4633429944515228},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.46096205711364746},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.44621002674102783},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.44581297039985657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4114741086959839},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.3804464340209961},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3655960261821747},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08349010348320007}],"concepts":[{"id":"https://openalex.org/C65647387","wikidata":"https://www.wikidata.org/wiki/Q1781706","display_name":"Conjunctive query","level":3,"score":0.7918405532836914},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7647888660430908},{"id":"https://openalex.org/C95916125","wikidata":"https://www.wikidata.org/wiki/Q840540","display_name":"Relational algebra","level":3,"score":0.5212879180908203},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.47496339678764343},{"id":"https://openalex.org/C71017364","wikidata":"https://www.wikidata.org/wiki/Q5421532","display_name":"Exponential time hypothesis","level":3,"score":0.47077223658561707},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46694767475128174},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.4662999212741852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4633429944515228},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.46096205711364746},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.44621002674102783},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44581297039985657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4114741086959839},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3804464340209961},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3655960261821747},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08349010348320007},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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:10.1145/3196959.3196967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3196959.3196967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.lboro.ac.uk:2134/26421","is_oa":true,"landing_page_url":"https://dspace.lboro.ac.uk/2134/26421","pdf_url":null,"source":{"id":"https://openalex.org/S4306401023","display_name":"Loughborough University Institutional Repository (Loughborough University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143804889","host_organization_name":"Loughborough University","host_organization_lineage":["https://openalex.org/I143804889"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symposium on Principles of Database Systems","raw_type":"Conference Contribution"}],"best_oa_location":{"id":"pmh:oai:dspace.lboro.ac.uk:2134/26421","is_oa":true,"landing_page_url":"https://dspace.lboro.ac.uk/2134/26421","pdf_url":null,"source":{"id":"https://openalex.org/S4306401023","display_name":"Loughborough University Institutional Repository (Loughborough University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143804889","host_organization_name":"Loughborough University","host_organization_lineage":["https://openalex.org/I143804889"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symposium on Principles of Database Systems","raw_type":"Conference Contribution"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3105452648","display_name":null,"funder_award_id":"FR 3551/1-1","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"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W36639738","https://openalex.org/W52840101","https://openalex.org/W133886465","https://openalex.org/W797346804","https://openalex.org/W1514152137","https://openalex.org/W1558832481","https://openalex.org/W1570425181","https://openalex.org/W1608639859","https://openalex.org/W1934084512","https://openalex.org/W1979514837","https://openalex.org/W1996328142","https://openalex.org/W1997520998","https://openalex.org/W1999563429","https://openalex.org/W2002089154","https://openalex.org/W2007940874","https://openalex.org/W2009591769","https://openalex.org/W2022166150","https://openalex.org/W2035266017","https://openalex.org/W2048685245","https://openalex.org/W2065023965","https://openalex.org/W2068882115","https://openalex.org/W2102632804","https://openalex.org/W2110367654","https://openalex.org/W2119422073","https://openalex.org/W2122112897","https://openalex.org/W2122865749","https://openalex.org/W2135779000","https://openalex.org/W2141456009","https://openalex.org/W2144416276","https://openalex.org/W2152336115","https://openalex.org/W2159636537","https://openalex.org/W2170798490","https://openalex.org/W2187169338","https://openalex.org/W2278936816","https://openalex.org/W2286758035","https://openalex.org/W2302109632","https://openalex.org/W2319151433","https://openalex.org/W2434235452","https://openalex.org/W2466758040","https://openalex.org/W2480499276","https://openalex.org/W2616567161","https://openalex.org/W2724745846","https://openalex.org/W2890631112","https://openalex.org/W2913688336","https://openalex.org/W3196919033","https://openalex.org/W4292230561","https://openalex.org/W4313371817"],"related_works":["https://openalex.org/W1505212787","https://openalex.org/W4226251578","https://openalex.org/W2127795772","https://openalex.org/W3047081115","https://openalex.org/W2949144621","https://openalex.org/W3107700780","https://openalex.org/W3170346938","https://openalex.org/W3092785261","https://openalex.org/W1967430536","https://openalex.org/W2046615742"],"abstract_inverted_index":{"Regular":[0],"expressions":[1],"with":[2,181,206],"capture":[3],"variables,":[4],"also":[5,100],"known":[6,79],"as":[7,28],"\"regex":[8],"formulas,''":[9],"extract":[10],"relations":[11,19],"of":[12,33,48,57,62,84,140,164,192,217],"spans":[13],"(interval":[14],"positions)":[15],"from":[16,96,116],"text.":[17,111],"These":[18],"can":[20,178,198],"be":[21,146,179,199],"further":[22],"manipulated":[23],"via":[24],"the":[25,31,46,81,90,97,113,117,125,150,212,215,218],"relational":[26,98,118,126],"Algebra":[27],"studied":[29],"in":[30,70,102,105],"context":[32],"\"document":[34],"spanners,\"":[35],"Fagin":[36],"et":[37],"al.'s":[38],"formal":[39],"framework":[40],"for":[41],"information":[42],"extraction.":[43],"We":[44,87],"investigate":[45],"complexity":[47,83],"querying":[49],"text":[50],"by":[51,153],"Conjunctive":[52],"Queries":[53],"(CQs)":[54],"and":[55,94,130,196],"Unions":[56],"CQs":[58],"(UCQs)":[59],"on":[60,73],"top":[61],"regex":[63,155],"formulas.":[64],"Such":[65],"queries":[66],"have":[67],"been":[68],"investigated":[69],"prior":[71],"work":[72],"document":[74],"spanners,":[75],"but":[76],"little":[77],"is":[78,142,204,214],"about":[80],"(combined)":[82],"their":[85],"evaluation.":[86],"show":[88],"that":[89,143,185],"lower":[91],"bounds":[92,115],"(NP-completeness":[93],"W[1]-hardness)":[95],"world":[99,119],"hold":[101],"our":[103],"setting;":[104],"particular,":[106,176],"hardness":[107,141],"hits":[108],"already":[109],"single-character":[110],"Yet,":[112,166],"upper":[114,173],"do":[120],"not":[121],"carry":[122],"over.":[123],"Unlike":[124],"world,":[127],"acyclic":[128],"CQs,":[129,133],"even":[131],"gamma-acyclic":[132],"are":[134,168],"hard":[135],"to":[136,148,170],"compute.":[137],"The":[138],"source":[139],"it":[144,159],"may":[145],"intractable":[147],"instantiate":[149],"relation":[151],"defined":[152],"a":[154,189],"formula,":[156],"simply":[157],"because":[158],"has":[160,188],"an":[161],"exponential":[162],"number":[163,191],"tuples.":[165],"we":[167],"able":[169],"establish":[171],"general":[172],"bounds.":[174],"In":[175],"UCQs":[177],"evaluated":[180],"polynomial":[182],"delay,":[183],"provided":[184],"every":[186],"CQ":[187],"bounded":[190],"atoms":[193],"(while":[194],"unions":[195],"projection":[197],"arbitrary).":[200],"Furthermore,":[201],"UCQ":[202],"evaluation":[203],"solvable":[205],"FPT":[207],"(Fixed-Parameter":[208],"Tractable)":[209],"delay":[210],"when":[211],"parameter":[213],"size":[216],"UCQ.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
