{"id":"https://openalex.org/W2063985934","doi":"https://doi.org/10.1145/1735886.1735890","title":"Inference of concise regular expressions and DTDs","display_name":"Inference of concise regular expressions and DTDs","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2063985934","doi":"https://doi.org/10.1145/1735886.1735890","mag":"2063985934"},"language":"en","primary_location":{"id":"doi:10.1145/1735886.1735890","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1735886.1735890","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","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/A5010031379","display_name":"Geert Jan Bex","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]},{"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"],"is_corresponding":true,"raw_author_name":"Geert Jan Bex","raw_affiliation_strings":["Hasselt University and Transnational University of Limburg, Belgium","Hasselt University and transnational University of Limburg, Belgium"],"affiliations":[{"raw_affiliation_string":"Hasselt University and Transnational University of Limburg, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]},{"raw_affiliation_string":"Hasselt University and transnational University of Limburg, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022264843","display_name":"Frank Neven","orcid":"https://orcid.org/0000-0002-7143-1903"},"institutions":[{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]},{"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"],"is_corresponding":false,"raw_author_name":"Frank Neven","raw_affiliation_strings":["Hasselt University and Transnational University of Limburg, Belgium","Hasselt University and transnational University of Limburg, Belgium"],"affiliations":[{"raw_affiliation_string":"Hasselt University and Transnational University of Limburg, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]},{"raw_affiliation_string":"Hasselt University and transnational University of Limburg, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031710345","display_name":"Thomas Schwentick","orcid":"https://orcid.org/0000-0002-1062-922X"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Schwentick","raw_affiliation_strings":["Dortmund University, Germany"],"affiliations":[{"raw_affiliation_string":"Dortmund University, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022558461","display_name":"Stijn Vansummeren","orcid":"https://orcid.org/0000-0001-7793-9049"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stijn Vansummeren","raw_affiliation_strings":["Universit\u00e9 Libre de Bruxelles, Belgium"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Libre de Bruxelles, Belgium","institution_ids":["https://openalex.org/I132053463"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010031379"],"corresponding_institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"],"apc_list":null,"apc_paid":null,"fwci":17.223,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.99227503,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"35","issue":"2","first_page":"1","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9995999932289124,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9995999932289124,"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":0.9987999796867371,"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":0.9984999895095825,"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":0.8450456857681274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8080776929855347},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.623076319694519},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5405735969543457},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5208004713058472},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49161773920059204},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.4672403633594513},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4360077381134033},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4213467240333557},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35370853543281555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24941956996917725},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2188113033771515}],"concepts":[{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.8450456857681274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080776929855347},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.623076319694519},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5405735969543457},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5208004713058472},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49161773920059204},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.4672403633594513},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4360077381134033},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4213467240333557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35370853543281555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24941956996917725},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2188113033771515},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1735886.1735890","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1735886.1735890","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.6881","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.6881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://fox7.eu/wp-content/uploads/neven-inference10.pdf","raw_type":"text"},{"id":"pmh:oai:dipot.ulb.ac.be:2013/72249","is_oa":false,"landing_page_url":"http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/72249","pdf_url":null,"source":{"id":"https://openalex.org/S4306401063","display_name":"D\u00e9p\u00f4t institutionnel de l'Universit\u00e9 libre de Bruxelles (Universit\u00e9 Libre de Bruxelles)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I132053463","host_organization_name":"Universit\u00e9 Libre de Bruxelles","host_organization_lineage":["https://openalex.org/I132053463"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM transactions on database systems, 35 (2","raw_type":"info:ulb-repo/semantics/openurl/article"},{"id":"pmh:oai:documentserver.uhasselt.be:1942/11342","is_oa":false,"landing_page_url":"http://hdl.handle.net/1942/11342","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G582362311","display_name":null,"funder_award_id":"FP7-ICT-233599","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W22428428","https://openalex.org/W26772505","https://openalex.org/W49766897","https://openalex.org/W101493532","https://openalex.org/W1482220696","https://openalex.org/W1489016619","https://openalex.org/W1508355880","https://openalex.org/W1519440323","https://openalex.org/W1542184482","https://openalex.org/W1556528519","https://openalex.org/W1595778895","https://openalex.org/W1607995248","https://openalex.org/W1662087476","https://openalex.org/W1908950999","https://openalex.org/W1912713675","https://openalex.org/W1969005071","https://openalex.org/W1971749487","https://openalex.org/W1979101142","https://openalex.org/W1983524017","https://openalex.org/W1985578047","https://openalex.org/W2002089154","https://openalex.org/W2006061474","https://openalex.org/W2008896880","https://openalex.org/W2024295392","https://openalex.org/W2030033535","https://openalex.org/W2031469331","https://openalex.org/W2032973786","https://openalex.org/W2047303298","https://openalex.org/W2056905497","https://openalex.org/W2057185776","https://openalex.org/W2057841333","https://openalex.org/W2061079066","https://openalex.org/W2064287550","https://openalex.org/W2066064214","https://openalex.org/W2080666934","https://openalex.org/W2080947572","https://openalex.org/W2082135413","https://openalex.org/W2099540492","https://openalex.org/W2100674109","https://openalex.org/W2107741633","https://openalex.org/W2108014443","https://openalex.org/W2108350934","https://openalex.org/W2108543348","https://openalex.org/W2109464129","https://openalex.org/W2109486375","https://openalex.org/W2123229843","https://openalex.org/W2124391840","https://openalex.org/W2125822162","https://openalex.org/W2125838338","https://openalex.org/W2134356404","https://openalex.org/W2136451095","https://openalex.org/W2137580272","https://openalex.org/W2137692226","https://openalex.org/W2142529424","https://openalex.org/W2142662777","https://openalex.org/W2152335717","https://openalex.org/W2154475850","https://openalex.org/W2164765168","https://openalex.org/W2169131377","https://openalex.org/W2569219525","https://openalex.org/W2737168042","https://openalex.org/W2998389348","https://openalex.org/W3104723580","https://openalex.org/W4230868072","https://openalex.org/W4233419801","https://openalex.org/W4249965121"],"related_works":["https://openalex.org/W2563334590","https://openalex.org/W3094387502","https://openalex.org/W2922478741","https://openalex.org/W2119827098","https://openalex.org/W2101092231","https://openalex.org/W2055243143","https://openalex.org/W2381031055","https://openalex.org/W2366070815","https://openalex.org/W2952363982","https://openalex.org/W2033575315"],"abstract_inverted_index":{"We":[0,32,181],"consider":[1],"the":[2,46,52,62,93,103,135],"problem":[3,19],"of":[4,16,36,55,64,79,117,126,173],"inferring":[5],"a":[6,13,18,76,88,107,122,160,171],"concise":[7,25,37],"Document":[8],"Type":[9],"Definition":[10],"(DTD)":[11],"for":[12,75],"given":[14,77],"set":[15,78],"XML-documents,":[17],"that":[20,70,85,153,165,183],"basically":[21],"reduces":[22],"to":[23,87,110,146],"learning":[24,162],"regular":[26,38,42,48,111,151],"expressions":[27,43,49,56,152],"from":[28],"positive":[29],"examples":[30],"strings.":[31],"identify":[33],"two":[34],"classes":[35],"expressions\u2014the":[39],"single":[40],"occurrence":[41],"(SOREs)":[44],"and":[45,82],"chain":[47],"(CHAREs)\u2014that":[50],"capture":[51],"far":[53],"majority":[54],"used":[57],"in":[58],"practical":[59],"DTDs.":[60],"For":[61],"inference":[63],"SOREs":[65],"we":[66,105,158],"present":[67],"several":[68],"algorithms":[69,149],"first":[71],"infer":[72],"an":[73,178],"automaton":[74,86,94,109,179],"example":[80],"strings":[81],"then":[83],"translate":[84],"corresponding":[89],"SORE,":[90],"possibly":[91],"repairing":[92],"when":[95,134],"no":[96],"equivalent":[97],"SORE":[98],"can":[99],"be":[100],"found.":[101],"In":[102],"process,":[104],"introduce":[106,159],"novel":[108,161],"expression":[112],"rewrite":[113],"technique":[114],"which":[115],"is":[116,129,137],"independent":[118],"interest.":[119],"When":[120],"only":[121],"very":[123,186,193],"small":[124,194],"amount":[125],"XML":[127],"data":[128,136],"available,":[130],"however":[131],"(for":[132],"instance":[133],"generated":[138],"by":[139,144],"Web":[140],"service":[141],"requests":[142],"or":[143],"answers":[145],"queries),":[147],"these":[148],"produce":[150],"are":[154],"too":[155],"specific.":[156],"Therefore,":[157],"algorithm":[163],"crx":[164,184],"directly":[166],"infers":[167],"CHAREs":[168],"(which":[169],"form":[170],"subclass":[172],"SOREs)":[174],"without":[175],"going":[176],"through":[177],"representation.":[180],"show":[182],"performs":[185],"well":[187],"within":[188],"its":[189],"target":[190],"class":[191],"on":[192],"datasets.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":16}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}